The Missing Primitive in AI-Employee Tooling: Agents Can't Watch and Wait
corbtt · x · 2026-11-05
The author argues that AI-as-employee tooling still lacks a primitive for monitoring the situation. Agents can work autonomously until they hit a blocker — waiting on a customer to send data, a days-long training run to finish — at which point a human has to tell them to fetch the update. He frames "wait for and sense external state changes" as a missing abstraction and a key gap in agent autonomy.
More from coding & agent
- Five ways an agent run can end: success, giving up, budget, human handoff, failure — ClickOk5811 · 2026-11-05
- Solo dev builds Suno + three.js music video pipeline with Claude Code in hours — Glass-Garden-5888 · 2026-11-05
- An obscure git command yields a 12% speedup, tested on the Linux kernel repo — DanielLockyer · 2026-11-05
- Visual Token Routing cuts VLM agent visual tokens up to 5.8x at same accuracy — wellecks · 2026-11-05
- Solo dev's open-source browser agent uses local models to watch your screen and trigger actions — Roy3838 · 2026-11-05
- Model selection is a routing problem: match model size to task ambiguity, says Together — togethercompute · 2026-11-05