How Internal Revenue Service uses AI

IRS procurement staff must produce extensive documentation for every contract file, and drafting and quality review were largely manual and slow, with some errors missed. Since July 2025 the IRS AI Contract Document Toolbox gives them a generative AI chat that drafts first versions of procurement documents, summarises and rewrites documents and extracts data, and that can be instructed to apply lessons learned and new procurement policy goals and to detect common past errors. Staff refine the drafts and vet documents together with the AI; the inventory states that the tool offers recommendations but does not approve contracts, and that agency officials make the final decisions. It records the use case as presumed high impact but determined not high impact. No outcome figures are published.

No outcome disclosed.

Since April 2025 the IRS runs an analytics hub for contract documents and contract spending data in which generative AI reads contract PDFs and writes a summary of the products or services bought under each agency contract into a table. The aim is better category management and a better view of what the agency buys. Outputs go to contracting officials for review, and the inventory classifies the use as not high impact because it is not the principal basis for significant decisions. No outcome figures are published.

No outcome disclosed.

The IRS User and Network Services IT service desk runs a generative AI pilot, described as a limited production challenge, that summarizes incident case notes for warm handoffs, writes resolution notes from the actions taken, and generates complete knowledge base articles from incident and case records. The agency expects the effort to feed its existing knowledge review and publication processes, save time on handoffs, shorten the mean time to restore and support more self service, but publishes no results.

No outcome disclosed.

IRS training developers used to record course narration with employees and microphone kits; with return to office mandates that was no longer possible. Since May 2024 they enter narration scripts into a web based AI voice tool that returns audio files for import into eLearning authoring applications. Scripts contain no personal or taxpayer information and use fictitious names and addresses. The IRS reports better quality, a wider choice of voices and much faster generation and revision of voiceovers, but publishes no figures.

No outcome disclosed.

In September 2023 the IRS announced that it was expanding its Large Partnership Compliance programme, which it described as a pilot leveraging AI, to additional large partnerships. It said the returns had been selected with the help of AI by data scientists and tax enforcement experts who applied machine learning to identify compliance risk in partnership tax, general income tax and accounting, and international tax. The IRS said it would open examinations of 75 of the largest partnerships, each with more than USD 10 billion in assets on average, a segment that had seen little examination coverage. The IRS also said AI would help improve case selection so that fewer taxpayers face audits that end with no change. No outcome of the AI selected examinations is published in the release.

No outcome disclosed.

Since 2021 the IRS has put intent based voice bots on many toll free lines: payment plans and balance due (with authentication so taxpayers can set up or change a payment plan), Where's My Refund and amended return status, notice clarifications, Economic Impact Payments and the Advance Child Tax Credit. On IRS.gov, chatbots answer FAQs on refunds, identity theft, payments and relief. The inventory stresses that answers are not generated: the model classifies the question and returns content approved by the business owner, or routes the call to a live assistor.

• Interactions handled: at least 3 million, calls answered by voice bots, cumulative to June 2022

  "To date, the voice bots have answered over 3 million calls."

  Claimed by: organization

The IRS runs an AI based synthetic data generator that builds a large population of synthetic people, households and businesses, ages them over time and correlates them with the socioeconomic patterns of US taxpayers. It outputs synthetic individual and business tax returns for several tax years, plus the reference files that seed test systems, so tax processing systems can be tested, including simulated fraud cases, without exposing taxpayer information. Automated checks run on every schema version to catch anomalies in the generated returns. No outcome figures are published.

No outcome disclosed.

The IRS Linguistic Policy, Tools and Services team uses a cloud machine translation application on AWS, with the IRS Publication 850 glossary of English and Spanish tax terms, to translate text and files between English and Spanish, Chinese, Korean and Vietnamese and speed up responses to taxpayers. Separately, staff use SYSTRAN neural translation, augmented with a domain dictionary and translation memories, to triage non English documents for relevance to case work and as a starting point for manual translation. Both appear in the federal AI inventory as in operation.

No outcome disclosed.

The IRS reports a pilot, with a 2019 operational date, that researches supervised learning methods to assess contractor responsibility and predict whether a prospective vendor would perform successfully, identifying vendors at heightened risk of poor performance or non compliance. The models are trained on contractor and contract data from SAM.gov and USASpending.gov, and the risk assessments are delivered as spreadsheets or dashboards. The AI only recommends: contracting decisions go through several layers of review by agency officials. The seminal research and model training were done by IRS and US Navy personnel. It remains a pilot and no outcome figures are published.

No outcome disclosed.