Q Answer-format search page
85 tool calls per prompt — the one-line delegation pattern
✦ AI editor's answer
Invisible plumbing (runtime, ontology, DB packaging) is laid at a 1-prompt = 85-tool-calls ratio. Lay it before features — otherwise the feature relays it every time.
Source: 4 notes from this publication + operator work logs
Source notes (4)
- Patterns2026-05-24
248 sessions that built plumbing, not features
85Tool calls per prompt — the one-line delegation unit› 85 tool calls per prompt is the unit of real automation — the 'one-line delegation' pattern.
- Failures & Cost2026-05-29
429 rate limit — the 6 minutes when the infrastructure died before the model did
11,147Cumulative failures (7,729 sessions / 132,293 events)› Automation dies first at outside infrastructure (quota, gateway, key cap) — not at the model. Same model, same prompt can still die in 6 minutes. Bake that in as a baseline.
- Tooling2026-05-25
26 hands — but one of them passed 1,333 messages
1,333Messages exchanged by a single deep session› Session count is the weaker signal; messages and tool-calls per session are the real automation depth.
- Failures & Cost2026-05-20
Remastering 178 cards — until the batch ran clean
11,147Failure events (7 buckets)› Enforce a No-Placeholder Policy on AI batch jobs — failures only become data if no fake file gets written on miss.
Related questions