LangSmith launches Trajectories: a readable chronological view of agent sessions
LangChain · x · 2026-09-25
LangChain shipped Trajectories in LangSmith, a chronological conversational view that aggregates human, AI, and tool messages across main agents and subagents for a full session.
- Faster root-cause analysis: see the path the agent took at a glance, then drill into the trace only where behavior deviated.
- SME-friendly review: experts can evaluate agent behavior without parsing nested traces.
- Continuous improvement: score trajectories with online evaluators, save sessions to datasets, and export examples for supervised fine-tuning.
It builds on LangSmith's run → trace → thread structure, turning multi-turn agent sessions into an at-a-glance narrative.
Related event: LangSmith Launches Trajectories for Readable Agent Runs(2 posts)→
More from coding & agent
- ECHO Paper Lands NeurIPS Spotlight: Terminal Agents Learn World Models for Free, Doubling GRPO Pass@1 — DimitrisPapail · 2026-09-25
- Kaigen, a C-based AI-native game engine, opens closed beta — gdechichi · 2026-09-25
- One-prompt Minecraft: AI-generated voxel game open-sourced, runs in browser and on Windows — gdechichi · 2026-09-25
- He used $100 of Claude credits to land his first VSCode PR — ThePeterMick · 2026-09-25
- What the OpenAI-Hugging Face incident says about agent oversight — rainerhahnekamp · 2026-09-25
- Podcast on AI state and harness engineering, with all visuals generated by Opus 5.5 — tensorqt · 2026-09-25