Anthropic's head of platform engineering on the new engineering problems agents create
danshipper · x · 2026-11-05
Every published a Thesis Statement by Katelyn Lesse, Anthropic's head of platform engineering: thousands of AI agents will soon work on one problem for weeks, raising new questions — who decides what agents may do, and who stops them when things go wrong? She argues software engineers face a fresh set of problems: infrastructure for long-running agents, permission systems worthy of human approval, and monitoring that can detect dangerous behavior.
More from coding & agent
- Tutorial: build phone apps with memory using GPT Live and Twilio Agent Connect — craigsdennis · 2026-11-05
- Engineer says manual tweaks after Claude optimization made EC2 CPU 50x faster than M4 Max — _Stocko_ · 2026-11-05
- A Rust todo app taking 14GB? Compile caches, not the app, eat ~13GB — lxfater · 2026-11-05
- Remote MCP: managing your devices remotely via the MCP protocol — Latter-Storage9610 · 2026-11-05
- MCP over HTTP: validating OAuth tokens isn't enough—check the audience claim — alvelda · 2026-11-05
- Short RL phase on GLM 5.3 Flash costs $372 vs $1,894 for notes, breaks even in 8.7 days — teortaxesTex · 2026-11-05