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.

Original post →

More from coding & agent

coding & agent channel →