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.
Related event: LangChain Cuts Coding Agent Costs 64% with Model Routing(2 posts)→
More from coding & agent
- Andriy Burkov's True Positive Weekly #186: what to know when agents do the work — burkov · 2026-11-20
- Raycast launches MCP: let Claude, Codex and any agent drive your Mac launcher — dean_rie · 2026-11-20
- A 6-model board for decisions: hide opinions, let Claude chair and adopt the sharpest argument — aryanXmahajan · 2026-11-20
- Zed Delta agents can now run background terminals and get notified on completion — dean_rie · 2026-11-20
- Gemini app for Mac ships computer use, automating tasks across folders, apps and the web — GeminiApp · 2026-11-20
- Linear data: 53% of merged code now ships with AI review only, no second engineer — rseroter · 2026-11-20