LangChain details how its Labs team trains custom models for LangSmith Engine with Baseten Loops
LangChain · x · 2026-09-16
LangChain shares how its Labs team uses Baseten Loops to train custom models for LangSmith Engine, its in-platform agent. The workflow: pick a problem/agent to improve, curate data and evals/environments, run many training experiments with continuous measurement, and loop. The thesis: the future is continuously turning valuable data into better/faster/cheaper models — 'Owning your Intelligence' — and today's infra lets any team run hundreds of experiments to optimize quality/cost/latency.
Related event: LangChain Trains Custom Agent Models on Baseten Loops(2 posts)→
More from coding & agent
- AI Evals FAQ grows to 48 Q&As: sensitive data, huge traces, and stale gold datasets — HamelHusain · 2026-09-16
- One prompt to a real object: AI agent models in Blender and 3D-prints the result — anthara_ai · 2026-09-16
- Open-source crew of 8+ AI agents manages your Obsidian vault, email triage included — tom_doerr · 2026-09-16
- AI agent gets user's $70 Amazon credit after weeks of runaround, one tap needed — armand_ruiz · 2026-09-16
- 3 weeks through Stanford CS329A: the generator has outrun the verifier — le_james94 · 2026-09-16
- Generator outruns verifier: 250 samples lift DeepSeek-Coder to 56% on SWE-bench — le_james94 · 2026-09-16