ImageFirmAgent engineeringA-05
SheetA-05
Added2026-08
Source1 blueprint poster
MethodVs real mechanisms

The Agent Loop, Verified

"Let AI agents run while you sleep," promises a widely-shared Loop Engineering 101 poster. Its core distinction — open loops that wander versus closed loops that terminate — is the single most useful idea in amateur agent operation, and it's correct. Around that core: sound building blocks, one genuinely good pattern, and the usual unsourced numbers. The ledger sorts them.

01 — The core distinctionOpen loops wander; closed loops finish

The poster's centerpiece survives contact with practice. An open loop — "keep improving until it's good" — has no termination condition, drifts from its objective, and burns budget in proportion to your patience. A closed loop has a defined goal, validation checkpoints, budget limits, and predictable outcomes. Every serious harness pushes you the same way: goal-conditioned running (state a testable finish line), scheduled runs with fixed scope, and verification before exit. This is the same lesson as I-09's "state the finish line, not the steps" — arrived at from the failure side.

The maturity ladder (prompter → operator → loop designer → system architect) is a reasonable self-diagnostic, folklore though the level boundaries are: the real threshold is the step from running agents to designing the loops agents run in.

02 — The building blocks, checkedSix named parts, five real

The good pattern

The self-learning loop — run, catch mistake at the quality gate, write the lesson to a rules file on disk, future runs read it — is the poster's best content. It's the compounding trick: failures become reusable rules. The file name varies by system (the poster says RULES.md); the practice is portable and worth stealing.

03 — The ledgerNine claims, checked 2026-08-06

ClaimVerdictThe record
Open vs closed loops as the core distinctionVERIFIEDMatches goal-conditioned running and budget-capped scheduling in real harnesses.
Goal → plan → execute → verify → iterate cycleVERIFIEDThe documented agent loop, correctly drawn.
Quality gate before shipping (tests, linters, checks)VERIFIEDSound: no gate, no unattended loop.
Maker and checker never the same agentVERIFIEDStandard verification practice; same rule this library operates by.
Work trees for collision-free parallel agentsVERIFIEDReal mechanism, accurately described.
Self-learning loop via a rules file on diskVERIFIEDPortable practice; file naming is per-system convention.
Single agent vs fleet framing (simplicity vs scale)NUANCEFair heuristic; the real trigger for a fleet is verification needs, not size alone.
"Open-loop agents can burn 2M tokens in a single run"NO SOURCEDirection true, number invented. Unbounded loops burn what you let them.
"Let AI agents run while you sleep"NUANCETrue exactly when the loop is closed, gated, and budgeted — the poster's own conditions, which the headline forgets.
A-05 · THE AGENT LOOP, VERIFIED · ADDED 2026-08 · ORIGINAL WORK, SOURCES CHECKED 2026-08-06 · VERIFIED SERIES No. 9
PRIMARY SOURCES · agent-harness documentation on goal-conditioned and scheduled runs, subagents, skills (docs.claude.com / code.claude.com) · companion sheets I-09 (operator patterns), C-11 (where the files live)
BLUEPRINT SOURCE · one third-party "Loop Engineering 101" poster, on file in the private register — analyzed, not reproduced