Basis completes a tax workbook 2x faster with GPT-6 Astra
- ID
- 29504
- Status
- summarized
- Published
- 28 Sep 2026, 8:00 AM
- Fetched
- 29 Sep 2026, 6:04 AM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/basis-tax-workbook-with-astra
- Source URL
- https://openai.com/news/rss.xml
Summary
- Score
- 3.0
- Created
- 29 Sep 2026, 6:05 AM
- Tags
- Audience
- ai_ml_learnersai_agent_userssaas_founders
What happened
OpenAI published a customer case study saying Basis, which builds AI agents that automate accountants' manual work, completed a 50-tab tax workbook in half the time with GPT-6 Astra compared with GPT-5.6 Sol, and saw roughly a 20% improvement in its internal evaluation scores. Basis co-founder Mitch Troyanovsky is quoted saying Astra better understands user intent, makes better decisions at the start of a task, and can dial reasoning effort up or down mid-task while keeping its cache intact, which he says lowers cost and response time on long-running tasks. Every number is self-reported by the vendor and its customer: there is no independent benchmark, no pricing, no context-window or token figures, and no availability date.
Why it matters
The only transferable detail here is cache-preserving adaptive reasoning on long agent runs, which is a cost lever if it is real - but this post gives you no price, no rate limits, and no way to verify the 2x claim, so do not plan a migration on it. Instead, treat the 50-tab workbook as a template for your own eval: pick your longest multi-step task, count the tabs-equivalent steps, and measure wall-clock time and token spend per run before believing any vendor speed claim.
Discussion angle
Ask the room to name the one long-horizon task in their own product that would serve as their '50-tab tax workbook' benchmark, and whether mid-task reasoning adjustment with cache retention is something they can even measure in their current stack today.