LukeW: developers now supervise hundreds of agents; Intent open-sources the next abstraction layer
LukeW · x · 2026-09-03
Luke Wroblewski's new article argues the next abstraction layer in AI products is agents handling application use. The most forward-leaning developers he works with now supervise many agents across many projects—hundreds or more coordinating to build, test, and ship software—while chat-era developer tools fall behind. His team redesigned and open-sourced Intent, which scales agent work by turning tasks into isolated workspaces with separate file copies, each run by a living spec and a coordinator that delegates to specialized sub-agents without babysitting, plus a higher-level agent managing work across workspaces and devices. The design goal is observability and introspection over large amounts of agentic work. He also notes more developers now skip manual review of agent code changes, interacting only with coordinator agents while retaining the ability to dive in and course-correct.
More from coding & agent
- Revera: Lean-verified POSIX regex engine with identical output in 6 languages — jedisct1 · 2026-09-03
- Fable 5.1 produced a result in ~10 minutes on the $100 plan — jasondeanlee · 2026-09-03
- Runway launches Dev MCP server for coding agents — tlakomy · 2026-09-03
- 7 GitHub Repos Turn One AI Agent Into an OS: Memory, Model Routing, Free Compute Stacks — garrytan · 2026-09-03
- The Zvi: agents rewire your reflexes — annoyances now get fixed by just asking Claude Code — TheZvi · 2026-09-03
- "A smarter model in a bad system just makes expensive mistakes faster" — iamKierraD · 2026-09-03