AI use case

AI enterprise knowledge search for employees

An assistant that lets any employee ask a question in plain language and get a synthesized answer from the organization's own policies, procedures, product manuals and research, with citations to the source documents and only from documents the employee is allowed to see.

By Len Debets · Last verified 27 September 2026 · 4 public deployments

At least 23 million
Interactions handled
Bank of America (organization claim).
USD 2.3 million to USD 18 million
Indicative value per year
A bank with 5,000 employees who regularly look up policies and procedures. Worked example, see how it is calculated.

What problem does it solve?

In a bank or insurer the knowledge that staff need to do their job correctly is scattered across credit and risk policies, operating procedures, product manuals, compliance guidance and internal research: many documents in several systems, each with versions. Keyword search returns a list of PDFs. Staff ask a colleague, use an outdated copy, or give a customer a wrong answer.

Retrieval augmented assistants change the interaction: ask a question, get an answer with the paragraphs it came from. The hard problems are not the model. They are permissions (an answer must never come from a document the person may not see), currency (the answer must come from the version in force), and trust (people must be able to check the source quickly). Done well, one governed retrieval layer can serve the service desk, HR, frontline and specialist assistants instead of each building its own.

How does it work?

  1. Ingest and index approved sources. Policies, procedures and research are ingested from the document management system, intranet and knowledge base, with owner, version and access rights kept as metadata.
  2. Retrieve with permissions. When an employee asks, retrieval runs only over documents their role and entitlements allow, combining semantic and keyword search.
  3. Answer with citations. The model answers only from the retrieved passages and cites each document and section, so the employee can open the source.
  4. Refuse when unsure. If retrieval finds nothing relevant or sources conflict, the assistant says so and points to the owner, rather than guessing.
  5. Learn from gaps. Unanswered and badly rated questions go to content owners, who fix or write the missing document.
Audience
Employee facing
Autonomy
Assist
Adoption
Mainstream
Channels
Internal tools, Microsoft Teams, Agent desktop

What is it worth?

Benchmarks are computed from the public deployments below: one data point per organization per KPI, with who made each claim.

Value benchmarks for AI enterprise knowledge search for employees
KPIMedianReported rangeData pointsClaimed by
Interactions handledNot pooled
at least 23 million
11 organization

Value drivers: Employee productivity, Speed and cycle time, Compliance quality, Customer experience.

Indicative value

A bank with 5,000 employees who regularly look up policies and procedures

USD 2.3 million to USD 18 million

Employee time released per year

How this is calculated

Formula: employees * searchHoursPerWeek * workingWeeks * timeSaved * hourlyCost. The low scenario uses every low input, the high scenario every high input.

InputLowHighBasis
Employees who search internal knowledge regularly employees, employees5,0005,000The reference organization.
Hours per week each spends finding and reading internal information searchHoursPerWeek, hours per employee per week24Editorial assumption. Replace with a time study of your own staff.
Share of that time saved timeSaved, fraction of search time0.10.25Editorial assumption, replace with a time study of your own. No source on this page reports a measured share of search time saved. For comparison, Google Cloud reports that information searches by less experienced SIGNAL IDUNA agents are 30% faster (read as speed, that is about 23% less time per search, since 1 / 1.3 is about 0.77), and that Wells Fargo's tool reduced the workflow for query resolution by about 20%, without saying whether that is time.
Working weeks per year workingWeeks, weeks4545Editorial assumption.
Fully loaded cost per hour hourlyCost, USD per hour5080Editorial assumption. Replace with your own blended cost.

What it leaves out: Released time, not cash. It leaves out the value of fewer wrong answers to customers and fewer policy breaches, which is often larger, and the cost of cleaning up and maintaining the content.

Who already uses it?

4 public deployments, strongest evidence first. Grades: A regulator or audit, B the organization itself, C vendor case study, D anonymous or estimate.

Bank of America

United States · Wealth and asset management · 2024

ScaledGrade B

Merrill and Bank of America Private Bank teams use ask MERRILL and ask PRIVATE BANK, built on the technology behind Erica, to curate the information they need for clients. For more complex requests, the chat can connect teams with experts at the bank. The bank reports more than 23 million interactions with the two tools in 2024.

  • Interactions handled: at least 23 million, calendar year 2024
    "In 2024, there were more than 23 million interactions with ask MERRILL and ask PRIVATE BANK, an increase of 1 million over 2023, helping employees more proactively connect with clients about timely and relevant opportunities."
    Claimed by: organization

SIGNAL IDUNA

Germany · Insurance · 2025

ProductionGrade C

SIGNAL IDUNA, a German insurer, built Co SI with Google Cloud, BCG and Deloitte: a knowledge assistant that helps customer service agents answer complex health insurance questions. Google Cloud reports that for less experienced agents, information searches are 30% faster and inquiries that previously needed further escalation dropped from 27% to 3%.

No outcome disclosed.

Wells Fargo

United States · Banking · 2025

ProductionGrade C

Wells Fargo deployed a retrieval augmented tool for branch bankers that finds the relevant policies and procedures during customer interactions. Google Cloud reports that it reduced the workflow for query resolution by about 20%, without saying whether that means time, steps or effort. The bank uses reusable APIs on Apigee to scale generative AI across teams.

No outcome disclosed.

How do you implement it?

A model agnostic playbook: what to prepare, the order to build in, and what goes wrong.

Data you need

  • An inventory of authoritative sources with an owner and review date per document
  • Access rights per document or collection that can be carried into the index
  • A set of real questions per domain with expected answers, for evaluation

Systems to integrate

  • Document management and intranet (for example SharePoint or Confluence)
  • Identity provider and entitlement data for permission aware retrieval
  • The channels where employees work (Teams, the agent desktop, the intranet)
  • Feedback routing to content owners

Complexity: Medium

A prototype over a folder of PDFs is quick to build. Production takes longer: connecting several document systems, carrying access rights into the index, handling versions and retirement, and building evaluation sets per domain so answer quality can be measured.

  1. 1

    Start with one domain and its owners

    Pick a domain with heavy lookup volume and willing owners, such as operations procedures or product terms. Clean its documents before indexing anything.

  2. 2

    Carry permissions into retrieval

    Index access rights with every chunk and filter at query time. Test with accounts of different roles that restricted content never appears.

  3. 3

    Build the evaluation set

    Collect a few hundred real questions with expected answers and sources, and run them on every change to content, retrieval settings or model.

  4. 4

    Make citations the product

    Show the source passage next to the answer with a link. Staff trust and adopt tools whose answers they can check in seconds.

  5. 5

    Close the loop with content owners

    Send unanswered questions and negative feedback to owners weekly, and retire documents that are superseded.

  6. 6

    Offer it as a shared layer

    Expose the same governed retrieval to the other assistants (service desk, HR, contact centre) so permissions, residency and versions are enforced in one place.

Guardrails

  • Permission aware retrieval, tested with role based test accounts
  • Answers only from retrieved passages, with citations, and refusal when nothing relevant is found
  • Only the version in force is indexed; superseded documents are removed
  • Prompt injection defences for content from shared or external sources
  • Query logs protected and retained according to policy

KPIs to instrument

  • Answer accuracy and citation correctness on the evaluation set, per domain
  • Share of questions answered versus refused
  • Weekly active users among target employees
  • Time to find information in a time study, before and after
  • Negative feedback and content gaps closed per month

Human in the loop

Content owners are accountable for their documents and review flagged answers. Employees remain responsible for decisions they take on the basis of an answer, and high impact decisions (credit, compliance, customer remediation) still follow their documented approval steps.

Common failure modes

Oversharing through search
The assistant surfaces documents that were technically accessible but never meant to be widely read. Review permissions before indexing, not after an incident.
Confident answers from old versions
Superseded policies stay in the index. Index only the version in force and track effective dates.
Answers without sources
Staff cannot verify and either distrust the tool or trust it blindly. Always show the cited passage.
Many point solutions
Every department builds its own index with its own permissions. Build one governed layer and reuse it.

What are the risks and rules?

EU AI Act

Limited risk (transparency)

Article 50(1) requires that people who interact directly with an AI system are informed of it, unless this is obvious from the context, as it usually is for an internal assistant. The system would be high risk only if it were intended for an Annex III purpose, such as assessing the creditworthiness of natural persons (point 5(b)) or making decisions on or evaluating workers (point 4(b)).

Guidance

Controls to put in place

  • Inventory entry with an accountable owner and the list of indexed sources
  • Permission tests per role before each new source is added
  • Evaluation set runs on every change to content, retrieval or model
  • Document ownership and review dates enforced for indexed content
  • Monitoring of refusals, negative feedback and unusual query patterns

When it went wrong elsewhere

  • CVE-2025-32711: AI command injection in Microsoft 365 Copilot. A vulnerability recorded by NVD in June 2025, not a reported breach: AI command injection in Microsoft 365 Copilot allowed an unauthorized attacker to disclose information over a network. It shows that an enterprise assistant can be made to disclose information through injected instructions.

Frequently asked questions

How is this different from the search we already have?
Search returns documents; the assistant returns an answer with the paragraphs it came from. Google Cloud reports that Wells Fargo's retrieval tool for branch bankers reduced the workflow for query resolution by about 20%, and that information searches by less experienced SIGNAL IDUNA service agents are 30% faster.
Will employees actually use it?
Two wealth managers have published usage figures. Morgan Stanley said in June 2024 that 98% of its Financial Advisor teams had adopted its AI @ Morgan Stanley Assistant. Bank of America reports more than 23 million interactions in 2024 with ask MERRILL and ask PRIVATE BANK, a volume figure that does not say what share of employees use the tools.
How do we stop it from showing confidential documents?
Carry each document's access rights into the index and filter at query time, then test with accounts of different roles. Review what is technically accessible before you index it, because an assistant makes forgotten oversharing easy to find.

How to cite this page

Blits.ai AI Use Case Library, "AI enterprise knowledge search for employees", last verified 27 September 2026, https://www.blits.ai/ai-use-cases/enterprise-knowledge-search. Licensed under CC BY 4.0. Method: how we verify use cases.

Changelog
  • 27 September 2026: First published

Related use cases

Wealth and asset managementBanking

AI knowledge assistant for wealth advisors and relationship managers

A conversational assistant that answers a wealth advisor's or relationship manager's questions in seconds from the firm's own research, house view, product documentation and policies, with every answer linked to the source document so the advisor can check it before using it with a client.

Deployments
6 public, best grade B
Autonomy
Assist
Cross industryBanking

AI assistant for HR and policy questions

An employee self service assistant that answers questions on leave, pay and tax forms, benefits, expenses, travel and conduct policies from the organization's own HR documents, personalized to the employee's country and role, and starts simple HR transactions such as leave requests or employment letters in the HR system.

Deployments
4 public, best grade B
Reported employee adoption
99%
IBM, organization claim
Cross industryBanking

AI agent for IT service desk resolution

An AI agent in Microsoft Teams, Slack or the intranet that takes the high volume IT support queue, such as password and MFA resets, account unlocks, VPN, device and software requests, and resolves common requests by acting in the identity and IT service management systems, handing the rest to the right resolver group with the context attached.

Deployments
6 public, best grade B
Reported employee adoption
94%
Mercari US, vendor claim
Cross industryBanking

Real time AI assist for contact centre agents

A real time copilot for human contact centre agents during a live call or chat: it transcribes the conversation as it happens, surfaces the relevant knowledge and next step, drafts responses, and writes the after call summary and CRM notes, while the agent stays in control of what is said and done.

Deployments
5 public, best grade B
Reported productivity gain
15%
Definity, vendor claim
Cross industryGovernment and public sector

AI for support knowledge article generation and maintenance

AI that drafts knowledge base articles from resolved tickets, cases and conversations, detects questions the knowledge base does not answer and articles that are outdated or contradict each other, and proposes new or revised articles for a knowledge owner to review and publish.

Deployments
4 public, best grade B
Autonomy
Copilot
Cross industryBanking

Governed text to SQL analytics assistant

An assistant that turns a business user's plain language question into a query against governed data, runs it under that user's own data permissions and returns the table or chart together with the SQL and the tables used, so routine ad hoc questions no longer queue for the data team.

Deployments
3 public, best grade B
Autonomy
Assist