UX3 Product Design Harness

1---
2name: product-design-harness
3description: Use when a product direction, feature, workflow, experiment, launch, feedback signal, automation, or scale decision needs judgment before execution or the next iteration.
4license: MIT
5---
6 
7# Product Design Harness
8 
9Decide whether a product direction should continue, be verified, or be
10reframed anywhere in the product loop.
11 
12Execution includes design, implementation, prototype, launch, growth,
13automation, or investment.
14 
15## Start
16 
17Load in this order:
18 
191. `resources/schemas/session-config.schema.json`: set `working_language`; keep
20   `canonical_identifiers` in English.
212. `resources/knowledge/ontology.json`: use the canonical UX3 knowledge kernel and its
22   approved Flow definitions.
233. `resources/knowledge/rules.json`: load required rules plus only triggered conditional
24   rules.
254. `resources/prompts/start-review.md`.
26 
27Then fill `resources/templates/product-brief.md`, select the smallest responsible mode,
28and return `resources/schemas/review-result.schema.json`.
29 
30Validate every review result with `resources/scripts/check_review.py`. JSON Schema checks
31shape and conditional fields; `check_review.py` is the canonical validator for
32the worst-verdict, weakest-flow, and headline-tier semantic checks.
33 
34## Modes
35 
36| Mode | Use when |
37|---|---|
38| Quick Gate | Small, reversible, low-risk change. |
39| Standard Gate | New feature, workflow, or experiment. |
40| UX3 Council | High uncertainty, external evidence, meaningful risk, multiple reviewers, or human-owned trade-off. |
41 
42Handoff is not a review mode. When a prior review already returned continue,
43reuse its context pack instead of running a new review.
44 
45Reversibility lowers mode, not the review requirement.
46 
47## UX3
48 
49Review three connected dimensions:
50 
51| Flow | Core question |
52|---|---|
53| User Flow | Who is the product for, who is affected, what are they trying to accomplish, and what cost or loss of control exists now? |
54| Evidence Flow | What signal was observed, where did it come from, what interpretation is being made, what counter-signal weakens it, and what decision impact follows? |
55| Business Flow | Who creates value, receives value, pays or decides, bears cost or risk, and can the exchange remain viable and legitimate? |
56 
57Then inspect the intersections: Situated Understanding, Viable Learning,
58and Sustainable Value Exchange.
59 
60## UX3 Decision Kernel
61 
62Apply the same reduction sequence to every submitted review:
63 
641. Validate lane contracts and evidence references with `resources/scripts/check_review.py`.
652. Reduce to the worst verdict and deterministic weakest flow.
663. Gate uncertainty, risk, reversibility, and human-owned calls.
674. Emit one canonical verdict, next action, execution boundary, and stop conditions.
68 
69Do not average lanes. Human-owned calls are recorded through an accountable
70decision record; they are not converted into a machine score.
71 
72Before handoff, name product organization, issuer, stakeholder effects, and
73accountable owner. Missing issuer or owner blocks implementation.
74 
75## Operating Rules
76 
77- Do not implement during review.
78- `verify` branch: verify authorizes only the exact proof_step and never
79  general coding.
80- `continue` branch: continue plus a valid context pack authorizes implementation.
81- Every result states `may_do`, `must_not_do`, and `must_ask`.
82- List disconfirming evidence before support.
83- Do not average reviewer verdicts.
84- The weakest flow controls the next action.
85- External tools return evidence receipts, not verdicts.
86- Evidence tier controls action size; confidence does not upgrade weak proof.
87- Council mode requires independent reviews and a challenge round.
88- If all independent Council reviews return continue, a valid
89  resources/schemas/red-team-review.schema.json result must be attached to
90  the Council input before synthesis.
91- Designer taste is a human-owned input, never an evidence score.
92- Incoming feedback must be classified before it changes direction or work.
93- Human-owned decisions stay human-owned.
94 
95## Triggered Distilled Rules
96 
97Load only rules whose observable trigger applies. These families refine the
98three Flow reviews; they do not create new verdicts or allow a strong Flow to
99outvote a weak one.
100 
101| Situation | Required rule |
102|---|---|
103| Mental-model mismatch, hidden capability, or misunderstood consequence | `ux3.rule.mental_model_alignment` |
104| Cognitive or recovery burden across human, task, tool, and environment | `ux3.rule.human_factors_load` |
105| Research claim, synthetic user, simulation, interview, survey, test, or analytics result | `ux3.rule.research_validity` |
106| Value proposition, positioning, buyer, channel, or GTM path before fit is proven | `ux3.rule.value_market_path` |
107| Agent plan or tool action that needs visibility, control, handoff, or recovery | `ux3.rule.human_agent_interaction` |
108| Retention, personalization, or gamification that changes repeated behavior | `ux3.rule.motivation_ethics` |
109 
110## Outcome
111 
112| Verdict | Required next step |
113|---|---|
114| continue | Create resources/templates/context-pack.md within the execution boundary. |
115| verify | Run one proof step only. |
116| stop_reframe | Stop execution and return a better product question. |
117 
118Use triggered rule IDs for detail instead of duplicating every rule in prompts.
119Common triggers include ux3.rule.actor_boundary,
120ux3.rule.problem_hypothesis, ux3.rule.evidence_separation,
121ux3.rule.minimum_validated_proof, ux3.rule.feedback_classification, and
122ux3.rule.human_judgment. The distilled trigger table above covers additional
123rules that activate only when their specific product condition appears.
124 
125Use resources/docs/HARNESS.md for the handbook, resources/docs/OPERATING-PROTOCOL.md for the six-gate protocol,
126resources/docs/CONTRACTS.md for output rules, and resources/examples/ for worked reviews.
127