Agent fleet landed 93 workflow changes, doubling daily experiments and cutting them 16h to 2.5h
jiayq · x · 2026-10-15
jiayq details how their agent fleet recursively improved its own process during ClickBench optimization: 397 proposed experiments, each with a design, independent review, correctness gates, and timing against the best build; 98 improved, 289 retired with written reasons, all logged in a shared record. An operations team of agents landed 93 workflow changes — after the biggest one (a quick check retiring weak ideas early), daily experiments nearly doubled and median experiment time dropped from 16h to 2.5h.
More from coding & agent
- 56% of US travelers already plan trips with AI — agentic tourism becomes a new distribution channel — robertonappe · 2026-10-15
- Data scientist's 2026 playbook: build a business decision machine with RAG + agents on the LangChain stack — mdancho84 · 2026-10-15
- Amazon blocks Meta's Muse shopping agent over unauthorized access — the agentic commerce gatekeeping battle begins — robertonappe · 2026-10-15
- Cut agent costs: route decisions to a cheap model, save Claude for the writing — Arindam_1729 · 2026-10-15
- Zenzap raises $44M and launches AI agents in its workplace chat app — testingcatalog · 2026-10-15
- LangChain Deep Agents demo: drop a CSV in Slack, get a slide deck back — Hacubu · 2026-10-15