Harrison Chase on using decision models to rein in agent workflows
hwchase17 · x · 2026-09-22
LangChain founder Harrison Chase highlights Josh Rosen's article on using decision models and AI checkpoints to manage agent work. The piece argues AI is at an awkward stage: trust in agents is low, yet models are becoming capable enough that we want them to just do the work. Chase likens the approach to a "goal" mechanism—but one requiring you to hit multiple goals in a row.
More from coding & agent
- jev-model-router Routes Claude Code Tasks Between Models via Function Hooks — dr_cintas · 2026-09-22
- A coding agent prompt: use my dotfile, keep keys safe, test locally without help — yoobinray · 2026-09-22
- Why devs skip Tinker for posttraining: cost and owning your own code — silver__tsuki · 2026-09-22
- codebase-memory-mcp indexes codebases into a persistent knowledge graph in milliseconds — tom_doerr · 2026-09-22
- Ambion: A Collaboration Kernel Running Multiple Agent SDKs in One Shared Room — andreisavu · 2026-09-22
- Formal Verification and Chaos Testing for Multi-Agent Systems with Dafny — andreisavu · 2026-09-22