Managed Deep Agents can now be steered mid-turn while agents work
hwchase17 · x · 2026-11-07
LangChain's Managed Deep Agents now support mid-turn steering: new user messages are read at the next model call instead of waiting for the turn to finish. A small change that makes long-running agents much nicer to work with, as shown in the accompanying diagram.
More from coding & agent
- Scope benchmark: only 16.6% of 1,035 AI agent attempts can sign up for hosted databases — RaphaelDabadie · 2026-11-07
- Every cloned its Slack with 51 AI coworkers trained on chat history via DSPy GEPA — lateinteraction · 2026-11-07
- User taunts AI coding agent about an edge case — it had already handled it at line 803 — alexanderchen · 2026-11-07
- GitHub Copilot adds one-time sign-in across Figma, Sentry, Slack, synced to every surface — 0xkarasy · 2026-11-07
- 'No moat, it's all a .md file': recreating a lens perspective illusion with Claude Code — itsOmSarraf_ · 2026-11-07
- Open-source tool shows system prompt and tools can eat 98% of API tokens — behrouzbk · 2026-11-07