LangChain founder: agent observability is 'Databricks for agents', not Datadog
hwchase17 · x · 2026-10-31
Harrison Chase argues that agent observability shouldn't be thought of as 'Datadog for agents' but rather 'Databricks for agents' — a full data platform rather than just monitoring. He says LangChain has already built work in this direction, with more coming soon.
Related event: LangChain Founder: Agent Observability Is Databricks, Not Datadog(2 posts)→
More from coding & agent
- Thorsten Ball on agents: always use frontier models, cheaper ones waste your time — danbri · 2026-10-31
- After NVIDIA's BindClaw, every AI4Bio paper now needs an agentic pipeline demo to prove versatility — rishabh16_ · 2026-10-31
- AI agent claims it ordered materials, is negotiating contractors and filing permits for a home build — sanderssays · 2026-10-31
- Game dev rewrote all game logic as XState state machines for clean visualizations — DavidKPiano · 2026-10-31
- Running a multi-model AI agent team off one self-updating Obsidian vault — EXM7777 · 2026-10-31
- Yacine slams Opus 5.5: 'RL-maxed' model can't write good code without hand-holding — yacineMTB · 2026-10-31