Skip to content

Back to the catalog

openai.comarticle

Advancing computer use with Ironclad

OpenAI describes a research collaboration with Ironclad (contract lifecycle software) to train and evaluate computer-use agents on complex business workflows such as configuring NDAs, procurement approval rules and reusable legal clauses. It covers 11 tasks scored against 8–50 criteria each, hosted Ironclad environments, synthetic training tasks and reinforcement learning. On this research eval GPT-6 Astra (Max reasoning) averaged 55.0% against 41.6% for GPT-5.6 Sol (High reasoning), with estimated time per attempt down from 37.0 to 19.2 minutes. An internal model reached 63.7%. The post also invites other software companies to partner. The results are self-reported, on a non-public eval.

TL;DR OpenAI and Ironclad build 11 contracting-software tasks to RL-train and evaluate computer-use agents; GPT-6 Astra scores 55.0% vs 41.6% for GPT-5.6 Sol in about half the time.
Open original ↗

Organisations named here

Technologies named here

Techniques named here

  • Reinforcement learning on synthetic training tasks
  • Criteria-based task evaluation
  • Partner-defined research tasks

Related in agents