OpenAI, Thrive, and Crete deploy Codex-powered Tax AI, cutting preparation times by one-third with up to 97% accuracy
The system increased tax firm throughput by 50%.
#19Greg Brockman@GDBOpenAI for self-improving tax agents:
Building evaluations and fast feedback and iteration loops is the most reliable way of solving hard problems and improving the product rapidly.
Here, the amazing Crete team with collaboration from OpenAI automated majority of the field extraction work, done during tax preparation within weeks!
Read the full blog on how this was achieved: https://openai.com/index/building-self-improving-tax-agents-with-codex/
Boris Power@BorisMPowerBuilding evaluations and fast feedback and iteration loops is the most reliable way of solving hard problems and improving the product rapidly. Here, the amazing Crete team with collaboration from OpenAI automated majority of the field extraction work, done during tax preparation within weeks!
#357Boris Power@BORISMPOWERA glimpse of an exciting future where tax professionals will be able to spend more time advising customers and explaining the tax returns!
OpenAI and Thrive just built a self-improving tax agent with up to 97% accuracy.
Tax AI processed 7,000 returns across 30+ accounting firms, saved about one-third of preparation time, reached up to 97% accuracy, and raised throughput by about 50%.
The hard part was not reading W-2s or 1099s, but handling messy K-1s, rental schedules, notes, spreadsheets, prior-year files, and values that must match across documents.
The system records the full trace: source file, extracted field, citation, tax-engine mapping, accountant correction, and final filed value.
Repeated corrections become eval targets, so Codex gets a narrow task with evidence, code, tests, and a pass condition.
A wrong tax field can come from many places: bad extraction, weak mapping, unsupported workflow, prior-year carryover, or human judgment.
The clever part was not simply using Codex to write fixes, but building a product environment where repeated practitioner corrections became bounded, testable engineering tasks.
In the rental-property example, the agent could inspect source documents, extraction traces, mapper behavior, expected outputs, and regression tests before proposing a change.
Rohan Paul@rohanpaul_aiOpenAI and Thrive just built a self-improving tax agent with up to 97% accuracy. Tax AI processed 7,000 returns across 30+ accounting firms, saved about one-third of preparation time, reached up to 97% accuracy, and raised throughput by about 50%. The hard part was not reading W-2s or 1099s, but handling messy K-1s, rental schedules, notes, spreadsheets, prior-year files, and values that must match across documents. The system records the full trace: source file, extracted field, citation, tax-engine mapping, accountant correction, and final filed value. Repeated corrections become eval targets, so Codex gets a narrow task with evidence, code, tests, and a pass condition. A wrong tax field can come from many places: bad extraction, weak mapping, unsupported workflow, prior-year carryover, or human judgment. The clever part was not simply using Codex to write fixes, but building a product environment where repeated practitioner corrections became bounded, testable engineering tasks. In the rental-property example, the agent could inspect source documents, extraction traces, mapper behavior, expected outputs, and regression tests before proposing a change.
#1076Linus@THESEPHISTI really appreciate the lessons and technical ideas @samaysham & team were able to share about their tax agent system, which learns from production traces to self-improve via detailed tracing tightly integrated into deployment + an autonomous AI engineer.