Preferences May Adapt. Policy Must Be Explicit.
Draw the line once
Preferences — density, tone, digest cadence, what “more like this” means for you — may adapt when evidence and policy allow.
Policy — Fourth Law thresholds, who must approve org-scoped change, which keys are locked — must stay legible and merged deterministically. No “the model felt 0.62 today.”
Read the effective surface
Operators start with GET /v1/humanos/policy/effective. It returns merged JSON including learning (memory scopes, allowed feedback types, learning_requires_approval) and confidence / review fields used by routing — see also HumanOS policy: threshold and config.
Admin overlays land with PUT /v1/humanos/policy/org (delegation humanos:admin), not by editing a row in an app database.
Preference keys are classified
set_preference proposals and POST /v1/humanos/tuning/actions reject policy-locked keys and keys outside adaptable prefixes — the same gate on both paths so there is no “bypass via proposals.”
Rollback is trust
If adaptation is a product feature, undo is too: POST /v1/humanos/learning/proposals/:proposal_id/rollback after apply — details in HumanOS learning, tuning, and rollback.
Next
Learning & Adaptation — Part 4 of 6
Code & Docs