2 sources filed · EN 2
Set-up: 30 API operations with an append-only audit log, 19 scored tasks plus two unauthorised-refund traps, baseline on Claude Sonnet 5.5 over three runs; thresholds set at twice baseline variance.
The agent ranked spans by frequency and duration and returned file, line, estimated weekly volume and an example trace per candidate; the engineer steered with short prompts and chose what to fix.
~143Mextra SELECT queries a week removed by reusing an already loaded project in ingestion hot paths
2 sources filed · EN 1 · JA 1
Origin: the team manager brought Coder back from KubeCon Japan 2026.
about 3xthe team manager's PRs in his first three weeks on the platform versus the three weeks before
Across 720 runs the largest prompt was 23k tokens against a 400k window (5.75%).
5.75%share of the context window used by the largest prompt across 720 agent runs