Follow-up R1 from the microsoft/AI-Engineering-Coach exploration (docs/superpowers/explorations/2026-06-16-ai-engineering-coach-findings.md, issue #340).
Idea
/assess today evaluates habitat evidence — what the repository contains (HARNESS.md, CI, tests, reflections, specs). The MS project's load-bearing difference is that it coaches from behavioural evidence — what the engineer actually did in AI sessions (prompt quality, session hygiene, tool mastery, review cadence).
Triangulating declared habitat against observed behaviour would let /assess detect a new kind of gap — a behaviour-vs-habitat gap, sibling to the existing Habitat Build Gap (cognitive level vs operational mean). A team can have an L4 habitat and L1 session behaviour; only behavioural data reveals it.
Why this is gated
This requires ingesting AI session logs, which is a privacy/consent matter. Out of scope until a privacy/consent design exists. The MS precedent is on-device, read-only, no-phone-home — a posture our hooks/reflections/telemetry already share and could cite.
Scope of a future spec
- Privacy/consent model: what session data, stored where, retained how long, opt-in.
- The behavioural axes (see R2 / the MS 5 categories) and how they map to a gap signal.
- How the gap surfaces in the assessment template alongside the Habitat Build Gap.
Disposition
Deferred / largest of the five. Do not start without the privacy/consent spec. Highest strategic value of the set.
Follow-up R1 from the microsoft/AI-Engineering-Coach exploration (
docs/superpowers/explorations/2026-06-16-ai-engineering-coach-findings.md, issue #340).Idea
/assesstoday evaluates habitat evidence — what the repository contains (HARNESS.md, CI, tests, reflections, specs). The MS project's load-bearing difference is that it coaches from behavioural evidence — what the engineer actually did in AI sessions (prompt quality, session hygiene, tool mastery, review cadence).Triangulating declared habitat against observed behaviour would let
/assessdetect a new kind of gap — a behaviour-vs-habitat gap, sibling to the existing Habitat Build Gap (cognitive level vs operational mean). A team can have an L4 habitat and L1 session behaviour; only behavioural data reveals it.Why this is gated
This requires ingesting AI session logs, which is a privacy/consent matter. Out of scope until a privacy/consent design exists. The MS precedent is on-device, read-only, no-phone-home — a posture our hooks/reflections/telemetry already share and could cite.
Scope of a future spec
Disposition
Deferred / largest of the five. Do not start without the privacy/consent spec. Highest strategic value of the set.