Why Your AI Coding Agents Fail After an Hour—and the Chief of Staff Pattern That Fixes It
Orchestrating Claude Code Agents: The Chief of Staff Pattern
Long-horizon AI coding fails because context is ephemeral and self-reports are unreliable. The fix is organizational: one coordinator session assigns work, verifies every claim by re-running commands, and maintains state on a durable external board, while separate short-lived sessions implement. This article details the operating loop, the tooling (Claude Code, cmux, Plan Desk), and the failure modes—like instruments that report success for work they never did—that the pattern exists to catch.
The single most common failure in agentic engineering is an instrument that reports success for work it did not do.
- albert_e
> What this is normally called
Is this also what Microsoft calls "Magentic" pattern?
(for a long time i kept reading it as Magnetic pattern)
https://learn.microsoft.com/en-us/semantic-kernel/frameworks...
- gritzko
This is close to my default workflow. One Fable to rule them all, many Opuses to implement. All work is planned, tracked and logged in plain Markdown tickets. No magic. Nothing to talk about.
Still, I have to keep an eye on it or it devolves into a mess real fast. An example from yesterday: I noticed the commit added 10K lines where it clearly should not have. 5min of digging: it was a combinatorial state explosion in the parsers. All at once because a shared grammar was tweaked.
Oopsies like this happen all the time, and with every passing hour it becomes harder to fix.
Can only rely on that chief-of-stuff for mundane things.
- ffsm8
i mean its not wrong, basically everyone learns this within a few weeks of actively working with the agentic loop.
but as usual with ai written content, the word bloat is roughly x5 of the words necessary to convey the message - with basically no effort on the meat proxy's part to clean it up in any way, shape of form