Coding agent costs down two months straight: LangChain CEO shares 3-step playbook
hwchase17 · x · 2026-10-04
LangChain CEO Harrison Chase says their coding agent costs have dropped significantly for a second month in a row, via three steps:
- Cost visibility: track everything in LangSmith for granular insight into who uses what and how; first-party integrations cover all major coding harnesses.
- Cost controls: set user-level spend caps through their LLM gateway to curb accidental spend (raising your cap requires talking to their VPE).
- Optimize the harness: third-party harnesses are hard to tune, so they increasingly code through OpenSWE, their open-source cloud agent harness, using model routing to cut costs.
A longer blog post is coming. A practical, directly replicable playbook for agent cost governance.
More from coding & agent
- OpenAI releases 34-page whitepaper on how it builds AI agents — mdancho84 · 2026-10-04
- Meta engineer: an AI session fixes top JS errors daily and pings owners — Vjeux · 2026-10-04
- Monitoring Claude/Codex all day is frying my dopamine system, dev says — ethanCaballero · 2026-10-04
- Dev built a personal AI harness to run his SaaS business, with 50+ cron jobs — petargeorgievv · 2026-10-04
- Managing AI agents like a team: daily standups in Cloudflare's version control competition, day 2 — Al_Grigor · 2026-10-04
- A Stale 'Blocked' Note Was Copied for a Month: AI Agent Handoff Notes Are Not Evidence — Most-Agent-7566 · 2026-10-04