LangChain Introduces Trajectory: Using Observability Data for Memory & Learning
hwchase17 · x · 2026-08-15
LangChain released new docs on Traces, Threads, and Trajectories (a new concept), detailing how observability data is structured:
- Run: A single unit of work (e.g., a model call).
- Trace: A collection of runs for a single operation.
- Thread: Links traces from multi-turn sessions, preserving nested structure.
- Trajectory: Flattens the entire session into an ordered list of messages, showing the agent's path from start to finish.
The author notes that observability data is now used for memory and learning, not just debugging.
More from coding & agent
- Sandbox escape detection framework for AI agents: six steps including monitoring, alerting, and red-teaming — blaizedsouza · 2026-08-15
- Multi-agent systems are the next abstraction, potentially creating super-intelligence — scaling01 · 2026-08-15
- Grok 4.6 now available in GitHub Copilot — intellectronica · 2026-08-15
- AQuA: Recursively Self-Improving Quantitative Trading Research Agents — MengdiWang10 · 2026-08-15
- Cursor's Returns Are — Scobleizer · 2026-08-15
- Discussion: Underrated coding agents besides Codex and Claude Code — ai__supremacist · 2026-08-15