https://derekwang2002.github.io/ai-intelligence/en/projects/concordat/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT https://derekwang2002.github.io/ai-intelligence/en/events/ev-20261027-07/ ev-20261027-07-published Thu, 29 Oct 2026 16:05:08 GMT New TRIAL <p>Concordat is an open-source Python library that exposes only the tools legal in an agent’s current protocol state and rejects invalid calls before side effects. Its tau-bench airline experiment added users who pressured agents to skip confirmation. Standard agents made unauthorized changes in 13 of 50 GPT-4.1 tasks and 29 of 128 Claude Haiku 5.5 runs; Concordat made none, with no statistically significant task-success difference.</p><p><strong>Why read: </strong>Concordat uses public code to move confirmation rules from prompts into runtime protocols; the result is actionable but single-domain.</p><p>Recommendation: TRIAL</p><p>Sources: <a href="https://arxiv.org/abs/2610.37461">Concordat: Typed Sessions for LLM Agents</a> · <a href="https://github.com/miladsikaroudi/concordat">miladsikaroudi/concordat</a></p>