[{"data":1,"prerenderedAt":1261},["ShallowReactive",2],{"blog-articles-for-slug-most-enterprise-ai-never-leaves-the-pilot":3},{"articles":4,"publishedKeys":1260},[5,25,40,58,72,89,107,122,138,151,169,186,201,218,235,252,270,287,306,320,336,355,369,382,400,416,431,444,456,471,484,500,515,527,545,558,574,589,606,624,640,655,672,687,925,938,950,964,977,993,1011,1025,1039,1052,1065,1080,1095,1110,1125,1139,1154,1168,1185,1201,1218,1232,1247],{"id":6,"title":7,"author":8,"category":9,"date":10,"description":11,"extension":12,"featured":13,"image":14,"meta":15,"metaDescription":16,"metaTitle":17,"navigation":18,"path":19,"seo":20,"stem":21,"tags":22,"__hash__":23,"__readTime":24},"blog\u002Fblog\u002F15-advanced-features-that-turn-your-chatbots-into-gold.md","15 advanced features that turn your chatbots into gold","Len Debets","Product Features","2020-08-20","A chatbot that answers a few FAQs is easy to build. Here are 15 advanced features that move your chatbot from a simple Q&A tool to something your business depends on.","md",false,"\u002Fblog\u002F3327590-300x200.jpg",{},"A chatbot that answers a few FAQs is easy to build. These 15 advanced features turn it into something your business actually depends on.","15 Advanced Chatbot Features Worth Building",true,"\u002Fblog\u002F15-advanced-features-that-turn-your-chatbots-into-gold",{"title":7,"description":11},"blog\u002F15-advanced-features-that-turn-your-chatbots-into-gold",[],"2Ub1RORB7pfLmgONRupxdg1IOzCXXrqje5046hBrjbA","3 min read",{"id":26,"title":27,"author":8,"category":28,"date":29,"description":30,"extension":12,"featured":13,"image":31,"meta":32,"metaDescription":33,"metaTitle":34,"navigation":18,"path":35,"seo":36,"stem":37,"tags":34,"__hash__":38,"__readTime":39},"blog\u002Fblog\u002F9-things-i-hate-about-ai.md","9 Things I Really Hate About AI","AI Technology","2025-05-12","I think it's great that technology is so embedded in our daily lives. It helps us get knowledge faster, finish tasks more efficiently, gives us inspiration, and occasionally scares the hell out of us with those crazy (fake) videos. I help a lot of companies implement AI, so in the end it pays my bills. But after spending a ridiculous amount of time with all these new technologies, it's time to write down the things I really hate about AI.","\u002Fblog\u002F1747039600744.png",{},"I help companies implement AI and it pays my bills. After a ridiculous amount of time with these tools, here are the 9 things I really hate about AI.",null,"\u002Fblog\u002F9-things-i-hate-about-ai",{"title":27,"description":30},"blog\u002F9-things-i-hate-about-ai","x3Pfa3upWCZeJg3PuHjgqCGhd8w1PdeVtVLlYXYmDZk","7 min read",{"id":41,"title":42,"author":8,"category":28,"date":43,"description":44,"extension":12,"featured":13,"image":45,"meta":46,"metaDescription":47,"metaTitle":34,"navigation":18,"path":48,"seo":49,"stem":50,"tags":51,"__hash__":57,"__readTime":39},"blog\u002Fblog\u002Fa-conversation-is-not-a-case.md","A Conversation Is Not a Case","2026-10-06","The 95 percent pilot failure stat is making the rounds again, this time with a diagnosis I actually agree with: chatbots automate sessions, but a bank runs cases. Why the unit of work decides whether your AI survives production, and the day eight test that shows which one you built.","\u002Fblog\u002Fblits-session-vs-case-hero.png",{},"Chatbots automate sessions, but a bank runs cases. Why the unit of work decides whether your AI survives production, and the day eight test.","\u002Fblog\u002Fa-conversation-is-not-a-case",{"title":42,"description":44},"blog\u002Fa-conversation-is-not-a-case",[52,53,54,55,56],"agentic ai","enterprise ai","ai strategy","case management","banking","IJO6dpCGt7jjLgV0FvRqM03LiuYvz779pb3P824edrk",{"id":59,"title":60,"author":8,"category":61,"date":62,"description":63,"extension":12,"featured":13,"image":64,"meta":65,"metaDescription":66,"metaTitle":34,"navigation":18,"path":67,"seo":68,"stem":69,"tags":34,"__hash__":70,"__readTime":71},"blog\u002Fblog\u002Fa-day-in-the-life-of-ai-scale-up.md","A day in the life of an AI scale-up","Company News","2025-02-24","AI moves at breakneck speed, and being the CTO of a fast growing scaleup in it is a great job. It is also not for the faint of heart. We work on large language models (LLMs), chatbots, digital humans and voicebots, and most of our customers are large banks, international companies and professional enterprises.","\u002Fblog\u002F1740065406903.png",{},"What it is like to be CTO of a fast growing AI scaleup that builds LLMs, chatbots, digital humans and voicebots for banks and large enterprises.","\u002Fblog\u002Fa-day-in-the-life-of-ai-scale-up",{"title":60,"description":63},"blog\u002Fa-day-in-the-life-of-ai-scale-up","TiXNFQdXhajzvfAWWOBvKGpeG5WGq1A5v2MXtyvF-w0","5 min read",{"id":73,"title":74,"author":8,"category":28,"date":75,"description":76,"extension":12,"featured":13,"image":77,"meta":78,"metaDescription":34,"metaTitle":79,"navigation":18,"path":80,"seo":81,"stem":82,"tags":83,"__hash__":87,"__readTime":88},"blog\u002Fblog\u002Fagentic-ai-dialects-and-the-voice-quality-gap.md","Agentic AI Languages and Dialects: Why Voice Quality Is Still the Hard Part","2026-04-10","Agentic systems promise autonomous workflows, but speech and dialect quality fail first. Why Arabic, Turkish, Chinese and more run into the same gap.","\u002Fblog\u002Fdialect.jpg",{},"Agentic AI Dialects and the Voice Quality Gap","\u002Fblog\u002Fagentic-ai-dialects-and-the-voice-quality-gap",{"title":74,"description":76},"blog\u002Fagentic-ai-dialects-and-the-voice-quality-gap",[52,84,85,86,53],"speech ai","dialects","multilingual ai","e0ZVAmJonwtrh9SFlhMirDWXgPrHQL-HItCKsC7cOFA","14 min read",{"id":90,"title":91,"author":8,"category":28,"date":92,"description":93,"extension":12,"featured":13,"image":94,"meta":95,"metaDescription":96,"metaTitle":97,"navigation":18,"path":98,"seo":99,"stem":100,"tags":101,"__hash__":105,"__readTime":106},"blog\u002Fblog\u002Fagentic-ai-on-premises-what-to-ask-before-you-choose.md","Agentic AI On Premises: What to Ask Before You Choose a Platform","2026-12-08","Many vendors say their agentic AI platform runs on premises. Fewer can show a private AI system that runs entirely inside your own data center, models included. What has to be inside, which models you can host yourself, what it costs, and the six questions I would ask every vendor.","\u002Fblog\u002Fblits-agentic-ai-on-premises-hero.png",{},"Looking for an agentic AI platform you can run on premises? What has to run inside, which models you can host yourself, what it costs and six vendor questions.","Agentic AI Platform On Premises: What to Ask First","\u002Fblog\u002Fagentic-ai-on-premises-what-to-ask-before-you-choose",{"title":91,"description":93},"blog\u002Fagentic-ai-on-premises-what-to-ask-before-you-choose",[102,52,103,104,56],"on premises ai","data residency","ai deployment","vU7JiBJPEX9OkswERPagpyR5w-awZvCX1nyp3HKuo3w","8 min read",{"id":108,"title":109,"author":8,"category":9,"date":110,"description":111,"extension":12,"featured":13,"image":112,"meta":113,"metaDescription":34,"metaTitle":34,"navigation":18,"path":114,"seo":115,"stem":118,"tags":119,"__hash__":120,"__readTime":121},"blog\u002Fblog\u002Fagentic-ai-studio-for-enterprises.md","Introducing the Agentic AI Studio for Enterprises","2026-02-17","Introducing Agentic AI Studio: a platform agnostic, enterprise ready way to design and run autonomous workflows with your own models and data.","\u002Fimages\u002Fblits-agentic-studio.png",{},"\u002Fblog\u002Fagentic-ai-studio-for-enterprises",{"title":116,"description":117},"Introducing the Agentic AI Studio for Enterprise","Self running AI agents are changing how enterprise processes work. We're releasing the Agentic AI Studio for Blits.ai, a platform agnostic, enterprise ready way to design and run autonomous workflows with your own models and data.","blog\u002Fagentic-ai-studio-for-enterprises",[],"Iko_ojcsirkF69bOvZZlrkHTDh-kRPk1Jr-wTgc8-no","9 min read",{"id":123,"title":124,"author":8,"category":28,"date":125,"description":126,"extension":12,"featured":13,"image":127,"meta":128,"metaDescription":129,"metaTitle":130,"navigation":18,"path":131,"seo":132,"stem":133,"tags":134,"__hash__":137,"__readTime":71},"blog\u002Fblog\u002Fagentic-ai-vs-generative-ai.md","Agentic AI vs Generative AI: What Changes When AI Starts Doing the Work","2026-10-23","Generative AI writes. Agentic AI does. That sounds like a small step, but it changes what can go wrong, what you need to govern and how you measure success. The real difference between agentic AI and generative AI, why most agentic projects stall, and what the ones in production have in common.","\u002Fblog\u002Fblits-agentic-vs-generative-hero.png",{},"Agentic AI vs generative AI explained for enterprises: the real difference, why most agentic projects stall, what BNY runs in production and what to govern.","Agentic AI vs Generative AI: What Really Changes","\u002Fblog\u002Fagentic-ai-vs-generative-ai",{"title":124,"description":126},"blog\u002Fagentic-ai-vs-generative-ai",[52,135,53,54,136],"generative ai","ai governance","0m-VgMpeulu0O6n741Xc_JzXzqKjxZfQNWYe0R9Qjow",{"id":139,"title":140,"author":8,"category":28,"date":141,"description":142,"extension":12,"featured":13,"image":143,"meta":144,"metaDescription":34,"metaTitle":145,"navigation":18,"path":146,"seo":147,"stem":148,"tags":149,"__hash__":150,"__readTime":71},"blog\u002Fblog\u002Fagentic-pay-and-the-moment-ai-was-allowed-to-spend-money-by-itself.md","Agentic Pay and the Moment AI Was Allowed to Spend Money","2026-01-11","Why giving AI agents controlled access to payments changes a lot, and why the open question is who designs the rules they spend under.","\u002Fimages\u002Fblits-agentic-pay.jpg",{},"Agentic Pay: When AI Was Allowed to Spend Money","\u002Fblog\u002Fagentic-pay-and-the-moment-ai-was-allowed-to-spend-money-by-itself",{"title":140,"description":142},"blog\u002Fagentic-pay-and-the-moment-ai-was-allowed-to-spend-money-by-itself",[],"njF5BBkPJMdXpGxOH8XGMC0IglTZeDkrA99y3UB_x3c",{"id":152,"title":153,"author":154,"category":28,"date":155,"description":156,"extension":12,"featured":13,"image":157,"meta":158,"metaDescription":159,"metaTitle":160,"navigation":18,"path":161,"seo":162,"stem":163,"tags":164,"__hash__":168,"__readTime":39},"blog\u002Fblog\u002Fagentic-workflows-explained.md","Agentic Workflows Explained, With Real Examples From Banking and Insurance","Coen Doolaard","2026-10-30","An agentic workflow lets AI work through a task in steps: it plans, uses your systems, checks its own work and hands the important decision to a person. A practical explanation for banks and insurers, with the design patterns, real production examples and a checklist before you build.","\u002Fblog\u002Fblits-agentic-workflows-hero.png",{},"What agentic workflows are, how they differ from AI agents, the four design patterns behind them, and what banks and insurers already run in production.","Agentic Workflows Explained: Examples From Banking and Insurance","\u002Fblog\u002Fagentic-workflows-explained",{"title":153,"description":156},"blog\u002Fagentic-workflows-explained",[165,52,56,166,167],"agentic workflows","insurance","ai architecture","W0-tqWrSk_0dyRYFIwv9EsNTXob0h-c4aARwuDABn78",{"id":170,"title":171,"author":8,"category":9,"date":172,"description":173,"extension":12,"featured":13,"image":174,"meta":175,"metaDescription":176,"metaTitle":177,"navigation":18,"path":178,"seo":179,"stem":180,"tags":181,"__hash__":185,"__readTime":121},"blog\u002Fblog\u002Fagents-that-ask-remember-and-show-their-work.md","Agents That Ask, Remember and Show Their Work: What's New in Blits.ai","2026-10-22","Release 5.9 is about one thing: giving AI agents real work without losing control of it. Agents now ask for approval before risky actions, record every decision, publish only after their tests pass, remember returning customers within strict limits and work with other companies' agents over the open A2A protocol. What each feature does, and how it works under the hood.","\u002Fblog\u002Fblits-v59-features-hero.png",{},"Blits.ai release 5.9: approval per tool, a decision log per conversation, tested publishing, memory per customer, the A2A protocol and provider control.","What's New in Blits.ai: Agents That Ask and Show Their Work","\u002Fblog\u002Fagents-that-ask-remember-and-show-their-work",{"title":171,"description":173},"blog\u002Fagents-that-ask-remember-and-show-their-work",[182,52,136,183,184],"product update","human in the loop","a2a","KG_IqJdr5mhRh9ZUxFQ9BrDqSPlcQipq0nQm0zBAGE8",{"id":187,"title":188,"author":8,"category":28,"date":189,"description":190,"extension":12,"featured":13,"image":191,"meta":192,"metaDescription":193,"metaTitle":188,"navigation":18,"path":194,"seo":195,"stem":196,"tags":197,"__hash__":200,"__readTime":71},"blog\u002Fblog\u002Fai-agency-or-ai-platform.md","AI Agency or AI Platform? How Enterprises Should Choose","2026-11-10","Hire an AI agency, buy a SaaS tool, build it yourself, or work with a platform? Every enterprise faces that choice, and the data is starting to show which path reaches production. Why custom built AI so often gets abandoned, and the questions that tell you whether you're buying a project or a capability.","\u002Fblog\u002Fblits-ai-agency-vs-platform-hero.png",{},"Should you hire an AI agency, buy software or build in house? What the data says about build vs buy, why custom AI gets abandoned, and the questions to ask.","\u002Fblog\u002Fai-agency-or-ai-platform",{"title":188,"description":190},"blog\u002Fai-agency-or-ai-platform",[198,53,199,54,52],"ai agency","build vs buy","3kzZhIokvhURrrQMls8Wry1YOEDElpvbqqdDBOP_BpM",{"id":202,"title":203,"author":154,"category":28,"date":204,"description":205,"extension":12,"featured":13,"image":206,"meta":207,"metaDescription":208,"metaTitle":209,"navigation":18,"path":210,"seo":211,"stem":212,"tags":213,"__hash__":217,"__readTime":106},"blog\u002Fblog\u002Fai-agent-governance-who-authorizes-what.md","AI Agent Governance: Who Authorizes an Agent to Do What?","2026-12-11","Most organizations now have AI agents that act in their systems, and few can say which agent is allowed to do what, or who answers for it. A practical governance framework for AI agents: four questions for every action, an owner for every agent, and what regulators already expect.","\u002Fblog\u002Fblits-ai-agent-governance-hero.png",{},"AI agent governance in plain terms: identity, permissions, approval and records for every agent action, who owns an agent, and what the EU AI Act expects.","AI Agent Governance: Who Authorizes What?","\u002Fblog\u002Fai-agent-governance-who-authorizes-what",{"title":203,"description":205},"blog\u002Fai-agent-governance-who-authorizes-what",[136,214,215,216,56],"ai agents","agent security","eu ai act","ZYHt-2M1pC4_ScgYNY_Ftdr9umZ4WxJfsaNll1XEIPc",{"id":219,"title":220,"author":154,"category":28,"date":221,"description":222,"extension":12,"featured":13,"image":223,"meta":224,"metaDescription":225,"metaTitle":220,"navigation":18,"path":226,"seo":227,"stem":228,"tags":229,"__hash__":234,"__readTime":106},"blog\u002Fblog\u002Fai-call-center-voice-agents-answer-first.md","AI Call Center: What Changes When Voice Agents Answer First","2026-11-17","An AI call center is not a call center without people. It is one where a voice agent answers first, AI supports the people who handle the harder calls, and every conversation feeds quality. What changes on the floor, what the public record shows, and where the first projects went wrong.","\u002Fblog\u002Fblits-ai-call-center-hero.png",{},"What an AI call center looks like in 2026: voice agents on the first line, AI assist for human agents, every call reviewed, and the mistakes to avoid.","\u002Fblog\u002Fai-call-center-voice-agents-answer-first",{"title":220,"description":222},"blog\u002Fai-call-center-voice-agents-answer-first",[230,231,232,233,56],"ai call center","voice agents","contact center","customer experience","2DBGhBP-vQqxS7vLMSEe6pm0nww6YYyGqSblfKRgCNI",{"id":236,"title":237,"author":154,"category":28,"date":238,"description":239,"extension":12,"featured":13,"image":240,"meta":241,"metaDescription":242,"metaTitle":243,"navigation":18,"path":244,"seo":245,"stem":246,"tags":247,"__hash__":250,"__readTime":251},"blog\u002Fblog\u002Fai-customer-service-what-actually-works.md","AI Customer Service in 2026: What Actually Works, and What the Benchmarks Hide","2026-10-27","AI customer service works, but not in the way most dashboards suggest. Public deployments show a median containment rate of two thirds, yet contacts drop by only a fifth. What separates the projects that deliver from the ones that quietly get reversed, and what to ask before you buy.","\u002Fblog\u002Fblits-ai-customer-service-hero.png",{},"What AI customer service really delivers in 2026: public benchmarks, the reversals at Klarna and CBA, and what to ask before you buy AI customer service software.","AI Customer Service in 2026: What Actually Works","\u002Fblog\u002Fai-customer-service-what-actually-works",{"title":237,"description":239},"blog\u002Fai-customer-service-what-actually-works",[248,233,232,249,56],"ai customer service","conversational ai","MTic7KjEg4zMr-2JCJeEX9masmR3GM0ZsGw8b4NhwsE","6 min read",{"id":253,"title":254,"author":154,"category":28,"date":255,"description":256,"extension":12,"featured":13,"image":257,"meta":258,"metaDescription":259,"metaTitle":260,"navigation":18,"path":261,"seo":262,"stem":263,"tags":264,"__hash__":269,"__readTime":71},"blog\u002Fblog\u002Fai-in-insurance-use-cases-in-production.md","AI in Insurance: The Use Cases Already Running in Production","2026-11-03","AI in insurance is no longer an experiment. Of 117 public insurance deployments we track, 103 run in production or at scale. Where insurers use AI today, what the leaders report, what regulators expect, and why most of the industry is still stuck at the pilot stage.","\u002Fblog\u002Fblits-ai-insurance-hero.png",{},"Where insurers already run AI in production: claims, fraud, underwriting and customer service, with results from Allianz, Zurich, Ping An, Lemonade and Aviva.","AI in Insurance: Use Cases Already in Production","\u002Fblog\u002Fai-in-insurance-use-cases-in-production",{"title":254,"description":256},"blog\u002Fai-in-insurance-use-cases-in-production",[265,266,267,52,268],"ai insurance","claims automation","underwriting","customer service","7l-cJ6cSc8Ox8EmQ6T0Q2DdDPy6FW5cLHrD5gx4zvq0",{"id":271,"title":272,"author":8,"category":28,"date":273,"description":274,"extension":12,"featured":13,"image":275,"meta":276,"metaDescription":34,"metaTitle":277,"navigation":18,"path":278,"seo":279,"stem":280,"tags":281,"__hash__":285,"__readTime":286},"blog\u002Fblog\u002Fai-spending-delegation-policies-without-losing-control.md","You Already Know How to Delegate Spending. Now Write the Mandate for an Agent.","2026-03-31","You already delegate spending with cards, POs and dual sign off. An AI agent is a new delegate. How to write its mandate, and where the analogy breaks.","\u002Fimages\u002Fblog-ai-policies.png",{},"Writing the Spending Mandate for an AI Agent","\u002Fblog\u002Fai-spending-delegation-policies-without-losing-control",{"title":272,"description":274},"blog\u002Fai-spending-delegation-policies-without-losing-control",[282,136,53,283,284],"agentic payments","delegation","payments","3UinRxWgwEV2xzGlI2-7RNVqr-WksZKCQs46SjskL6E","11 min read",{"id":288,"title":289,"author":290,"category":28,"date":291,"description":292,"extension":12,"featured":13,"image":293,"meta":294,"metaDescription":295,"metaTitle":296,"navigation":18,"path":297,"seo":298,"stem":299,"tags":300,"__hash__":305,"__readTime":251},"blog\u002Fblog\u002Fai-voice-agents-for-enterprises.md","AI Voice Agents for Enterprises: Latency, Dialects and Compliance","Yuri Ihnatov","2026-11-06","An AI voice agent can answer every call at once, in many languages, at any hour. Whether customers accept it comes down to three things that rarely show up in a demo: how fast it answers, whether it understands the way they actually speak, and whether it follows the rules for disclosure, consent and authentication.","\u002Fblog\u002Fblits-ai-voice-agents-hero.png",{},"What enterprises need from an AI voice agent: response times people accept, speech recognition that works for every dialect, and the rules on disclosure and fraud.","AI Voice Agents for Enterprises: Latency, Dialects, Compliance","\u002Fblog\u002Fai-voice-agents-for-enterprises",{"title":289,"description":292},"blog\u002Fai-voice-agents-for-enterprises",[301,302,232,303,304],"ai voice agents","voice ai","speech recognition","compliance","d_UKYWERVh6gaVcc2b1uSw1fBPQO39q6odNaVlq-jC8",{"id":307,"title":308,"author":309,"category":310,"date":311,"description":312,"extension":12,"featured":13,"image":313,"meta":314,"metaDescription":34,"metaTitle":34,"navigation":18,"path":315,"seo":316,"stem":317,"tags":34,"__hash__":318,"__readTime":319},"blog\u002Fblog\u002Fbenchmarking-conversational-ai-whitepaper.md","Benchmarking Conversational AI: Whitepaper","Paul Coerkamp","Research","2022-08-25","Our research into conversational AI performance shows clear gains in chatbot effectiveness across several industries and use cases.","\u002Fblog\u002FCover-Benchmarking-Conversational-AI-Whitepaper.jpg",{},"\u002Fblog\u002Fbenchmarking-conversational-ai-whitepaper",{"title":308,"description":312},"blog\u002Fbenchmarking-conversational-ai-whitepaper","nfDZr9Jn-Owi4BXRnkyz9owwZBZPJNEZp01hok5_J-Y","2 min read",{"id":321,"title":322,"author":309,"category":28,"date":323,"description":324,"extension":12,"featured":13,"image":325,"meta":326,"metaDescription":34,"metaTitle":327,"navigation":18,"path":328,"seo":329,"stem":330,"tags":331,"__hash__":335,"__readTime":286},"blog\u002Fblog\u002Fbenchmarking-tts-for-customers-beyond-mos-and-demos.md","How to Score a TTS Bake-Off When the Demo Is Lying to You","2026-04-08","MOS has saturated and demos are hand tuned. The lab protocol we use to grade TTS on latency, jitter, entity accuracy, barge in and cloning risk.","\u002Fimages\u002Fblog-benchmark.png",{},"Benchmarking TTS Beyond MOS and Demos","\u002Fblog\u002Fbenchmarking-tts-for-customers-beyond-mos-and-demos",{"title":322,"description":324},"blog\u002Fbenchmarking-tts-for-customers-beyond-mos-and-demos",[332,302,333,334,231],"tts","benchmarking","ai evaluation","DqEdE-KfCVokeZ_dDpJUjEgDp0i4PzcbAYQtN1PjJJA",{"id":337,"title":338,"author":8,"category":339,"date":340,"description":341,"extension":12,"featured":13,"image":342,"meta":343,"metaDescription":344,"metaTitle":345,"navigation":18,"path":346,"seo":347,"stem":348,"tags":349,"__hash__":354,"__readTime":251},"blog\u002Fblog\u002Fblits-ai-bug-hunt-game-2026-results.md","What We Learned from Turning Bug Hunting into a Game at Blits.ai","Product & Culture","2026-01-08","In the first week of January we turned quality assurance into a Bug Hunt Game. This is what happened when we put Hunters, Fixers and a Judge on a shared leaderboard powered by Azure DevOps.","\u002Fimages\u002Fblits-bounty-bug-game.png",{},"In January we turned quality assurance into a Bug Hunt Game, with Hunters, Fixers and a Judge on one Azure DevOps leaderboard. Here is what we learned.","Bug Hunting as a Game: What We Learned","\u002Fblog\u002Fblits-ai-bug-hunt-game-2026-results",{"title":338,"description":341},"blog\u002Fblits-ai-bug-hunt-game-2026-results",[350,351,352,353],"quality","devops","culture","experimentation","mWTOkdFZW8DPX4ik3aCDl_en1vapZ9YS-nCMmu1FFQU",{"id":356,"title":357,"author":309,"category":61,"date":358,"description":359,"extension":12,"featured":13,"image":360,"meta":361,"metaDescription":34,"metaTitle":362,"navigation":13,"path":363,"seo":364,"stem":365,"tags":366,"__hash__":367,"__readTime":368},"blog\u002Fblog\u002Fblits-ai-joins-llms4eu-project.md","Blits.ai joins the EU-funded LLMs4EU project","2026-01-05","Blits.ai joins LLMs4EU. Who builds large language models, on what data, and under which European values and regulations, and why that matters now.","\u002Fblog\u002Fllms4eu-blog-image.png",{},"LLMs4EU: Blits.ai Joins the European LLM Effort","\u002Fblog\u002Fblits-ai-joins-llms4eu-project",{"title":357,"description":359},"blog\u002Fblits-ai-joins-llms4eu-project",[],"M97zWsJIDe49eUcICylhQBw6aT5EKnTNuNWbZw178Pc","4 min read",{"id":370,"title":371,"author":8,"category":28,"date":372,"description":373,"extension":12,"featured":13,"image":374,"meta":375,"metaDescription":376,"metaTitle":377,"navigation":18,"path":378,"seo":379,"stem":380,"tags":34,"__hash__":381,"__readTime":71},"blog\u002Fblog\u002Fbusiness-predictions-chatgpt.md","Business predictions based on my years of experience with ChatGPT and its predecessors","2023-02-20","Over 5 years ago I started a chatbot (ad)venture called Blits.ai. My reason was simple: I believed the way we humans deal with data would turn into a conversation. Now that ChatGPT (generative AI) is all over the news and every LinkedIn feed, more and more people are reaching the same conclusion. Great! We're clearly not there yet, though.","\u002Fblog\u002F1675857460197.jpeg",{},"Five years after starting Blits.ai, my business predictions for ChatGPT and generative AI: where conversations with data are heading, and what is missing.","ChatGPT and Business: My Predictions","\u002Fblog\u002Fbusiness-predictions-chatgpt",{"title":371,"description":373},"blog\u002Fbusiness-predictions-chatgpt","26eZfqYo1gr5l1hXYbn1uJPqnvLUXu4T4vCAb5Gy39c",{"id":383,"title":384,"author":154,"category":28,"date":385,"description":386,"extension":12,"featured":13,"image":387,"meta":388,"metaDescription":389,"metaTitle":390,"navigation":18,"path":391,"seo":392,"stem":393,"tags":394,"__hash__":399,"__readTime":39},"blog\u002Fblog\u002Fcontact-center-automation-beyond-the-voice-bot.md","Contact Center Automation: Six Places Where AI Does the Work","2026-12-15","Most contact center automation projects start and stop at the bot that answers. The larger part of the work sits around the call: routing, helping the human agent, the summary afterwards, quality review and the follow up in the back office. Six places where AI does the work, what organizations report, and the rules that apply.","\u002Fblog\u002Fblits-contact-center-automation-hero.png",{},"Contact center automation is more than an AI phone system. Six places where AI does the work, from routing to back office follow up, with public results.","Contact Center Automation: Six Places for AI","\u002Fblog\u002Fcontact-center-automation-beyond-the-voice-bot",{"title":384,"description":386},"blog\u002Fcontact-center-automation-beyond-the-voice-bot",[395,396,397,268,398],"contact center automation","ai phone system","agent assist","telecom","2gNid7yjO7cAtcgLfb7Ajp5X291iNggc4RW4J2hW2vE",{"id":401,"title":402,"author":290,"category":28,"date":403,"description":404,"extension":12,"featured":13,"image":405,"meta":406,"metaDescription":407,"metaTitle":408,"navigation":18,"path":409,"seo":410,"stem":411,"tags":412,"__hash__":415,"__readTime":286},"blog\u002Fblog\u002Fconversational-ai-design-why-bad-bots-are-a-design-problem.md","Conversational AI Design: Why Bad Bots Are a Design Problem, Not a Model Problem","2026-10-21","Most chatbots that frustrate people run on perfectly capable models. What fails is the design: unclear goals, no boundaries, fallbacks that go nowhere and handoffs that lose the context. A practical guide in questions and answers, from the team that builds and tests these systems every day.","\u002Fblog\u002Fblits-conversation-design-hero.png",{},"A practical guide to conversational AI design: user goals, decision boundaries, fallback and human handoff, opening messages, tone, voice and measuring quality.","Conversational AI Design: A Practical Guide","\u002Fblog\u002Fconversational-ai-design-why-bad-bots-are-a-design-problem",{"title":402,"description":404},"blog\u002Fconversational-ai-design-why-bad-bots-are-a-design-problem",[249,413,414,302,233],"conversation design","chatbot ux","SYan43Yp4zcenD8JNZGc8XiID_yYDPGC44wjX9n9iGg",{"id":417,"title":418,"author":8,"category":28,"date":419,"description":420,"extension":12,"featured":13,"image":421,"meta":422,"metaDescription":423,"metaTitle":418,"navigation":18,"path":424,"seo":425,"stem":426,"tags":427,"__hash__":430,"__readTime":251},"blog\u002Fblog\u002Fdo-you-need-forward-deployed-engineers-to-run-ai-agents.md","Do You Need Forward Deployed Engineers to Run AI Agents?","2026-12-01","Forward deployed engineers are the delivery model of the moment in enterprise AI, and serious money is behind it. They solve a real problem. But what decides whether your AI agents survive isn't who builds the first one. It's what your own team can do on the day those engineers leave.","\u002Fblog\u002Fblits-forward-deployed-engineers-hero.png",{},"Forward deployed engineers are enterprise AI's favorite delivery model. When you need them, what you should own when they leave, and how to test a handover.","\u002Fblog\u002Fdo-you-need-forward-deployed-engineers-to-run-ai-agents",{"title":418,"description":420},"blog\u002Fdo-you-need-forward-deployed-engineers-to-run-ai-agents",[428,53,214,429,199],"forward deployed engineers","ai implementation","TVovOJbWvP1wW73yMN4Bk-LMgV7bHlngif-CtsEhOgA",{"id":432,"title":433,"author":309,"category":28,"date":434,"description":435,"extension":12,"featured":13,"image":436,"meta":437,"metaDescription":34,"metaTitle":438,"navigation":18,"path":439,"seo":440,"stem":441,"tags":442,"__hash__":443,"__readTime":368},"blog\u002Fblog\u002Feu-ai-act-2026-enterprise-readiness-checklist.md","EU AI Act 2026: The Enterprise AI Readiness Checklist Before August","2026-03-11","Most teams treat EU AI Act compliance as a legal side project. A checklist of what enterprises should implement now to avoid disruption and rework.","\u002Fimages\u002Fblog-eu-ai-act.png",{},"EU AI Act 2026: Enterprise Readiness Checklist","\u002Fblog\u002Feu-ai-act-2026-enterprise-readiness-checklist",{"title":433,"description":435},"blog\u002Feu-ai-act-2026-enterprise-readiness-checklist",[216,53,136,304],"rluJvoZAzD04WieClVwCsoj6r18ndtcHInhwIzsy0v4",{"id":445,"title":446,"author":8,"category":28,"date":447,"description":448,"extension":12,"featured":13,"image":449,"meta":450,"metaDescription":34,"metaTitle":451,"navigation":18,"path":452,"seo":453,"stem":454,"tags":34,"__hash__":455,"__readTime":106},"blog\u002Fblog\u002Ffeeding-llms-without-leaking-secrets.md","Feeding LLMs Without Leaking Secrets: A Guide for Companies On How To Add Your Company Data","2025-05-19","A plain guide for business teams on how to add your company data to an LLM safely, without leaking secrets, and the concepts behind it.","\u002Fblog\u002F1747588091563.png",{},"Feeding LLMs Without Leaking Company Secrets","\u002Fblog\u002Ffeeding-llms-without-leaking-secrets",{"title":446,"description":448},"blog\u002Ffeeding-llms-without-leaking-secrets","8IxE-B9QPvTgygMq-My29zKji23d5TeHn16xmfgIgYY",{"id":457,"title":458,"author":290,"category":459,"date":460,"description":461,"extension":12,"featured":13,"image":462,"meta":463,"metaDescription":34,"metaTitle":464,"navigation":18,"path":465,"seo":466,"stem":467,"tags":468,"__hash__":470,"__readTime":286},"blog\u002Fblog\u002Ffrom-johannesburg-five-signals-agentic-ai-enterprise-banking.md","From Johannesburg: Five Signals on Where Agentic AI Meets Enterprise Banking","Events","2026-07-15","Five takeaways from Mastercard's summit in Johannesburg: the technology is no longer the bottleneck, governance, trust and context are.","\u002Fblog\u002Ffive-signals-mastercard.png",{},"Five Signals on Agentic AI in Enterprise Banking","\u002Fblog\u002Ffrom-johannesburg-five-signals-agentic-ai-enterprise-banking",{"title":458,"description":461},"blog\u002Ffrom-johannesburg-five-signals-agentic-ai-enterprise-banking",[52,469,249,282,334],"enterprise banking","b_mlFIOndF2DPQRqZDiXZNvaVGRyPPI3P5jsTOTRhQY",{"id":472,"title":473,"author":154,"category":459,"date":474,"description":475,"extension":12,"featured":18,"image":476,"meta":477,"metaDescription":34,"metaTitle":478,"navigation":18,"path":479,"seo":480,"stem":481,"tags":482,"__hash__":483,"__readTime":251},"blog\u002Fblog\u002Ffrom-paris-to-rio-signals-and-where-enterprise-ai-is-heading.md","From Paris to Rio: Production Over Pilots, Substance Over Spectacle","2026-07-10","Signals from VivaTech and Web Summit Rio: production over pilots, substance over spectacle, and why your operating framework beats any one model.","\u002Fblog\u002Ffrom-paris-to-rio.png",{},"From Paris to Rio: Where Enterprise AI Is Heading","\u002Fblog\u002Ffrom-paris-to-rio-signals-and-where-enterprise-ai-is-heading",{"title":473,"description":475},"blog\u002Ffrom-paris-to-rio-signals-and-where-enterprise-ai-is-heading",[53,52,249,54,136],"6DzNE9FCbGcnNxwm9Du9-SwxJ5yh585XO0lPY3tLxng",{"id":485,"title":486,"author":309,"category":28,"date":487,"description":488,"extension":12,"featured":13,"image":489,"meta":490,"metaDescription":34,"metaTitle":491,"navigation":18,"path":492,"seo":493,"stem":494,"tags":495,"__hash__":498,"__readTime":499},"blog\u002Fblog\u002Ffrom-single-agent-to-multi-agent-systems-when-to-split-roles.md","Most Multi Agent Systems Are a Solution Looking for a Problem","2026-03-19","Start with one agent, and reach for multi agent only for parallel, read heavy work. The case against splitting too early, and how to do it right.","\u002Fimages\u002Fblog-multi-agent.png",{},"When to Split Into Multi Agent Systems","\u002Fblog\u002Ffrom-single-agent-to-multi-agent-systems-when-to-split-roles",{"title":486,"description":488},"blog\u002Ffrom-single-agent-to-multi-agent-systems-when-to-split-roles",[52,496,53,167,497],"multi agent systems","llm","jh1LuV8_t23zMxcRv4qwpkRBlmGeW4eHuFvagOyENQM","10 min read",{"id":501,"title":502,"author":8,"category":9,"date":503,"description":504,"extension":12,"featured":13,"image":505,"meta":506,"metaDescription":34,"metaTitle":507,"navigation":18,"path":508,"seo":509,"stem":512,"tags":513,"__hash__":514,"__readTime":71},"blog\u002Fblog\u002Ffrom-talking-to-doing-six-months-of-blits-ai-updates.md","Blits.ai Platform Update: Five Big Additions from the Last Six Months","2026-07-20","A plain roundup of five things we shipped this year: emotional voice, interactive cards, agentic tasks, in chat payments and response feedback.","\u002Fblog\u002Fblits-login-screen.png",{},"Blits.ai Platform Update: Six Months of Additions","\u002Fblog\u002Ffrom-talking-to-doing-six-months-of-blits-ai-updates",{"title":510,"description":511},"Product Update: Five Big Additions from the Last Six Months","A plain language roundup of the five biggest things we shipped this year (emotional voice, rich interactive cards, agentic tasks, in chat payments and response feedback) and what each one does for the person on the other end of the conversation.","blog\u002Ffrom-talking-to-doing-six-months-of-blits-ai-updates",[182,52,249,302,282],"yojUU4dXMnn1LM4XJdH8rXr-2_-CI5k9oYKfDLjNOwo",{"id":516,"title":517,"author":309,"category":28,"date":518,"description":519,"extension":12,"featured":13,"image":520,"meta":521,"metaDescription":34,"metaTitle":522,"navigation":18,"path":523,"seo":524,"stem":525,"tags":34,"__hash__":526,"__readTime":319},"blog\u002Fblog\u002Fgpt-4-in-chatbots.md","GPT-4 in Chatbots: Blits.ai Breaks New Ground in Conversational AI","2023-07-14","Blits.ai now supports GPT-4, bringing new capabilities to chatbot development and deployment. What it means for conversational AI.","\u002Fblog\u002Fgpt-4.webp",{},"GPT-4 Chatbots: New Ground in Conversational AI","\u002Fblog\u002Fgpt-4-in-chatbots",{"title":517,"description":519},"blog\u002Fgpt-4-in-chatbots","G00HNe_XJ2lwAPzMes8evMiwWORzWzdgIFCzLrsptWU",{"id":528,"title":529,"author":290,"category":310,"date":530,"description":531,"extension":12,"featured":13,"image":532,"meta":533,"metaDescription":534,"metaTitle":535,"navigation":18,"path":536,"seo":537,"stem":538,"tags":539,"__hash__":543,"__readTime":544},"blog\u002Fblog\u002Fhow-europe-tests-ai-in-its-own-languages.md","How Europe Tests AI in Its Own Languages","2026-11-16","What Blits.ai does in the LLMs4EU project, and what we learned in the first eighteen months. How Europe adapts open language models to its own languages, why testing comes first, how the distributed evaluation centre works, and the lessons from writing, running and building the tests.","\u002Fblog\u002Fblits-llms4eu-hrastovlje-church.jpg",{},"What Blits.ai does in the EU project LLMs4EU, how the distributed evaluation centre tests AI in every EU language, and what we learned in eighteen months.","LLMs4EU: How Europe Tests AI in Its Own Languages","\u002Fblog\u002Fhow-europe-tests-ai-in-its-own-languages",{"title":529,"description":531},"blog\u002Fhow-europe-tests-ai-in-its-own-languages",[540,541,86,334,542],"llms4eu","european ai","language technology","Le5SM4Pjlf-dqqPnqWJJHVwjDgM_tTYJNuV8Cok0-Mg","17 min read",{"id":546,"title":547,"author":309,"category":28,"date":548,"description":549,"extension":12,"featured":13,"image":550,"meta":551,"metaDescription":552,"metaTitle":553,"navigation":18,"path":554,"seo":555,"stem":556,"tags":34,"__hash__":557,"__readTime":319},"blog\u002Fblog\u002Fhow-practical-is-gpt-3-for-conversational-ai-chatbots.md","How practical is GPT-3 for Conversational AI chatbots?","2022-01-25","GPT-3 has changed what people expect from conversational AI. Ask it almost anything and you get a fluent, often surprisingly good answer. Whether that makes it practical for a chatbot or voicebot that talks to your customers is a different question, and that is what this article is about.","\u002Fblog\u002FGPT-3.jpg",{},"GPT-3 gives fluent, often surprisingly good answers. Whether that makes it practical for a chatbot that talks to your customers is another question.","How Practical Is GPT-3 for Chatbots?","\u002Fblog\u002Fhow-practical-is-gpt-3-for-conversational-ai-chatbots",{"title":547,"description":549},"blog\u002Fhow-practical-is-gpt-3-for-conversational-ai-chatbots","5bcufuhpdudmHxSJDIeisrRbO9tOk1zdavIsJZcNhBY",{"id":559,"title":560,"author":8,"category":28,"date":561,"description":562,"extension":12,"featured":13,"image":563,"meta":564,"metaDescription":565,"metaTitle":566,"navigation":18,"path":567,"seo":568,"stem":569,"tags":570,"__hash__":573,"__readTime":286},"blog\u002Fblog\u002Fhow-to-build-an-ai-control-tower-for-agentic-operations.md","The AI Control Tower: Air Traffic Control for Agents in Production","2026-03-23","A dashboard tells you the plane landed. A control tower keeps two aircraft off the same runway in real time, with the authority to divert one. What that distinction means for running AI agents in production, and why an HTTP 200 will lie to you.","\u002Fimages\u002Fblog-control-tower.png",{},"A dashboard tells you the plane landed. A control tower keeps two aircraft off one runway. What that means for running AI agents in production.","How to Build an AI Control Tower for Agents","\u002Fblog\u002Fhow-to-build-an-ai-control-tower-for-agentic-operations",{"title":560,"description":562},"blog\u002Fhow-to-build-an-ai-control-tower-for-agentic-operations",[571,52,136,572,53],"ai observability","guardrails","tekVT7bbrPjtuBBrGEuTtVN495S40tyKTdMJ6WTqSmQ",{"id":575,"title":576,"author":290,"category":28,"date":577,"description":578,"extension":12,"featured":13,"image":579,"meta":580,"metaDescription":581,"metaTitle":582,"navigation":18,"path":583,"seo":584,"stem":585,"tags":586,"__hash__":588,"__readTime":106},"blog\u002Fblog\u002Finsurance-ai-claims-underwriting-fraud-on-top-of-the-core-system.md","AI for Insurance Claims, Underwriting and Fraud: What Sits on Top of the Core System","2026-12-18","Insurers don't need new claims management software or underwriting software to use AI. The deployments that work put an agent layer on top of the core system they already have. How that layer is built for claims, underwriting and fraud detection, what insurers report, and where the limits are.","\u002Fblog\u002Fblits-insurance-claims-underwriting-fraud-hero.png",{},"How AI agents work with insurance claims management software, underwriting software and fraud detection, without replacing the core system. With public results.","AI for Insurance Claims, Underwriting and Fraud","\u002Fblog\u002Finsurance-ai-claims-underwriting-fraud-on-top-of-the-core-system",{"title":576,"description":578},"blog\u002Finsurance-ai-claims-underwriting-fraud-on-top-of-the-core-system",[166,266,267,587,214],"fraud detection","08_0XCOfCZBlzrSuqPhuMlZpHYAtN7j4KvH3vzEJ0ME",{"id":590,"title":591,"author":309,"category":9,"date":592,"description":593,"extension":12,"featured":13,"image":594,"meta":595,"metaDescription":596,"metaTitle":597,"navigation":18,"path":598,"seo":599,"stem":600,"tags":601,"__hash__":605,"__readTime":39},"blog\u002Fblog\u002Fintroducing-blits-ai-financial-wellbeing.md","Introducing Blits.ai Financial Wellbeing: Guidance, Never Financial Advice","2026-08-29","Our newest product turns a bank's own transaction data into a wellbeing score, plain language insight and gentle nudges toward healthier money habits. It runs inside the bank, it measures its own impact, and it will never give financial advice. Here is how it works.","\u002Fblog\u002Fblits-fw-dashboard.png",{},"Our newest product turns a bank's transaction data into a wellbeing score, plain language insight and gentle nudges. It runs inside the bank, never as advice.","Blits.ai Financial Wellbeing: Guidance, Not Advice","\u002Fblog\u002Fintroducing-blits-ai-financial-wellbeing",{"title":591,"description":593},"blog\u002Fintroducing-blits-ai-financial-wellbeing",[602,469,572,603,604],"financial wellbeing","product","nudges","fr19gXuC3QnydGpIKcJpc9c9ZjA6F-HESxQnaqK8dfY",{"id":607,"title":608,"author":290,"category":28,"date":609,"description":610,"extension":12,"featured":13,"image":611,"meta":612,"metaDescription":613,"metaTitle":614,"navigation":18,"path":615,"seo":616,"stem":617,"tags":618,"__hash__":623,"__readTime":39},"blog\u002Fblog\u002Fknowledge-graphs-vs-vector-search.md","Knowledge Graphs vs Vector Search: What Enterprise AI Actually Needs","2026-11-24","Vector search finds passages that mean the same thing. A knowledge graph knows how things are connected. Most enterprise AI needs the first, some needs the second, and a surprising number of questions need neither. A practical guide to choosing, from someone who builds both.","\u002Fblog\u002Fblits-knowledge-graph-hero.png",{},"Knowledge graph or vector search? What each one is good at, where each breaks, and how to decide which questions your enterprise AI needs to answer.","Knowledge Graphs vs Vector Search for Enterprise AI","\u002Fblog\u002Fknowledge-graphs-vs-vector-search",{"title":608,"description":610},"blog\u002Fknowledge-graphs-vs-vector-search",[619,620,621,622,53],"knowledge graph","vector search","rag","retrieval","IPa50HdvBjLxCAI5Q_SAlhu7UaoQewgBoWLBooU0CkQ",{"id":625,"title":626,"author":309,"category":28,"date":627,"description":628,"extension":12,"featured":13,"image":629,"meta":630,"metaDescription":34,"metaTitle":631,"navigation":18,"path":632,"seo":633,"stem":634,"tags":635,"__hash__":639,"__readTime":286},"blog\u002Fblog\u002Fmcp-security-in-production-auth-and-least-privilege.md","MCP Security: The Threat Model Changes the Day After You Ship","2026-03-15","Most MCP breaches needed no exploit code; the servers behaved as specified. What goes wrong in production, and why the new OAuth spec is half a fix.","\u002Fimages\u002Fblog-mcp-security.png",{},"MCP Security in Production: Auth and Privilege","\u002Fblog\u002Fmcp-security-in-production-auth-and-least-privilege",{"title":626,"description":628},"blog\u002Fmcp-security-in-production-auth-and-least-privilege",[636,637,638,53,52],"mcp","ai security","prompt injection","Hz41mPrcsT9FC-R_MkrwnwIFerSFFo6bu9tJw9xeKTA",{"id":641,"title":642,"author":8,"category":28,"date":643,"description":644,"extension":12,"featured":13,"image":645,"meta":646,"metaDescription":34,"metaTitle":647,"navigation":18,"path":648,"seo":649,"stem":650,"tags":651,"__hash__":654,"__readTime":368},"blog\u002Fblog\u002Fmcp-servers-and-tools.md","MCP Servers and Tools: How LLMs Connect to the Real World","2026-01-27","MCP servers standardize how LLMs find and use tools. What they are, why they matter, how we use them at Blits.ai, and where this is going next.","\u002Fimages\u002Fmcp-server-header.webp",{},"MCP Servers and Tools: How LLMs Reach the World","\u002Fblog\u002Fmcp-servers-and-tools",{"title":642,"description":644},"blog\u002Fmcp-servers-and-tools",[497,652,636,653],"tools","agents","H-rIH_hhI4AEIuhMm5XBRn8GqeNa7Ie_6MmiMlzHllw",{"id":656,"title":657,"author":309,"category":459,"date":658,"description":659,"extension":12,"featured":13,"image":660,"meta":661,"metaDescription":662,"metaTitle":663,"navigation":18,"path":664,"seo":665,"stem":666,"tags":667,"__hash__":671,"__readTime":71},"blog\u002Fblog\u002Fmeasurable-beats-impressive-blits-ai-at-ai-everything-abu-dhabi.md","Measurable Beats Impressive: 75 Conversations at Ai Everything Abu Dhabi","2026-10-15","Len, Coen and I spent two days on our stand at Ai Everything Abu Dhabi and had more than 75 conversations with banks, government entities, telcos, investors and fellow founders. Five themes kept coming back, and together they point one way: from impressive demos to measurable results in production.","\u002Fblog\u002Fblits-ai-everything-abu-dhabi-recap-hero.png",{},"What more than 75 conversations at Ai Everything Abu Dhabi taught us about enterprise AI in the Gulf: production, sovereignty, agents, language and trust.","75 Conversations at Ai Everything Abu Dhabi 2026","\u002Fblog\u002Fmeasurable-beats-impressive-blits-ai-at-ai-everything-abu-dhabi",{"title":657,"description":659},"blog\u002Fmeasurable-beats-impressive-blits-ai-at-ai-everything-abu-dhabi",[668,669,52,670,53],"events","abu dhabi","financial services","ElFxoh8zy2QDQJsKiNXkHDIYRHEUUfMjIaRxR4vFaD0",{"id":673,"title":674,"author":8,"category":28,"date":675,"description":676,"extension":12,"featured":13,"image":677,"meta":678,"metaDescription":34,"metaTitle":34,"navigation":18,"path":679,"seo":680,"stem":681,"tags":682,"__hash__":686,"__readTime":39},"blog\u002Fblog\u002Fmeasure-ai-performance-and-set-the-right-kpis.md","Measure AI Performance and Set the Right KPIs","2026-03-07","AI performance means more than accuracy. These are the production KPIs that matter (latency, P99, TTFT and error rates) and how to measure them.","\u002Fimages\u002Fblits-performance.jpg",{},"\u002Fblog\u002Fmeasure-ai-performance-and-set-the-right-kpis",{"title":674,"description":676},"blog\u002Fmeasure-ai-performance-and-set-the-right-kpis",[683,684,685,53],"ai kpi","ai performance","observability","7izChjS6RtzVMstKY8mFca2uii-3N31S4GP1zVQOxX0",{"id":688,"title":689,"author":8,"body":690,"category":28,"date":913,"description":914,"extension":12,"featured":13,"image":915,"meta":916,"metaDescription":917,"metaTitle":918,"navigation":18,"path":919,"seo":920,"stem":921,"tags":922,"__hash__":924},"blog\u002Fblog\u002Fmost-enterprise-ai-never-leaves-the-pilot.md","Most Enterprise AI Never Leaves the Pilot. Ours Goes Live.",{"type":691,"value":692,"toc":897},"minimark",[693,697,702,705,712,735,750,753,757,760,763,768,771,775,778,782,791,795,798,802,805,811,815,818,825,836,845,851,857,863,866,870,873,876,880,883],[694,695,696],"p",{},"\"Most enterprise AI never leaves the pilot. Ours goes live.\" That sentence is the first thing you read on our home page. It is a big claim, and a big claim deserves more than one line. So this post is the long version. What do we know about enterprise AI that gets stuck, why does it get stuck, and what do we do so it doesn't?",[698,699,701],"h2",{"id":700},"what-the-research-says-about-enterprise-ai-pilots","What the research says about enterprise AI pilots",[694,703,704],{},"I'll start with the first half of the sentence, because I didn't make it up.",[694,706,707],{},[708,709],"img",{"alt":710,"src":711},"What the studies say about enterprise AI pilots","\u002Fblog\u002Fblits-pilot-to-production-numbers.png",[694,713,714,715,722,723,728,729,734],{},"MIT's NANDA initiative published The GenAI Divide in August 2025. As Fortune summarized it, ",[716,717,721],"a",{"href":718,"rel":719},"https:\u002F\u002Ffortune.com\u002F2025\u002F08\u002F18\u002Fmit-report-95-percent-generative-ai-pilots-at-companies-failing-cfo\u002F",[720],"noopener","about 5 percent of AI pilot programs achieve rapid revenue acceleration",", and the vast majority stall. S&P Global Market Intelligence found that the share of businesses scrapping most of their AI initiatives ",[716,724,727],{"href":725,"rel":726},"https:\u002F\u002Fwww.ciodive.com\u002Fnews\u002Fai-project-fail-data-spglobal\u002F742590\u002F",[720],"rose to 42 percent, up from 17 percent a year earlier",", and that the average organization scrapped 46 percent of its proofs of concept before they reached production. IDC, working with Lenovo, counted it per project: for every 33 AI proofs of concept a company launched, ",[716,730,733],{"href":731,"rel":732},"https:\u002F\u002Fwww.cio.com\u002Farticle\u002F3850763\u002F88-of-ai-pilots-fail-to-reach-production-but-thats-not-all-on-it.html",[720],"only four graduated to production",".",[694,736,737,738,743,744,749],{},"You could say that was 2025 and things have moved on. A little. In Deloitte's State of AI in the Enterprise report from January this year, ",[716,739,742],{"href":740,"rel":741},"https:\u002F\u002Fwww.deloitte.com\u002Fus\u002Fen\u002Fabout\u002Fpress-room\u002Fstate-of-ai-report-2026.html",[720],"only 25 percent of respondents had moved 40 percent or more of their AI pilots into production",". And in a Gartner survey of more than 2,000 CIOs published this October, ",[716,745,748],{"href":746,"rel":747},"https:\u002F\u002Fwww.eweek.com\u002Fnews\u002Fgartner-cio-ai-value-rules\u002F",[720],"only 13 percent said their organization had realized significant or transformational value from AI",". My favorite number from that survey: just 31 percent have rules for stopping an unsuccessful pilot. So most companies can't get pilots into production, and can't kill them either. They just sit there, costing money.",[694,751,752],{},"One caveat, because I care about using numbers properly. These studies don't all measure the same thing. MIT looks at revenue impact, S&P and IDC at reaching production, Gartner at value. Don't add them up. They do all point the same way, and it matches what I see in meeting rooms.",[698,754,756],{"id":755},"why-enterprise-ai-projects-fail-ten-ways-a-pilot-dies","Why enterprise AI projects fail: ten ways a pilot dies",[694,758,759],{},"If you watch the animation on our home page for a minute, you'll see pilots stall one after another, each with a reason next to it. We didn't pick those ten reasons for effect. They are the ones we keep running into when an organization tells us why an earlier AI project stopped. When corporate AI implementation failure comes up in a boardroom, the model usually gets the blame. In the stories we hear, the model is rarely the reason.",[694,761,762],{},"I'll group them, because they come in families.",[764,765,767],"h3",{"id":766},"it-was-built-for-the-demo","It was built for the demo",[694,769,770],{},"\"Never left the sandbox\", \"no back office integration\" and \"missing functionality\" are the same story. A pilot that answers questions from a few uploaded PDFs is quick to build and looks great in a steering committee. Then someone asks whether it can block the card, change the address or look up the real order, and the answer is that this was out of scope for the pilot. The integration with the core systems was always going to be most of the work, and it was postponed to a phase that never got funded.",[764,772,774],{"id":773},"nobody-asked-security-and-compliance-until-the-end","Nobody asked security and compliance until the end",[694,776,777],{},"\"Stuck in security review\" and \"blocked by compliance\" kill more pilots than any model limitation. I've said before where the time in an enterprise AI project goes: roughly 20 percent technology, 20 percent customization and 60 percent approvals and stakeholders. A pilot that skips that 60 percent only moves it to the end, where it shows up as a full stop. The CISO sees the architecture for the first time when you ask for a production go ahead, and discovers that customer data goes to a model in another region, with no audit trail and no answer to who approved what.",[764,779,781],{"id":780},"the-money-questions-came-too-late","The money questions came too late",[694,783,784,785,790],{},"\"Running costs unknown\" and \"out of budget\". A pilot runs on a credit card and a few thousand conversations. Production means a few hundred thousand, with voice, guardrails and retries on top. If nobody can say what an interaction costs at that volume, finance will say no, and finance will be right. Gartner predicted back in 2024 that at least 30 percent of generative AI projects would be ",[716,786,789],{"href":787,"rel":788},"https:\u002F\u002Fwww.gartner.com\u002Fen\u002Fnewsroom\u002Fpress-releases\u002F2024-07-29-gartner-predicts-30-percent-of-generative-ai-projects-will-be-abandoned-after-proof-of-concept-by-end-of-2025",[720],"abandoned after proof of concept",", and escalating costs and unclear business value were two of its four reasons.",[764,792,794],{"id":793},"quality-couldnt-be-proven","Quality couldn't be proven",[694,796,797],{},"\"Failed QA\" and \"data not ready\". Everyone in the pilot team feels that the assistant is good, and a feeling is not something you can hand to a risk team. When they ask how often it gives a wrong answer about fees, and the answer is \"we tried it a lot and it seemed fine\", the project is over. Usually the knowledge behind it is the weak spot: three versions of the same policy, one of them from 2021, and the assistant picks the wrong one with total confidence.",[764,799,801],{"id":800},"the-sponsor-moved-on","The sponsor moved on",[694,803,804],{},"The last one is the most human. A pilot belongs to one enthusiastic director. That director gets promoted, reorganized or headhunted, and what stays behind is an experiment without an owner and without a line in anyone's budget. A system in production has an owner by definition, and that is one more reason to get there quickly.",[806,807,808],"blockquote",{},[694,809,810],{},"A pilot shows that AI can do something once. Going live means running it every day and being able to explain it to the regulator.",[698,812,814],{"id":813},"how-we-get-enterprise-ai-into-production","How we get enterprise AI into production",[694,816,817],{},"Now the second half of the sentence. I'm not claiming we are smarter than everyone else. We are a platform company that has delivered more than 100 use cases, many of them for banks, and we have organized the way we work around the ten reasons above. In plain terms it comes down to this.",[694,819,820,824],{},[821,822,823],"strong",{},"We start with the production requirements."," Before anyone writes a prompt, we want to know where it will run, which systems it must talk to, who has to approve it and what it has to prove. It sounds slow, and it turns out to be the fastest route, because nothing has to be rebuilt later. A first use case typically goes live within weeks, and the second one reuses the integrations, the guardrails and the approvals of the first.",[694,826,827,830,831,835],{},[821,828,829],{},"It runs where your security team wants it to run."," In our managed cloud, in your own cloud or on premises, with the model you choose. That takes the hardest security discussion off the table before it starts. For customers who want cloud models but can't let personal data leave, there is the ",[716,832,834],{"href":833},"\u002Fblog\u002Fusing-cloud-ai-without-sending-personal-data-abroad","privacy shield",". The platform is certified for ISO 27001, ISO 42001, SOC 2 Type II and PCI DSS Level 1, which doesn't replace your own review but shortens it considerably.",[694,837,838,841,842,734],{},[821,839,840],{},"The agent does real work in real systems."," Agents act through tools connected to your core systems, with a permission per tool. A refund above a limit waits for a colleague. Everything an agent decides is in a decision log your auditors can read. I described those controls in ",[716,843,844],{"href":178},"Agents That Ask, Remember and Show Their Work",[694,846,847,850],{},[821,848,849],{},"Quality is measured, every release."," Each use case gets a test suite with the questions that matter, including the nasty ones. A change to an agent can be set to go live only after those tests pass. So when risk asks how you know it works, you show a report.",[694,852,853,856],{},[821,854,855],{},"You know what an interaction costs before you scale."," Usage is metered per assistant and per model, so the business case is built on measured numbers from your own traffic.",[694,858,859,862],{},[821,860,861],{},"We stay."," Platform plus people. Our team designs, builds, runs and improves the agents with yours, so the project doesn't depend on one sponsor's enthusiasm or on three scarce engineers you'd have to hire first.",[694,864,865],{},"None of this is exotic, and most of it is boring in the good sense of the word. What separates a pilot from a production system in enterprise AI is integration, approval, proof and ownership far more often than the model, and you can plan for all four from day one.",[698,867,869],{"id":868},"what-live-means","What \"live\" means",[694,871,872],{},"One more thing, because the word gets stretched. For us a use case is live when real customers or employees use it for real requests, when it is connected to the systems it needs, when it runs under your security and compliance rules, and when somebody owns its numbers. A chatbot on an internal test page with ten friendly users is a pilot, however long it has been running.",[694,874,875],{},"If your enterprise AI strategy lists a handful of initiatives and you want to know where each one stands, ask four questions about each of them. Which system does it change something in? Who signed off on it? What is its pass rate on a fixed test set? Whose budget pays for it next year? Four clear answers and you are in production. Blanks, and you know what to work on.",[698,877,879],{"id":878},"bring-the-pilot-that-got-stuck","Bring the pilot that got stuck",[694,881,882],{},"We make the same offer to everyone, and it's on the home page too: bring the use case that matters most to you, we show you a working version first, and then we put it into production. Preferably one that already got stuck somewhere, because those are the most fun.",[694,884,885,886,890,891,896],{},"Our ",[716,887,889],{"href":888},"\u002Fai-use-cases\u002Fstate-of-ai-use-cases","AI Use Case Library"," shows what organizations like yours already run in production, with sources. And if you want to talk through a pilot that isn't moving, ",[716,892,895],{"href":893,"rel":894},"https:\u002F\u002Fwww.blits.ai\u002Fcontact-us",[720],"send me a message",". I'll tell you which of the ten it is.",{"title":898,"searchDepth":899,"depth":899,"links":900},"",2,[901,902,910,911,912],{"id":700,"depth":899,"text":701},{"id":755,"depth":899,"text":756,"children":903},[904,906,907,908,909],{"id":766,"depth":905,"text":767},3,{"id":773,"depth":905,"text":774},{"id":780,"depth":905,"text":781},{"id":793,"depth":905,"text":794},{"id":800,"depth":905,"text":801},{"id":813,"depth":899,"text":814},{"id":868,"depth":899,"text":869},{"id":878,"depth":899,"text":879},"2026-11-13","The line on our home page is a big claim, so here is what sits behind it. What the research says about enterprise AI pilots, the ten ways we see pilots die, and what we do differently so that a use case reaches production and stays there.","\u002Fblog\u002Fblits-pilot-to-production-hero.png",{},"Why most enterprise AI stalls in the pilot, what the studies from MIT, S&P, IDC, Deloitte and Gartner show, and how we get enterprise AI into production.","Why Most Enterprise AI Never Leaves the Pilot","\u002Fblog\u002Fmost-enterprise-ai-never-leaves-the-pilot",{"title":689,"description":914},"blog\u002Fmost-enterprise-ai-never-leaves-the-pilot",[53,54,923,136,56],"ai in production","tsDVW3yzbg6ITwAmCYpbM1m5Fmicz2U6xP685igxzPQ",{"id":926,"title":927,"author":8,"category":28,"date":928,"description":929,"extension":12,"featured":13,"image":930,"meta":931,"metaDescription":34,"metaTitle":34,"navigation":18,"path":932,"seo":933,"stem":934,"tags":935,"__hash__":937,"__readTime":121},"blog\u002Fblog\u002Fnobody-budgets-in-tokens.md","Nobody Budgets in Tokens","2026-08-12","Per seat licensing carried software for a decade, but agents don't sit in seats and token pricing breaks the moment AI succeeds. Where AI pricing lands.","\u002Fblog\u002Fblits-pricing-eras-hero.png",{},"\u002Fblog\u002Fnobody-budgets-in-tokens",{"title":927,"description":929},"blog\u002Fnobody-budgets-in-tokens",[936,53,52,54],"ai pricing","hkBVqOB8OWhD605LVQ0T2z7EUAGFurKvJc45xadSVxs",{"id":939,"title":940,"author":309,"category":28,"date":941,"description":942,"extension":12,"featured":13,"image":943,"meta":944,"metaDescription":34,"metaTitle":945,"navigation":18,"path":946,"seo":947,"stem":948,"tags":34,"__hash__":949,"__readTime":24},"blog\u002Fblog\u002Fopening-the-natural-language-understanding-nlu-blackbox.md","Opening the Natural Language Understanding (NLU) Blackbox","2020-06-23","NLU is often treated as a black box, but knowing how it works is key to building effective conversational AI. A look inside.","\u002Fblog\u002FMonitoring-300x234.png",{},"Opening the NLU Black Box","\u002Fblog\u002Fopening-the-natural-language-understanding-nlu-blackbox",{"title":940,"description":942},"blog\u002Fopening-the-natural-language-understanding-nlu-blackbox","qPChjo2cCcMnFSlIS91oCjCT84N-DppSPKyROYaYC2Q",{"id":951,"title":952,"author":290,"category":28,"date":953,"description":954,"extension":12,"featured":13,"image":955,"meta":956,"metaDescription":957,"metaTitle":958,"navigation":18,"path":959,"seo":960,"stem":961,"tags":962,"__hash__":963,"__readTime":251},"blog\u002Fblog\u002Fprompt-injection-enterprise-ai-agents.md","Prompt Injection: The Attack Every Enterprise AI Agent Will Face","2026-11-20","Prompt injection is the number one risk on the OWASP list for LLM applications, and security agencies say it may never be fully solved. For AI agents that read emails and documents and act in your systems, that changes how you design them. What prompt injection is, real incidents, and five layers that keep a successful attack from doing real harm.","\u002Fblog\u002Fblits-prompt-injection-hero.png",{},"What prompt injection is, why it is the top risk for LLM applications, why it cannot be fully solved, and five layers that limit the damage for AI agents.","Prompt Injection: The Attack Every AI Agent Will Face","\u002Fblog\u002Fprompt-injection-enterprise-ai-agents",{"title":952,"description":954},"blog\u002Fprompt-injection-enterprise-ai-agents",[638,637,52,136,56],"mBu03eY3ykp-MVizY4m6FATerfgXKC3E7Rka_o9M8vc",{"id":965,"title":966,"author":8,"category":28,"date":967,"description":968,"extension":12,"featured":13,"image":969,"meta":970,"metaDescription":34,"metaTitle":971,"navigation":18,"path":972,"seo":973,"stem":974,"tags":975,"__hash__":976,"__readTime":499},"blog\u002Fblog\u002Frag-in-2026-why-enterprise-pipelines-still-fail.md","The RAG That Passed Its Demo and Quietly Died in Production","2026-04-16","A knowledge assistant that aces its pilot can fail silently, recall sliding while dashboards stay green. Why good RAG rots after the demo.","\u002Fimages\u002Fblits-hallucination.jpg",{},"RAG in 2026: Why Enterprise Pipelines Still Fail","\u002Fblog\u002Frag-in-2026-why-enterprise-pipelines-still-fail",{"title":966,"description":968},"blog\u002Frag-in-2026-why-enterprise-pipelines-still-fail",[621,53,497,622,334],"30WucP_fwRnTHUJ8UHdi6VXrjrevV1S2Uhl6sQMEEMY",{"id":978,"title":979,"author":8,"category":28,"date":980,"description":981,"extension":12,"featured":13,"image":982,"meta":983,"metaDescription":984,"metaTitle":979,"navigation":18,"path":985,"seo":986,"stem":987,"tags":988,"__hash__":992,"__readTime":39},"blog\u002Fblog\u002Fretail-ai-use-cases-that-survive-the-demo.md","Retail AI: The Use Cases That Survive Beyond the Demo","2026-11-27","Retail AI demos are all shopping assistants that talk like a friend with great taste. The retail AI that survives in production is mostly pricing, forecasting, fraud screening and product data. What 123 public deployments tell us, what Walmart, Amazon and IKEA actually report, and where the shopping assistant finally earns its place.","\u002Fblog\u002Fblits-retail-ai-hero.png",{},"Which retail AI use cases make it to production? What 123 public deployments, Walmart, Amazon, IKEA and Lowe's show, and why the boring ones pay first.","\u002Fblog\u002Fretail-ai-use-cases-that-survive-the-demo",{"title":979,"description":981},"blog\u002Fretail-ai-use-cases-that-survive-the-demo",[989,990,52,233,991],"retail ai","ecommerce","ai use cases","-ud86QKo5OoTfyhYMSq4I40xq-UYZWhtOdJTUPcddHU",{"id":994,"title":995,"author":8,"category":28,"date":996,"description":997,"extension":12,"featured":13,"image":998,"meta":999,"metaDescription":1000,"metaTitle":1001,"navigation":18,"path":1002,"seo":1003,"stem":1004,"tags":1005,"__hash__":1010,"__readTime":121},"blog\u002Fblog\u002Fswiss-data-protection-law-vs-gdpr-for-ai-services.md","Swiss Data Protection Law vs GDPR: What It Means for AI Services","2026-12-22","Switzerland has no AI Act and its data protection law looks a lot like GDPR, so AI companies often assume one compliance program covers both. It nearly does. Where the Swiss FADP differs for AI services, why the EU AI Act reaches Swiss companies anyway, and what to arrange if you serve customers on both sides of the border.","\u002Fblog\u002Fblits-swiss-law-vs-gdpr-ai-hero.png",{},"AI service compliance in Switzerland vs the EU: how the Swiss FADP differs from GDPR for AI, why the EU AI Act still reaches Swiss companies, and a checklist.","Swiss Data Protection Law vs GDPR for AI Services","\u002Fblog\u002Fswiss-data-protection-law-vs-gdpr-for-ai-services",{"title":995,"description":997},"blog\u002Fswiss-data-protection-law-vs-gdpr-for-ai-services",[1006,1007,1008,216,1009],"data protection","switzerland","gdpr","ai compliance","HTi0ta-8IDYFkEmZSIVcvzJD8nuPg8rih8YxluBvEKE",{"id":1012,"title":1013,"author":8,"category":28,"date":1014,"description":1015,"extension":12,"featured":13,"image":1016,"meta":1017,"metaDescription":34,"metaTitle":1018,"navigation":18,"path":1019,"seo":1020,"stem":1021,"tags":1022,"__hash__":1024,"__readTime":39},"blog\u002Fblog\u002Ftext-to-speech-engines-and-why-they-matter.md","Text-to-Speech Engines: The Voice Layer Every AI Product Needs","2026-03-03","Text to speech is core AI infrastructure. What TTS engines are, the model approaches, the providers that matter, and why speed and dialect decide.","\u002Fimages\u002Fblits-voice.jpg",{},"Text to Speech Engines: The Voice Layer for AI","\u002Fblog\u002Ftext-to-speech-engines-and-why-they-matter",{"title":1013,"description":1015},"blog\u002Ftext-to-speech-engines-and-why-they-matter",[332,302,1023],"ai infrastructure","Eu3je_dRENeJZno3LYJ_fO5Q8qAgtwBhXUoOKz3wGcA",{"id":1026,"title":1027,"author":8,"category":28,"date":1028,"description":1029,"extension":12,"featured":13,"image":1030,"meta":1031,"metaDescription":1032,"metaTitle":34,"navigation":18,"path":1033,"seo":1034,"stem":1035,"tags":1036,"__hash__":1038,"__readTime":106},"blog\u002Fblog\u002Fthe-ai-bank-runs-on-governance.md","The AI Bank Runs on Governance","2026-09-30","Our banking use case map grew from 21 to 81 jobs, so we turned it into a playbook. Along the way the story changed: the destination is the AI bank, where the work itself runs on governed AI, and what decides who gets there is governance far more than the models.","\u002Fblog\u002Fblits-ai-bank-eras-hero.png",{},"Our banking use case map grew from 21 to 81 jobs. The destination is the AI bank, and what decides who gets there is governance more than the models.","\u002Fblog\u002Fthe-ai-bank-runs-on-governance",{"title":1027,"description":1029},"blog\u002Fthe-ai-bank-runs-on-governance",[1037,136,469,52,304],"ai bank","ziFVXhwwYmus7n690c2_Rwb-4y8O4_M3dywY49MRwnc",{"id":1040,"title":1041,"author":8,"category":28,"date":1042,"description":1043,"extension":12,"featured":13,"image":1044,"meta":1045,"metaDescription":34,"metaTitle":34,"navigation":18,"path":1046,"seo":1047,"stem":1048,"tags":1049,"__hash__":1051,"__readTime":106},"blog\u002Fblog\u002Fthe-best-ai-model-doesnt-exist.md","The Best AI Model Doesn't Exist","2026-07-27","62 AI model versions got a retirement date this year. Why locking your business to one model is a hidden risk, and why staying model agnostic wins.","\u002Fblog\u002Fblits-model-agnostic-hub.png",{},"\u002Fblog\u002Fthe-best-ai-model-doesnt-exist",{"title":1041,"description":1043},"blog\u002Fthe-best-ai-model-doesnt-exist",[1050,53,497,333,54],"model agnostic","JqdV1Cu_gxRCBVp7H6x-wfyip2yVMkHRo7Tu0G_4gnM",{"id":1053,"title":1054,"author":8,"category":61,"date":1055,"description":1056,"extension":12,"featured":13,"image":1057,"meta":1058,"metaDescription":1059,"metaTitle":1060,"navigation":18,"path":1061,"seo":1062,"stem":1063,"tags":34,"__hash__":1064,"__readTime":24},"blog\u002Fblog\u002Fthe-best-way-for-chatbots-to-actually-understand-your-customers.md","Blits.ai: The Best Way for Chatbots to Actually Understand Your Customers","2021-02-11","We're introducing a new method at Blits.ai that changes how chatbots work under the hood. From the start our idea was simple: companies should be able to use the best performing engines on the market without having to pick one vendor and hope for the best. Right now we are two things at once, a middleware layer and a low code platform, and through it our customers get access to 40+ cognitive AI services.","\u002Fblog\u002F1611759270728.png",{},"A new Blits.ai method lets chatbots use the best AI engines on the market without betting on one vendor, through 40+ cognitive AI services.","How Chatbots Truly Understand Your Customers","\u002Fblog\u002Fthe-best-way-for-chatbots-to-actually-understand-your-customers",{"title":1054,"description":1056},"blog\u002Fthe-best-way-for-chatbots-to-actually-understand-your-customers","jlCmU9T6D-chVvdsZIMpRg5Gk4hbzvt7Mut-plLU6ZY",{"id":1066,"title":1067,"author":309,"category":28,"date":1068,"description":1069,"extension":12,"featured":13,"image":1070,"meta":1071,"metaDescription":1072,"metaTitle":34,"navigation":18,"path":1073,"seo":1074,"stem":1075,"tags":1076,"__hash__":1079,"__readTime":39},"blog\u002Fblog\u002Fthe-chargeback-arms-race.md","The Chargeback Arms Race","2026-10-03","Chargebacks are heading for 337 million a year, most of them aren't real fraud, and each one costs a multiple of its face value. A practical look at the six AI jobs hiding in one dispute, what each of them needs to be governed, and why agentic commerce will change the volume.","\u002Fblog\u002Fblits-chargeback-loop-hero.png",{},"Chargebacks head for 337 million a year and most are not fraud. The six AI jobs in one dispute, how to govern each, and what agentic commerce changes.","\u002Fblog\u002Fthe-chargeback-arms-race",{"title":1067,"description":1069},"blog\u002Fthe-chargeback-arms-race",[1077,284,52,53,1078],"chargebacks","fraud","HPFO_kwJvdXKmDRJf83bSyREvy4-rH815TsB1ButS64",{"id":1081,"title":1082,"author":154,"category":28,"date":1083,"description":1084,"extension":12,"featured":13,"image":1085,"meta":1086,"metaDescription":1087,"metaTitle":34,"navigation":18,"path":1088,"seo":1089,"stem":1090,"tags":1091,"__hash__":1094,"__readTime":106},"blog\u002Fblog\u002Fthe-company-that-calls-first.md","The Company That Calls First","2026-09-23","A brief landed on my desk asking for 600,000 outbound calls a month, by AI. The pattern is not a banking story: it applies to every enterprise with customers worth calling. Why human dialling died, what insurers, banks, lenders and software companies already run, and the anatomy of a governed outbound call.","\u002Fblog\u002Fblits-outbound-hero.png",{},"A brief asked for 600,000 outbound AI calls a month. Why human dialling died, what insurers, banks and lenders already run, and how a governed outbound call works.","\u002Fblog\u002Fthe-company-that-calls-first",{"title":1082,"description":1084},"blog\u002Fthe-company-that-calls-first",[1092,302,53,52,1093],"outbound ai","sales","lex9hp4VJze5EHsfvgwSNDTKzRgcx7xuHKtS3Co1hxc",{"id":1096,"title":1097,"author":309,"category":28,"date":1098,"description":1099,"extension":12,"featured":13,"image":1100,"meta":1101,"metaDescription":1102,"metaTitle":1103,"navigation":18,"path":1104,"seo":1105,"stem":1106,"tags":1107,"__hash__":1109,"__readTime":251},"blog\u002Fblog\u002Fthe-coordination-layer-what-to-build-when-models-converge.md","The Coordination Layer: What to Build When Models Converge","2026-10-20","Models are converging and getting cheaper to swap, so the durable engineering in enterprise AI is moving somewhere else: the layer that decides who may act, what is remembered, when a human takes over and what gets evidenced. A build guide for the part of your AI stack you'll still own in five years.","\u002Fblog\u002Fblits-coordination-layer-hero.png",{},"Models converge and get cheaper to swap, so lasting work moves to the layer that decides who acts, what is remembered and when a human takes over.","What to Build When AI Models Converge","\u002Fblog\u002Fthe-coordination-layer-what-to-build-when-models-converge",{"title":1097,"description":1099},"blog\u002Fthe-coordination-layer-what-to-build-when-models-converge",[167,52,53,136,1108],"integration","6bV3tAmavHYlr6iTqMhgdg-TOmMYZipHTMmtAENHZCE",{"id":1111,"title":1112,"author":8,"category":28,"date":1113,"description":1114,"extension":12,"featured":13,"image":969,"meta":1115,"metaDescription":1116,"metaTitle":1117,"navigation":18,"path":1118,"seo":1119,"stem":1120,"tags":1121,"__hash__":1124,"__readTime":106},"blog\u002Fblog\u002Fthe-danger-of-ai-hallucinations-and-how-businesses-should-handle-it.md","The Danger of AI Hallucinations and How Businesses Should Handle It","2026-02-25","AI hallucinations are a business risk as much as an error. What they are, why models make things up, how often it happens, real cases from courts and companies, practical mitigations, and what you gain by getting it right.",{},"What AI hallucinations are, why models make things up, how often they do, real cases from courts and companies, and how businesses reduce the risk.","AI Hallucinations and How Businesses Handle Them","\u002Fblog\u002Fthe-danger-of-ai-hallucinations-and-how-businesses-should-handle-it",{"title":1112,"description":1114},"blog\u002Fthe-danger-of-ai-hallucinations-and-how-businesses-should-handle-it",[1122,497,1123,53],"ai","risk management","hXB0xURMAestXPn4SvNI1RX6xuzd8zazx12PKSMkFJU",{"id":1126,"title":1127,"author":8,"category":28,"date":1128,"description":1129,"extension":12,"featured":13,"image":1130,"meta":1131,"metaDescription":34,"metaTitle":1132,"navigation":18,"path":1133,"seo":1134,"stem":1135,"tags":1136,"__hash__":1138,"__readTime":499},"blog\u002Fblog\u002Fthe-many-forms-of-rag-explained-without-the-jargon.md","The Many Forms of RAG, Explained Without the Jargon","2026-07-02","Hybrid search, reranking, ColBERT, GraphRAG, self-RAG: a plain language guide to what each RAG variant does and which ones you probably don't need.","\u002Fblog\u002FBlits-ai-RAG-used-to-be-one-thing.png",{},"The Many Forms of RAG, Without the Jargon","\u002Fblog\u002Fthe-many-forms-of-rag-explained-without-the-jargon",{"title":1127,"description":1129},"blog\u002Fthe-many-forms-of-rag-explained-without-the-jargon",[621,53,497,622,1137],"ai explained","I_4mb1aJRQPXhlA7DS18iNF9x69fHflEzyBjmTit6RE",{"id":1140,"title":1141,"author":290,"category":28,"date":1142,"description":1143,"extension":12,"featured":13,"image":1144,"meta":1145,"metaDescription":34,"metaTitle":1146,"navigation":18,"path":1147,"seo":1148,"stem":1149,"tags":1150,"__hash__":1152,"__readTime":1153},"blog\u002Fblog\u002Fthe-missing-text-layer-why-speech-to-speech-fails-enterprise.md","The Missing Text Layer: Why Speech-to-Speech Agents Fail Enterprise Requirements","2026-07-23","Native speech to speech demos beautifully, then fails enterprise needs. Why the text layer, where guardrails and audit live, still wins regulated voice.","\u002Fblog\u002Fblitsai-voice-isnt-safe.png",{},"Why Speech to Speech Voice Agents Fail Enterprise","\u002Fblog\u002Fthe-missing-text-layer-why-speech-to-speech-fails-enterprise",{"title":1141,"description":1143},"blog\u002Fthe-missing-text-layer-why-speech-to-speech-fails-enterprise",[302,1151,53,167,249],"speech to speech","_wRru7BtLUWa3kxmqXFqOH19LuZw0aj0P7uY7jSmSYc","15 min read",{"id":1155,"title":1156,"author":8,"category":28,"date":1157,"description":1158,"extension":12,"featured":13,"image":1159,"meta":1160,"metaDescription":1161,"metaTitle":1162,"navigation":18,"path":1163,"seo":1164,"stem":1165,"tags":1166,"__hash__":1167,"__readTime":106},"blog\u002Fblog\u002Fthe-universal-commerce-protocol-and-why-llms-need-a-new-economic-language.md","The Universal Commerce Protocol and Why LLMs Need a New Economic Language","2026-01-19","Why commerce as we know it does not work for AI and what the Universal Commerce Protocol is trying to fix","\u002Fimages\u002FbannerUCP-blits.png",{},"Why commerce as we know it does not work for AI, what the Universal Commerce Protocol is trying to fix, and why LLMs need a new economic language.","The Universal Commerce Protocol for LLMs","\u002Fblog\u002Fthe-universal-commerce-protocol-and-why-llms-need-a-new-economic-language",{"title":1156,"description":1158},"blog\u002Fthe-universal-commerce-protocol-and-why-llms-need-a-new-economic-language",[],"m0tr5KARy4ydjJJuxAi4PVAYnRO7OhZnTm_iqltnddk",{"id":1169,"title":1170,"author":8,"category":28,"date":1171,"description":1172,"extension":12,"featured":18,"image":1173,"meta":1174,"metaDescription":34,"metaTitle":1175,"navigation":18,"path":1176,"seo":1177,"stem":1178,"tags":1179,"__hash__":1184,"__readTime":88},"blog\u002Fblog\u002Fuse-cases-in-what-the-future-of-banking-ai-actually-looks-like.md","21 Use Cases In: What the Future of Banking AI Actually Looks Like","2026-08-05","21 banking AI use cases, live or in delivery, across the Middle East, Africa and Europe: dialect voice, digital humans, KYC, fraud screening and outbound agents.","\u002Fblog\u002Fblits-banking-ai-hero.png",{},"21 Use Cases: The Future of Banking AI","\u002Fblog\u002Fuse-cases-in-what-the-future-of-banking-ai-actually-looks-like",{"title":1170,"description":1172},"blog\u002Fuse-cases-in-what-the-future-of-banking-ai-actually-looks-like",[469,52,1180,302,1181,1182,1183],"digital humans","super apps","outbound voice","use cases","8xwelyyim84wM89UJ3_AwxnBerKWf2IZG1930y4KjcI",{"id":1186,"title":1187,"author":8,"category":9,"date":1188,"description":1189,"extension":12,"featured":13,"image":1190,"meta":1191,"metaDescription":1192,"metaTitle":1193,"navigation":18,"path":833,"seo":1194,"stem":1195,"tags":1196,"__hash__":1200,"__readTime":121},"blog\u002Fblog\u002Fusing-cloud-ai-without-sending-personal-data-abroad.md","Using Cloud AI Without Sending Personal Data Abroad","2026-10-16","Strict data rules, no local AI cloud region, no GPUs, and a board that wants agents live this quarter. For a lot of banks and other regulated organizations that used to mean picking two out of three. Our new privacy shield removes the trade off: the best cloud models do the thinking, and the personal data never leaves your building.","\u002Fblog\u002Fblits-privacy-shield-hero.png",{},"Banks and other regulated organizations without a local AI cloud or GPUs can use the best cloud models while personal data stays in their own environment.","Cloud AI Without Sending Personal Data Abroad",{"title":1187,"description":1189},"blog\u002Fusing-cloud-ai-without-sending-personal-data-abroad",[1197,103,1198,670,1199,52],"privacy","on premises","regulated industries","6RznfjQ5ouJ8-p4PHDvoYFz7sJc2d3OrPwHh9ZsvWek",{"id":1202,"title":1203,"author":8,"category":28,"date":1204,"description":1205,"extension":12,"featured":13,"image":1206,"meta":1207,"metaDescription":1208,"metaTitle":1209,"navigation":18,"path":1210,"seo":1211,"stem":1212,"tags":1213,"__hash__":1217,"__readTime":39},"blog\u002Fblog\u002Fwe-read-650-ai-deployments-so-you-dont-have-to.md","We Read 1,300+ AI Deployments So You Don't Have To","2026-10-13","We built a public library of 257 AI use cases and 1,377 real deployments, with every number quoted from its source and labelled with who made the claim. The verdict: AI is doing real work, the industry can't prove it, and the sellers are writing the benchmarks.","\u002Fblog\u002Fblits-use-case-library-hero.png",{},"A public library of 257 AI use cases and 1,377 real deployments, every number sourced. AI does real work, but the industry cannot prove it yet.","Lessons From 1,300+ AI Deployments","\u002Fblog\u002Fwe-read-650-ai-deployments-so-you-dont-have-to",{"title":1203,"description":1205},"blog\u002Fwe-read-650-ai-deployments-so-you-dont-have-to",[991,1214,53,1215,1216],"ai adoption","ai benchmarks","research","1t8kKQ1aRAV876lRNXk4uMDvFc_IGXhaAaVoH9WtrnI",{"id":1219,"title":1220,"author":8,"category":28,"date":928,"description":1221,"extension":12,"featured":13,"image":1222,"meta":1223,"metaDescription":34,"metaTitle":1224,"navigation":18,"path":1225,"seo":1226,"stem":1227,"tags":1228,"__hash__":1231,"__readTime":39},"blog\u002Fblog\u002Fwere-not-saas-not-an-integrator-on-purpose.md","We're Not SaaS. We're Not an Integrator. On Purpose.","Procurement wants us to be a software vendor or an implementation partner. We are neither, and I think the model in between is what gets AI into production.","\u002Fblog\u002Fblits-positioning-hero.png",{},"Not SaaS, Not an Integrator, On Purpose","\u002Fblog\u002Fwere-not-saas-not-an-integrator-on-purpose",{"title":1220,"description":1221},"blog\u002Fwere-not-saas-not-an-integrator-on-purpose",[53,54,1229,1230],"platform","company","NNBRDZDagTR5umxOvb2Os1ZCgfhPE4FIwUzmjgyZSYc",{"id":1233,"title":1234,"author":154,"category":28,"date":1235,"description":1236,"extension":12,"featured":13,"image":1237,"meta":1238,"metaDescription":1239,"metaTitle":1240,"navigation":18,"path":1241,"seo":1242,"stem":1243,"tags":1244,"__hash__":1246,"__readTime":71},"blog\u002Fblog\u002Fwhat-ai-native-means-for-a-bank.md","What \"AI Native\" Actually Means for a Bank","2026-12-04","Every bank now has AI. Very few are AI native. The difference is not the number of pilots but whether the bank's processes run on AI, with people making the decisions. What AI native means in practice, what the leaders already show, and five shifts that separate AI added from AI native.","\u002Fblog\u002Fblits-ai-native-bank-hero.png",{},"AI native is more than a chatbot. What an AI native bank looks like, what DBS, JPMorgan and BNY already do, and five shifts from AI added to AI native.","What AI Native Actually Means for a Bank","\u002Fblog\u002Fwhat-ai-native-means-for-a-bank",{"title":1234,"description":1236},"blog\u002Fwhat-ai-native-means-for-a-bank",[1245,56,54,52,136],"ai native","fXtWAaRr-S_BtaDs4aqjaPZPdQRfQ7L3j276gRIvzeI",{"id":1248,"title":1249,"author":8,"category":28,"date":1250,"description":1251,"extension":12,"featured":13,"image":1252,"meta":1253,"metaDescription":1254,"metaTitle":1255,"navigation":18,"path":1256,"seo":1257,"stem":1258,"tags":34,"__hash__":1259,"__readTime":251},"blog\u002Fblog\u002Fwhat-is-artificial-intelligence.md","At this point, most people are afraid to ask a simple question; what is artificial intelligence (AI)?","2023-03-28","Someone once told me stupid questions don't exist. Maybe so, but people are still afraid to look stupid by asking about things that are assumed to be general knowledge, and Artificial Intelligence (AI) is one of them. With ChatGPT and Midjourney everyone loves to talk about AI, yet I only know a handful of people who actually know how it works. So here are the basics.","\u002Fblog\u002F1678649727454.jpeg",{},"Everyone talks about ChatGPT and Midjourney, yet few people know how AI actually works, and many are afraid to ask. So here are the basics.","What Is Artificial Intelligence (AI)?","\u002Fblog\u002Fwhat-is-artificial-intelligence",{"title":1249,"description":1251},"blog\u002Fwhat-is-artificial-intelligence","puXtdqK7g8r2GrDbxm4d77lDflWUdtOTBEqLRtvmeIs",[21,37,50,69,82,118,133,148,163,180,196,246,263,280,299,317,330,348,365,380,411,441,454,467,481,494,512,525,556,569,600,634,650,666,681,921,934,948,974,1021,1035,1048,1063,1075,1090,1106,1120,1135,1149,1165,1178,1195,1212,1227,1258],1794572851585]