pbi-challenge

name	pbi-challenge
version	1.0.0
description	[Code Quality] Use when you need an AI-assisted Dev BA PIC review of PBI drafts.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Break drafter confirmation bias before grooming — by helping Dev BA PIC (Person In Charge — development Business Analyst responsible for technical review sign-off per squad) review BA drafters' PBI drafts with specific, actionable challenge prompts, surface every architectural-feasibility, vague-AC, missing-auth, cross-service, and M1-M6 gap so an INFEASIBLE or under-specified PBI never reaches grooming with a false APPROVE. AI provides analysis; human makes decision.

Summary:

• This is a CROSS-PERSON review, not self-review: a different reviewer (Dev BA PIC) challenges the BA drafter's PBI — never run on your own draft (use /review-artifact --type=pbi for that). The whole value is external skepticism that breaks the drafter's blind spots.
• Confirm the auto-detected module via AskUserQuestion BEFORE loading domain docs (Step 2) — wrong module = wrong entity context = false APPROVE; then load domain-entities-reference + relevant docs/specs/{App}/ feature docs.
• The M1-M6 Compliance Gate is BLOCKING and drives the verdict: any M1-M5 mandate failure forces REQUEST_REVISION with a challenge prompt naming the violated mandate ID + exact section/line/AC citation; an APPROVE over an M1-M5 violation is itself defective.
• Order matters to fight automation bias: present Challenge Prompts FIRST so the Dev BA PIC forms their own view, THEN the AI Verdict (APPROVE / REQUEST_REVISION / ESCALATE_TO_LEAD); challenges must be SPECIFIC with suggested answers, and the human records the final decision via AskUserQuestion.

Key distinction: Collaborative review tool (drafter → reviewer flow), NOT self-review (use /review-artifact --type=pbi for AI self-review).

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Why This Skill Exists

PBI drafts routinely pass informal review unchallenged on architectural feasibility, vague AC, missing auth scenarios, cross-service impact. /refine generates PBIs but does not adversarially challenge them — creation tool, not review tool. /review-artifact --type=pbi provides AI self-review for drafter, but drafter has inherent blind spots about own assumptions. Separate reviewer (Dev BA PIC) applying AI-assisted challenge prompts breaks drafter confirmation bias before grooming — catches gaps drafter cannot catch themselves.

Why not just /review-artifact --type=pbi? Drafter runs it on own work; even with adversarial prompts, drafter rationalizes own choices. pbi-challenge invoked by different person with different mandate — external skepticism requires different author, not different tool on same author.

Alternatives Considered

Approach	Pros	Cons	Decision
Extend /review-artifact --type=pbi with a reviewer-role flag	No new skill, single codebase	Drafter runs it themselves in practice; role separation breaks down without enforcement	Rejected — role separation requires a distinct invocation point owned by a different person
Fully autonomous AI verdict (no human decision)	Faster, no Dev BA PIC scheduling needed	Automation bias: AI wrong on domain specifics propagates unchecked; no human accountability for false APPROVE	Rejected — cost of false APPROVE on infeasible PBIs exceeds review time saved
Static DoR checklist given to Dev BA PIC (no AI)	Simple, no AI dependency	No domain entity context loading, no AC vagueness flagging; manual effort is high and inconsistent across reviewers	Rejected — AI domain lookup provides non-trivial value for cross-service entity detection
Async comment-thread model (AI generates questions posted as ticket comments)	Eliminates scheduling bottleneck; drafter can research before responding	Slower feedback loop; requires external ticket integration	Valid alternative for async teams; prefer if Dev BA PIC availability is chronically a bottleneck

Risk Assessment

Risk	Likelihood	Impact	Mitigation
Automation bias — Dev BA PIC rubber-stamps AI verdict without independent assessment	High	High	Workflow Step 7 shows challenge prompts BEFORE the verdict — Dev BA PIC forms their own view first
Module misdetection — AI loads wrong domain context, produces entity conflict analysis for wrong service	Medium	High	Workflow Step 2 confirms detected module with Dev BA PIC via AskUserQuestion before proceeding
Challenge prompts ignored — Drafter revises PBI superficially to satisfy reviewer without resolving root gaps	Medium	Medium	Decision Record includes drafter-response field; Dev BA PIC re-runs skill on revision, not just reads revised PBI
Suggested answers create adoption pressure — Drafter adopts suggested answer rather than reasoning independently	Medium	Medium	Suggested answers framed as "consider whether X" options, not corrections; language review in challenge prompt templates
3-way BA vote deadlock — UX BA, Designer BA, Dev BA PIC all disagree	Low	Medium	Escalation path per ba-team-decision-model: Engineering Manager for tech uncertainty, PO for business value

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,

• Component patterns: docs/project-reference/frontend-patterns-reference.md
• Styling/BEM guide: docs/project-reference/scss-styling-guide.md
• Design system tokens: docs/project-reference/design-system/README.md

Workflow

1. Locate PBI draft — Find BA drafters' draft PBI in team-artifacts/pbis/ or path provided by user

2. Load domain context — Auto-detect module from PBI content. MANDATORY: Use AskUserQuestion to confirm detected module with Dev BA PIC before loading domain docs. Wrong module = wrong entity context = false APPROVE risk. Then load:

   • docs/project-reference/domain-entities-reference.md (entity definitions)
   • Relevant feature docs from docs/specs/{App}/
   • Existing business rules (BR-{MOD}-XXX) from feature docs

3. Technical Feasibility Analysis:

   • Can described features be built with the project's architecture?
   • Any domain entity conflicts? (cross-reference entity definitions)
   • Any cross-service implications? (message bus events, shared data between services)
   • Estimated complexity alignment (does scope match story points?)

4. AC Quality Analysis:

   • Vagueness detector: flag "should", "might", "TBD", "etc.", "various", "appropriate"
   • Coverage check: happy path + edge case + error case + authorization scenario
   • Missing scenarios: suggest specific additions based on feature type

5. Cross-Cutting Concerns Check:

   • Authorization section present and complete? (roles × CRUD matrix)
   • Seed data requirements addressed? (or explicit "N/A")
   • Data migration implications? (schema changes)
   • Performance considerations? (list/grid/export features)
   • UI Layout section present? If PBI involves UI: must have ## UI Layout per UI wireframe protocol with wireframe + components (with tiers) + states + design tokens. If backend-only: explicit "N/A". Flag missing UI visualization as a gap.

6. Generate Challenge Prompts — Output specific, actionable questions:

   • NOT vague: "needs work" or "improve AC"
   • SPECIFIC: "AC #2 says 'user can filter results' — which filters exactly? Suggest: status, date range, priority"

7. Present Challenge Prompts first, then AI Verdict — Output challenge prompts BEFORE the verdict to prevent automation bias. Dev BA PIC reads and forms their preliminary view, THEN sees: APPROVE / REQUEST_REVISION / ESCALATE_TO_LEAD

   • (feasibility, dependencies, cross-service impact, security): Dev BA PIC has unilateral veto power — no 2/3 vote needed

M1-M6 Compliance Gate (BLOCKING — drives the AI Verdict)

Contract: See .claude/skills/shared/sdd-artifact-contract.md → "AI-SDD Mandates (M1-M6)". This challenge enforces M6: a PBI draft that violates any of M1-M5 MUST produce an AI Verdict of REQUEST_REVISION with a challenge prompt that names the violated mandate ID and cites the exact PBI section + line/AC. An APPROVE over an M1-M5 violation is itself defective. (AI provides the analysis; the human still records the final decision.)

Carriers are EXEMPT from M1/M2 — source identifiers are CORRECT inside [Source: ...], **Evidence**, **IntegrationTest** fields, YAML frontmatter, and ```mermaid ``` blocks. Only challenge leakage in PBI narrative prose (problem statement, AC text, scope, rule descriptions). Banned prose token list: docs/project-reference/spec-principles.md §3.2.

Run these five checks as part of Step 4 (AC Quality) and Step 5 (Cross-Cutting Concerns); any failure becomes a specific challenge prompt and forces REQUEST_REVISION:

• MUST ATTENTION M1 — Tech-agnostic prose. FAIL if problem statement, AC, or rule prose names framework/product, language-native type, or product/design-pattern class name (banned list spec-principles.md §3.2). Challenge: cite section + leaked token + business-term replacement. — why: stack-named prose locks the PBI to one implementation.
• MUST ATTENTION M2 — No source code in prose. FAIL if requirement expressed as class/method/file-path/namespace instead of business operation. Source identifiers belong only in evidence carriers. Challenge: cite section + line.
• MUST ATTENTION M3 — Abstract-IDs-first. FAIL if requirement/rule lacks logical ID (FR-/BR-/OP-), has logical ID but no [Source: namespace/service/id] abstract-anchor evidence, uses physical code coordinates or repository-root paths instead of abstract anchor, or makes anchor its primary citation. Evidence REQUIRED and KEPT, but SECONDARY to logical ID (physical coordinates live only in provenance sidecar).
• MUST ATTENTION M4 — Unambiguous AC. FAIL if any AC uses vague language ("should", "might", "appropriate", "various", "as needed"), two engineers could implement it differently while both claiming conformance, or no observable completion state / named error condition exists. (Extends Step-4 vagueness detector to M4 verdict.)
• MUST ATTENTION M5 — Implementable from artifact alone. FAIL if competent team with ZERO codebase knowledge could not build PBI on different stack from PBI alone (relies on reading source to understand it). Challenge: cite section + missing detail.

If ANY check fails → AI Verdict is REQUEST_REVISION; tag each violated mandate ID with its concrete section/line citation in the Challenge Prompts and the AI Verdict Reason.

Output

## PBI Challenge Review

**PBI:** {PBI filename}
**Reviewer:** Dev BA PIC
**Date:** {date}
**Module:** {detected module code}

### Technical Feasibility

**Status:** FEASIBLE | CONCERNS | INFEASIBLE
{Analysis with evidence — cite domain entities, service boundaries, architecture constraints}

### AC Quality

**Status:** GOOD | NEEDS_REVISION | POOR

| AC # | Issue            | Suggested Fix             |
| ---- | ---------------- | ------------------------- |
| {#}  | {specific issue} | {specific fix suggestion} |

### Cross-Cutting Concerns

| Concern        | Status    | Issue    |
| -------------- | --------- | -------- |
| Authorization  | ✅/❌     | {detail} |
| Seed Data      | ✅/❌/N/A | {detail} |
| Data Migration | ✅/❌/N/A | {detail} |
| Performance    | ✅/❌/N/A | {detail} |

### Challenge Prompts for BA Drafters

1. {Specific actionable question with suggested answer}
2. {Specific actionable question with suggested answer}
3. {Specific actionable question with suggested answer}

### AI Verdict

**{APPROVE | REQUEST_REVISION | ESCALATE_TO_LEAD}**
**Reason:** {evidence-based justification}
**Confidence:** {X%} — {what was verified vs. what needs more investigation}

### Decision Record

**Dev BA PIC Decision:** {filled after human review via AskUserQuestion}
**Vote:** {approve / request-revision / escalate}
**Conditions:** {if any}
**Drafter Response (on revision):** {drafter's response to each challenge prompt — filled when Dev BA PIC re-runs on revised PBI}
**Resolution:** {how each challenge prompt was addressed, deferred, or accepted as known risk}
**Stored at:** `plans/reports/pbi-challenge-{YYMMDD}-{pbi-id}.md` (save output there for audit trail)

Key Rules

• AI provides ANALYSIS, human makes DECISION — Never auto-approve or auto-reject
• Challenge prompts must be specific — Include suggested answers, not just questions
• Domain context required — Always load entity reference + feature docs before analysis
• Technical veto scope — Dev BA PIC CAN veto: architecture feasibility, dependency correctness, cross-service impact, performance, security. CANNOT veto: UI/UX design, visual design, business value (see ba-team-decision-model-protocol.md §2)
• Evidence-based — Every concern raised must cite source (protocol section, entity definition, feature doc)
• Constructive tone — Focus on improving the PBI, not criticizing the drafters

---

Next Steps

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS after completing this skill, you MUST ATTENTION use AskUserQuestion to present these options. Do NOT skip because the task seems "simple" or "obvious" — the user decides:

• "/dor-gate (Recommended)" — If APPROVE: validate DoR before grooming
• "/refine" — If REQUEST_REVISION: BA drafters revise, then re-run /pbi-challenge
• "Escalate to Engineering Manager" — If ESCALATE_TO_LEAD: document concern for technical consultation
• "Skip, continue manually" — user decides

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting.

Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim requires file:line proof or traced evidence with confidence percentage (>80% to act).

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

UI System Context — For ANY task touching .ts, .html, .scss, or .css files:

MUST ATTENTION READ before implementing:

1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms
2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive
3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons

Reference docs/project-config.json for project-specific paths.

BA Team Decision Model — 2/3 majority vote: Dev BA PIC + UX BA + Designer BA per squad. 2 of 3 agree = decision final. 3-way split = escalate to full squad + Tech Leads + Engineering Manager.

Technical Veto: Dev BA PIC can unilaterally veto on: architecture feasibility, dependency correctness, cross-service impact, performance, security. CANNOT veto: UI/UX design, visual design, business value, user research.

Rules: Disagree-and-commit after vote. Grooming override requires >75% non-BA squad vote. Record decisions in PBI Validation Summary (member, role, vote, notes).

Escalation: Tech uncertainty → Engineering Manager. Business value → PO. Design feasibility → UX BA + Designer BA consensus.

Refinement DoR Checklist — ALL 7 criteria MUST ATTENTION pass before grooming:

1. User story template — "As a {role}, I want {goal}, so that {benefit}" format
2. AC testable & unambiguous — GIVEN/WHEN/THEN. No "should/might/TBD/various/appropriate". Min 3 scenarios (happy, edge, error) + 1 auth scenario
3. Wireframes attached — UI features: ## UI Layout with wireframe + components + states + tokens. Backend-only: explicit "N/A"
4. UI design ready — Visual design + component decomposition tree. Backend-only: "N/A"
5. AI pre-review passed — /review-artifact --type=pbi or /pbi-challenge returned PASS or WARN (not FAIL)
6. Story points estimated — Fibonacci 1-21 + complexity (Low/Medium/High). >13 SP → recommend split
7. Dependencies table complete — Dependency, Type (must-before/can-parallel/blocked-by/independent), Status

Failure fixes: Vague AC → specify exact CRUD + roles. Missing auth → add roles × CRUD table. No wireframes → UX BA creates. TBD in AC → replace with decision.

Estimation Framework — Bottom-up first; SP DERIVED; output min-max range when likely ≥3d. Stack-agnostic. Baseline: 3-5yr dev, 6 productive hrs/day. AI estimate assumes Claude Code + project context.

Method:

1. Blast Radius pass (below) — drives code AND test cost
2. Decompose phases → hours/phase → bottom_up_hours = Σ phase_hours
3. likely_days = ceil(bottom_up_hours / 6) × productivity_factor
4. Sum Risk Margin (base + add-ons) → max_days = likely_days × (1 + margin)
5. min_days = likely_days × 0.9
6. Output as range when likely_days ≥3; single point allowed <3 (still record margin)
7. man_days_ai = same range × AI speedup
8. story_points DERIVED from likely_days via SP-Days — NEVER driver. Disagreement >50% → trust bottom-up

Productivity factor: 0.8 strong scaffolding+codegen+AI hooks · 1.0 mature default · 1.2 weak patterns · 1.5 greenfield

Cost Driver Heuristic (apply BEFORE work-type row):

• UI dominates in CRUD/business apps — 1.5-3x backend (states, validation, responsive, a11y, polish)
• Backend dominates ONLY: multi-aggregate invariants, cross-service contracts, schema migrations, heavy query/perf, new event flows

Reuse-vs-Create axis (PRIMARY lever, per layer):

UI tier	Cost
Reuse component on existing screen	0.1-0.3d
Add control/column to existing screen	0.3-0.8d
Compose components into NEW screen	1-2d
NEW screen, custom layout/states/validation	2-4d
NEW shared/common component (themed, tested)	3-6d+

Backend tier	Cost
Reuse query/handler from new place	0.1-0.3d
Small update existing handler/entity	0.3-0.8d
NEW query on existing repo/model

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

Sequential Thinking Protocol — Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.

Trigger when: complex problem decomposition · adaptive plans needing revision · analysis with course correction · unclear/emerging scope · multi-step solutions · hypothesis-driven debugging · cross-cutting trade-off evaluation.

Format (explicit mode — visible thought trail):

1. Thought N/M: [aspect] — one aspect per thought, state assumptions/uncertainty
2. Thought N/M [REVISION of Thought K]: ... — when prior reasoning invalidated; state Original / Why revised / Impact
3. Thought N/M [BRANCH A from Thought K]: ... — explore alternative; converge with decision rationale
4. Thought N/M [HYPOTHESIS]: ... then [VERIFICATION]: ... — test before acting
5. Thought N/N [FINAL] — only when verified, all critical aspects addressed, confidence >80%

Mandatory closers: Confidence % stated · Assumptions listed · Open questions surfaced · Next action concrete.

Stop conditions: confidence <80% on any critical decision → escalate via AskUserQuestion · ≥3 revisions on same thought → re-frame the problem · branch count >3 → split into sub-task.

Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).

Deep-dive: see /sequential-thinking skill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (API design, debugging, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).

• MANDATORY IMPORTANT MUST ATTENTION read frontend-patterns-reference, scss-styling-guide, design-system/README before any UI change.

• MANDATORY MUST ATTENTION estimation: bottom-up phase hours drive man_days_traditional (Σh/6 × productivity_factor); SP DERIVED. UI cost usually dominates — bump SP one bucket if NEW UI surface (page/complex form/dashboard). Frontmatter MUST include story_points, complexity, man_days_traditional, man_days_ai, estimate_scope_included, estimate_scope_excluded, estimate_reasoning (UI vs backend cost driver). Cap SP 3 for additive-on-existing-model+existing-UI unless test scope >1.5d. SP 13 SHOULD split, SP 21 MUST split.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply sequential-thinking — multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see /sequential-thinking skill.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

Closing Reminders

IMPORTANT MUST ATTENTION Goal: Break drafter confirmation bias before grooming — surface every architectural-feasibility, vague-AC, missing-auth, cross-service, and M1-M6 gap as a specific challenge prompt so an INFEASIBLE or under-specified PBI never reaches grooming with a false APPROVE.

Protocols in force (concise digest of the SYNC/shared blocks this skill carries) — MUST ATTENTION each canonical body still governs:

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
• UI System Context: ALWAYS read frontend-patterns, scss-styling, design-system before any UI change.
• BA Team Decision Model: 2/3 BA vote; Dev BA PIC technical veto; escalate 3-way splits.
• Refinement DoR Checklist: All 7 DoR criteria pass before grooming; testable AC, wireframes, estimate.
• Estimation Framework: Bottom-up phase hours drive man-days; SP derived; UI usually dominates.
• Critical Thinking: Traced file:line proof per claim; confidence >80% to act, <60% reject.
• Sequential Thinking: Multi-step Thought N/M with REVISION/BRANCH/HYPOTHESIS; NEVER skip confidence closer.

IMPORTANT MUST ATTENTION AI provides ANALYSIS, human makes DECISION — present Challenge Prompts FIRST, AI Verdict (APPROVE / REQUEST_REVISION / ESCALATE_TO_LEAD) SECOND, then record the human decision via AskUserQuestion. NEVER auto-approve or auto-reject — why: verdict-first triggers automation bias and the Dev BA PIC rubber-stamps without independent assessment. IMPORTANT MUST ATTENTION this is CROSS-PERSON review, not self-review — run only on a BA drafter's draft, NEVER on your own; route self-review to /review-artifact --type=pbi — why: external skepticism breaks the drafter's blind spots that self-review rationalizes away. IMPORTANT MUST ATTENTION M1-M6 Compliance Gate is BLOCKING and drives the verdict — any M1-M5 failure forces REQUEST_REVISION with a challenge prompt naming the violated mandate ID + exact section/line/AC; an APPROVE over an M1-M5 violation is itself defective. Carriers ([Source: ...], **Evidence**, **IntegrationTest**, YAML, mermaid) are EXEMPT — challenge leakage only in PBI narrative prose — why: stack-named or under-specified prose locks the PBI to one implementation and ships ambiguity to grooming. IMPORTANT MUST ATTENTION confirm the auto-detected module via AskUserQuestion BEFORE loading domain docs — wrong module = wrong entity context = false APPROVE — why: entity-conflict analysis built on the wrong service is worse than none. MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting; keep one in_progress; add a final review todo to verify work quality — why: untracked multi-step work loses state on compaction. IMPORTANT MUST ATTENTION every concern raised must cite source (file:line, protocol section, entity definition, feature doc) with confidence — >80% to act, <60% DO NOT recommend; "Insufficient evidence" is valid output. NEVER present a guess as a verdict — why: a false APPROVE on an infeasible PBI costs more than the review. IMPORTANT MUST ATTENTION challenge prompts must be SPECIFIC with suggested answers, not vague ("needs work") — frame suggestions as "consider whether X" options, never corrections — why: vague challenges get superficially satisfied; corrections create adoption pressure that suppresses independent reasoning. IMPORTANT MUST ATTENTION search 3+ existing entity definitions + feature docs in the detected module before flagging a conflict or feasibility gap; verify the PBI's context shares the same constraints before reusing a nearby pattern as evidence — why: closest example ≠ matching preconditions. IMPORTANT MUST ATTENTION Technical-veto scope (architecture feasibility, dependency correctness, cross-service impact, performance, security) is the Dev BA PIC's unilateral call — no 2/3 vote; non-technical decisions (UI/UX, visual design, business value) require 2/3 BA majority per — why: routing a technical veto through a vote dilutes accountability for false APPROVE. after completing, use to present Next Steps ( on APPROVE, on REQUEST_REVISION, escalate on ESCALATE_TO_LEAD, or skip) — the user decides; never skip because the task seems obvious.

Anti-Rationalization:

Evasion	Rebuttal
"Verdict first, prompts are just support"	Verdict-first = automation bias. Prompts FIRST so the human forms their own view.
"I can review my own draft with this"	This is cross-person review. Use /review-artifact --type=pbi for self-review.
"Minor M1-M5 slip, still APPROVE"	Any M1-M5 failure forces REQUEST_REVISION. An APPROVE over a violation is itself defective.
"Module is obvious, skip the confirm"	Wrong module = wrong entity context = false APPROVE. Confirm via AskUserQuestion.
"Concern is clearly right, no citation needed"	Show file:line / section / entity ref + confidence. No proof = no verdict.
"Challenge prompt good enough as a question"	Must be SPECIFIC with a suggested answer, or the drafter satisfies it superficially.

IMPORTANT MUST ATTENTION AI provides ANALYSIS, human makes DECISION — challenge prompts FIRST, verdict SECOND, human records via AskUserQuestion. IMPORTANT MUST ATTENTION M1-M5 violation forces REQUEST_REVISION with mandate ID + section/line citation — an APPROVE over a violation is defective. IMPORTANT MUST ATTENTION cite file:line/section/entity evidence for every concern (confidence >80% to act); never run on your own draft — cross-person review only.