LATAM Airlines Cuts Agent Out-of-Scope Rate to 1% Using Production Traces
LangChain · x · 2026-08-20
LangChain shares a case study from LATAM Airlines where analyzing production conversation traces revealed that 95% of messages marked as "out of scope" were legitimate passenger needs. By adding a customer-care specialist agent, they reduced the out-of-scope rate from 13% to 1% and improved the return rate by 6%. The post also compiles lessons from Lyft and Vodafone on using production feedback to improve agent performance.
More from coding & agent
- Updating an agent app remotely via another agent — yacineMTB · 2026-08-20
- OpenKnowledge launches ACP to support 'Bring Your Own Agent' — iamrobotbear · 2026-08-20
- Papers with Code adds paper visualizations powered by the Excalidraw MCP — NielsRogge · 2026-08-20
- MUZIM: Local-First AI Media Agent with MCP Integration — dr_cintas · 2026-08-20
- Max Drake: Canvas as Boundary Object Between You and Your Agent, Sketch to Code — max__drake · 2026-08-20
- Coding FPGA with Codex: Day 1 progress includes HDMI output and FM synth monitoring — blaizedsouza · 2026-08-20