Changes for page POC Requirements (POC1 & POC2)

Last modified by Robert Schaub on 2025/12/24 20:16

From version 2.3

edited by Robert Schaub
on 2025/12/24 20:16

Change comment: Update document after refactoring.

To version 1.1

edited by Robert Schaub
on 2025/12/24 19:45

Change comment: Imported from XAR

Raw
Rendered

Summary

Page properties (2 modified, 0 added, 0 removed)

Details

Page properties

Parent

@@ -1,1 +1,1 @@
--WebHome
++Test.FactHarbor.Specification.POC.WebHome

Content

@@ -1,14 +1,5 @@
  = POC Requirements =
--
--{{info}}
--**POC1 Architecture:** 3-stage AKEL pipeline (Extract → Analyze → Holistic) with Redis caching, credit tracking, and LLM abstraction layer.
--
--See [[POC1 API Specification>>FactHarbor.Specification.POC.API-and-Schemas.WebHome]] for complete technical details.
--{{/info}}
--
--
--
  **Status:** ✅ Approved for Development
  **Version:** 2.0 (Updated after Specification Cross-Check)
  **Goal:** Prove that AI can extract claims and determine verdicts automatically without human intervention
@@ -18,11 +18,9 @@
  === 1.1 What POC Tests ===
  **Core Question:**
--
  > Can AI automatically extract factual claims from articles and evaluate them with reasonable verdicts?
  **What we're proving:**
--
  * AI can identify factual claims from text
  * AI can evaluate those claims and produce verdicts
  * Output is comprehensible and useful
@@ -29,7 +29,6 @@
  * Fully automated approach is viable
  **What we're NOT testing:**
--
  * Scenario generation (deferred to POC2)
  * Evidence display (deferred to POC2)
  * Production scalability
@@ -43,7 +43,6 @@
  Scenarios are a core component of the full FactHarbor system (Claims → Scenarios → Evidence → Verdicts), but are **deliberately excluded from POC1**.
  **Rationale:**
--
  * **POC1 tests:** Can AI extract claims and generate verdicts?
  * **POC2 will add:** Scenario generation and management
  * **Open questions remain:** Should scenarios be separate entities? How are they sequenced with evidence gathering? What's the optimal workflow?
@@ -55,7 +55,6 @@
  **No Risk:**
  Scenarios are additive complexity, not foundational. Deferring them to POC2 allows:
--
  * Faster POC1 validation
  * Learning from POC1 to inform scenario design
  * Iterative approach: fail fast if basic AI doesn't work
@@ -62,10 +62,14 @@
  * Flexibility to adjust scenario architecture based on POC1 insights
  **Full System Workflow (Future):**
--{{code}}Claims → Scenarios → Evidence → Verdicts{{/code}}
++{{code}}
++Claims → Scenarios → Evidence → Verdicts
++{{/code}}
  **POC1 Simplified Workflow:**
--{{code}}Claims → Verdicts (scenarios implicit in reasoning){{/code}}
++{{code}}
++Claims → Verdicts (scenarios implicit in reasoning)
++{{/code}}
  == 2. POC Output Specification ==
@@ -76,7 +76,6 @@
  **Length:** 4-6 sentences
  **Content (Required Elements):**
--
 . **Article's main thesis/claim** - What is the article trying to argue or prove?
 . **Claim count and verdicts** - How many claims analyzed, distribution of verdicts
 . **Central vs. supporting claims** - Which claims are central to the article's argument?
@@ -86,28 +86,30 @@
  **Critical Innovation:**
  POC1 tests whether AI can understand that **article credibility ≠ simple average of claim verdicts**. An article might:
--
  * Make accurate supporting facts but draw unsupported conclusions
  * Have one false central claim that invalidates the whole argument
  * Misframe accurate information to mislead
  **Good Example (Context-Aware):**
--{{code}}This article argues that coffee cures cancer based on its antioxidant
++{{code}}
++This article argues that coffee cures cancer based on its antioxidant
  content. We analyzed 3 factual claims: 2 about coffee's chemical
  properties are well-supported, but the main causal claim is refuted
  by current evidence. The article confuses correlation with causation.
  Overall assessment: MISLEADING - makes an unsupported medical claim
--despite citing some accurate facts.{{/code}}
++despite citing some accurate facts.
++{{/code}}
  **Poor Example (Simple Aggregation - Don't Do This):**
--{{code}}This article makes 3 claims. 2 are well-supported and 1 is refuted.
--Overall assessment: mostly accurate (67% accurate).{{/code}}
++{{code}}
++This article makes 3 claims. 2 are well-supported and 1 is refuted.
++Overall assessment: mostly accurate (67% accurate).
++{{/code}}
  ↑ This misses that the refuted claim IS the article's main point!
  **What POC1 Tests:**
  Can AI identify and assess:
--
  * ✅ The article's main thesis/conclusion?
  * ✅ Which claims are central vs. supporting?
  * ✅ Whether the evidence supports the conclusion?
@@ -116,7 +116,6 @@
  **If AI Cannot Do This:**
  That's valuable to learn in POC1! We'll:
--
  * Note as limitation
  * Fall back to simple aggregation with warning
  * Design explicit article-level analysis for POC2
@@ -127,18 +127,19 @@
  **Format:** Numbered list
  **Quantity:** 3-5 claims
  **Requirements:**
--
  * Factual claims only (not opinions/questions)
  * Clearly stated
  * Automatically extracted by AI
  **Example:**
--{{code}}CLAIMS IDENTIFIED:
++{{code}}
++CLAIMS IDENTIFIED:
  [1] Coffee reduces diabetes risk by 30%
  [2] Coffee improves heart health
  [3] Decaf has same benefits as regular
--[4] Coffee prevents Alzheimer's completely{{/code}}
++[4] Coffee prevents Alzheimer's completely
++{{/code}}
  === 2.3 Component 3: CLAIMS VERDICTS ===
@@ -146,7 +146,6 @@
  **Format:** Per claim structure
  **Required Elements:**
--
  * **Verdict Label:** WELL-SUPPORTED / PARTIALLY SUPPORTED / UNCERTAIN / REFUTED
  * **Confidence Score:** 0-100%
  * **Brief Reasoning:** 1-3 sentences explaining why
@@ -153,7 +153,8 @@
  * **Risk Tier:** A (High) / B (Medium) / C (Low) - for demonstration
  **Example:**
--{{code}}VERDICTS:
++{{code}}
++VERDICTS:
  [1] WELL-SUPPORTED (85%) [Risk: C]
  Multiple studies confirm 25-30% risk reduction with regular consumption.
@@ -165,10 +165,10 @@
  Some benefits overlap, but caffeine-related benefits are reduced in decaf.
  [4] REFUTED (90%) [Risk: B]
--No evidence for complete prevention. Claim is significantly overstated.{{/code}}
++No evidence for complete prevention. Claim is significantly overstated.
++{{/code}}
  **Risk Tier Display:**
--
  * **Tier A (Red):** High Risk - Medical/Legal/Safety/Elections
  * **Tier B (Yellow):** Medium Risk - Policy/Science/Causality
  * **Tier C (Green):** Low Risk - Facts/Definitions/History
@@ -182,11 +182,13 @@
  **Tone:** Neutral (article's position, not FactHarbor's analysis)
  **Example:**
--{{code}}ARTICLE SUMMARY:
++{{code}}
++ARTICLE SUMMARY:
  Health News Today article discusses coffee benefits, citing studies
  on diabetes and Alzheimer's. Author highlights research linking coffee
--to disease prevention. Recommends 2-3 cups daily for optimal health.{{/code}}
++to disease prevention. Recommends 2-3 cups daily for optimal health.
++{{/code}}
  === 2.5 Component 5: USAGE STATISTICS (Cost Tracking) ===
@@ -193,7 +193,6 @@
  **What:** LLM usage metrics for cost optimization and scaling decisions
  **Purpose:**
--
  * Understand cost per analysis
  * Identify optimization opportunities
  * Project costs at scale
@@ -200,7 +200,8 @@
  * Inform architecture decisions
  **Display Format:**
--{{code}}USAGE STATISTICS:
++{{code}}
++USAGE STATISTICS:
  • Article: 2,450 words (12,300 characters)
  • Input tokens: 15,234
  • Output tokens: 892
@@ -208,18 +208,17 @@
  • Estimated cost: $0.24 USD
  • Response time: 8.3 seconds
  • Cost per claim: $0.048
--• Model: claude-sonnet-4-20250514{{/code}}
++• Model: claude-sonnet-4-20250514
++{{/code}}
  **Why This Matters:**
  At scale, LLM costs are critical:
--
  * 10,000 articles/month ≈ $200-500/month
  * 100,000 articles/month ≈ $2,000-5,000/month
  * Cost optimization can reduce expenses 30-50%
  **What POC1 Learns:**
--
  * How cost scales with article length
  * Prompt optimization opportunities (caching, compression)
  * Output verbosity tradeoffs
@@ -227,7 +227,6 @@
  * Article length limits (if needed)
  **Implementation:**
--
  * Claude API already returns usage data
  * No extra API calls needed
  * Display to user + log for aggregate analysis
@@ -237,8 +237,7 @@
  === 2.6 Total Output Size ===
--**Combined:** 220-350 words
--
++**Combined:** ~220-350 words
  * Analysis Summary (Context-Aware): 60-90 words (4-6 sentences)
  * Claims Identification: 30-50 words
  * Claims Verdicts: 100-150 words
@@ -253,7 +253,6 @@
  The following are **explicitly excluded** from POC:
  **Content Features:**
--
  * ❌ Scenarios (deferred to POC2)
  * ❌ Evidence display (supporting/opposing lists)
  * ❌ Source links (clickable references)
@@ -263,7 +263,6 @@
  * ❌ Risk assessment (shown but not workflow-integrated)
  **Platform Features:**
--
  * ❌ User accounts / authentication
  * ❌ Saved history
  * ❌ Search functionality
@@ -273,7 +273,6 @@
  * ❌ Social sharing
  **Technical Features:**
--
  * ❌ Browser extensions
  * ❌ Mobile apps
  * ❌ API endpoints
@@ -281,7 +281,6 @@
  * ❌ Export features (PDF, CSV)
  **Quality Features:**
--
  * ❌ Accessibility (WCAG compliance)
  * ❌ Multilingual support
  * ❌ Mobile optimization
@@ -288,7 +288,6 @@
  * ❌ Media verification (images/videos)
  **Production Features:**
--
  * ❌ Security hardening
  * ❌ Privacy compliance (GDPR)
  * ❌ Terms of service
@@ -302,13 +302,17 @@
  === 4.1 Architecture Comparison ===
  **POC Architecture (Simplified):**
--{{code}}User Input → Single AKEL Call → Output Display
-- (all processing){{/code}}
++{{code}}
++User Input → Single AKEL Call → Output Display
++ (all processing)
++{{/code}}
  **Full System Architecture:**
--{{code}}User Input → Claim Extractor → Claim Classifier → Scenario Generator
++{{code}}
++User Input → Claim Extractor → Claim Classifier → Scenario Generator
  → Evidence Summarizer → Contradiction Detector → Verdict Generator
--→ Quality Gates → Publication → Output Display{{/code}}
++→ Quality Gates → Publication → Output Display
++{{/code}}
  **Key Differences:**
@@ -324,14 +324,12 @@
  === 4.2 Workflow Comparison ===
  **POC1 Workflow:**
--
 . User submits text/URL
 . Single AKEL call (all processing in one prompt)
 . Display results
--**Total: 3 steps, 10-18 seconds**
++**Total: 3 steps, ~10-18 seconds**
  **Full System Workflow:**
--
 . **Claim Submission** (extraction, normalization, clustering)
 . **Scenario Building** (definitions, assumptions, boundaries)
 . **Evidence Handling** (retrieval, assessment, linking)
@@ -338,7 +338,7 @@
 . **Verdict Creation** (synthesis, reasoning, approval)
 . **Public Presentation** (summaries, landscapes, deep dives)
 . **Time Evolution** (versioning, re-evaluation triggers)
--**Total: 6 phases with quality gates, 10-30 seconds**
++**Total: 6 phases with quality gates, ~10-30 seconds**
  === 4.3 Why POC is Simplified ===
@@ -361,7 +361,6 @@
  === 4.4 Gap Between POC1 and POC2/Beta ===
  **What needs to be built for POC2:**
--
  * Scenario generation component
  * Evidence Model structure (full)
  * Scenario-evidence linking
@@ -369,7 +369,6 @@
  * Truth landscape visualization
  **What needs to be built for Beta:**
--
  * Multi-component AKEL pipeline
  * Quality gate infrastructure
  * Review workflow system
@@ -386,7 +386,6 @@
  **Mode:** Mode 2 (AI-Generated, No Prior Human Review)
  Per FactHarbor Specification Section 11 "POC v1 Behavior":
--
  * Produces public AI-generated output
  * No human approval gate
  * Clear AI-Generated labeling
@@ -396,7 +396,8 @@
  === 5.2 User-Facing Labels ===
  **Primary Label (top of analysis):**
--{{code}}╔════════════════════════════════════════════════════════════╗
++{{code}}
++╔════════════════════════════════════════════════════════════╗
  ║ [AI-GENERATED - POC/DEMO] ║
  ║ ║
  ║ This analysis was produced entirely by AI and has not ║
@@ -406,10 +406,10 @@
  ║ Review Status: Not Reviewed (Proof-of-Concept) ║
  ║ Quality Gates: 4/4 Passed (Simplified) ║
  ║ Last Updated: [timestamp] ║
--╚════════════════════════════════════════════════════════════╝{{/code}}
++╚════════════════════════════════════════════════════════════╝
++{{/code}}
  **Per-Claim Risk Labels:**
--
  * **[Risk: A]** 🔴 High Risk (Medical/Legal/Safety)
  * **[Risk: B]** 🟡 Medium Risk (Policy/Science)
  * **[Risk: C]** 🟢 Low Risk (Facts/Definitions)
@@ -417,7 +417,6 @@
  === 5.3 Display Requirements ===
  **Must Show:**
--
  * AI-Generated status (prominent)
  * POC/Demo disclaimer
  * Risk tier per claim
@@ -426,7 +426,6 @@
  * Timestamp
  **Must NOT Claim:**
--
  * Human review
  * Production quality
  * Medical/legal advice
@@ -450,7 +450,6 @@
  Per FactHarbor Specification Section 6, all AI-generated content must pass quality gates before publication. POC implements **simplified versions** of the 4 mandatory gates.
  **Full System Has 4 Gates:**
--
 . Source Quality
 . Contradiction Search (MANDATORY)
 . Uncertainty Quantification
@@ -457,7 +457,6 @@
 . Structural Integrity
  **POC Implements Simplified Versions:**
--
  * Focus on demonstrating concept
  * Basic implementations sufficient
  * Failures displayed to user (not blocking)
@@ -466,7 +466,6 @@
  === 6.2 Gate 1: Source Quality (Basic) ===
  **Full System Requirements:**
--
  * Primary sources identified and accessible
  * Source reliability scored against whitelist
  * Citation completeness verified
@@ -474,7 +474,6 @@
  * Author credentials validated
  **POC Implementation:**
--
  * ✅ At least 2 sources found
  * ✅ Sources accessible (URLs valid)
  * ❌ No whitelist checking
@@ -488,7 +488,6 @@
  === 6.3 Gate 2: Contradiction Search (Basic) ===
  **Full System Requirements:**
--
  * Counter-evidence actively searched
  * Reservations and limitations identified
  * Alternative interpretations explored
@@ -497,7 +497,6 @@
  * Academic literature (supporting AND opposing)
  **POC Implementation:**
--
  * ✅ Basic search for counter-evidence
  * ✅ Identify obvious contradictions
  * ❌ No comprehensive academic search
@@ -512,7 +512,6 @@
  === 6.4 Gate 3: Uncertainty Quantification (Basic) ===
  **Full System Requirements:**
--
  * Confidence scores calculated for all claims/verdicts
  * Limitations explicitly stated
  * Data gaps identified and disclosed
@@ -520,7 +520,6 @@
  * Alternative scenarios considered
  **POC Implementation:**
--
  * ✅ Confidence scores (0-100%)
  * ✅ Basic uncertainty acknowledgment
  * ❌ No detailed limitation disclosure
@@ -534,7 +534,6 @@
  === 6.5 Gate 4: Structural Integrity (Basic) ===
  **Full System Requirements:**
--
  * No hallucinations detected (fact-checking against sources)
  * Logic chain valid and traceable
  * References accessible and verifiable
@@ -542,7 +542,6 @@
  * Premises clearly stated
  **POC Implementation:**
--
  * ✅ Basic coherence check
  * ✅ References accessible
  * ❌ No comprehensive hallucination detection
@@ -556,20 +556,24 @@
  === 6.6 Quality Gate Display ===
  **POC shows simplified status:**
--{{code}}Quality Gates: 4/4 Passed (Simplified)
++{{code}}
++Quality Gates: 4/4 Passed (Simplified)
  ✓ Source Quality: 3 sources found
  ✓ Contradiction Search: Basic search completed
  ✓ Uncertainty: Confidence scores assigned
--✓ Structural Integrity: Output coherent{{/code}}
++✓ Structural Integrity: Output coherent
++{{/code}}
  **If any gate fails:**
--{{code}}Quality Gates: 3/4 Passed (Simplified)
++{{code}}
++Quality Gates: 3/4 Passed (Simplified)
  ✓ Source Quality: 3 sources found
  ✗ Contradiction Search: Search failed - limited evidence
  ✓ Uncertainty: Confidence scores assigned
  ✓ Structural Integrity: Output coherent
--Note: This analysis has limited evidence. Use with caution.{{/code}}
++Note: This analysis has limited evidence. Use with caution.
++{{/code}}
  === 6.7 Simplified vs. Full System ===
@@ -586,7 +586,6 @@
  === 7.1 POC AKEL (Simplified) ===
  **Implementation:**
--
  * Single Claude API call (Sonnet 4.5)
  * One comprehensive prompt
  * All processing in single request
@@ -594,7 +594,8 @@
  * No orchestration layer
  **Prompt Structure:**
--{{code}}Task: Analyze this article and provide:
++{{code}}
++Task: Analyze this article and provide:
 . Extract 3-5 factual claims
 . For each claim:
@@ -606,7 +606,8 @@
 . Generate article summary (3-5 sentences)
 . Run basic quality checks
--Return as structured JSON.{{/code}}
++Return as structured JSON.
++{{/code}}
  **Processing Time:** 10-18 seconds (estimate)
@@ -613,7 +613,8 @@
  === 7.2 Full System AKEL (Production) ===
  **Architecture:**
--{{code}}AKEL Orchestrator
++{{code}}
++AKEL Orchestrator
  ├── Claim Extractor
  ├── Claim Classifier (with risk tier assignment)
  ├── Scenario Generator
@@ -621,10 +621,10 @@
  ├── Contradiction Detector
  ├── Quality Gate Validator
  ├── Audit Sampling Scheduler
--└── Federation Sync Adapter (Release 1.0+){{/code}}
++└── Federation Sync Adapter (Release 1.0+)
++{{/code}}
  **Processing:**
--
  * Parallel processing where possible
  * Separate component calls
  * Quality gates between phases
@@ -636,7 +636,6 @@
  === 7.3 Why POC Uses Single Call ===
  **Advantages:**
--
  * ✅ Simpler to implement
  * ✅ Faster POC development
  * ✅ Easier to debug
@@ -644,7 +644,6 @@
  * ✅ Good enough for concept validation
  **Limitations:**
--
  * ❌ No component reusability
  * ❌ No parallel processing
  * ❌ All-or-nothing (can't partially succeed)
@@ -671,7 +671,6 @@
  **Requirement:** User can submit article for analysis
  **Functionality:**
--
  * Text input field (paste article text, up to 5000 characters)
  * URL input field (paste article URL)
  * "Analyze" button to trigger processing
@@ -678,7 +678,6 @@
  * Loading indicator during analysis
  **Excluded:**
--
  * No user authentication
  * No claim history
  * No search functionality
@@ -685,7 +685,6 @@
  * No saved templates
  **Acceptance Criteria:**
--
  * User can paste text from article
  * User can paste URL of article
  * System accepts input and triggers analysis
@@ -695,7 +695,6 @@
  **Requirement:** AI automatically extracts 3-5 factual claims
  **Functionality:**
--
  * AI reads article text
  * AI identifies factual claims (not opinions/questions)
  * AI extracts 3-5 most important claims
@@ -702,7 +702,6 @@
  * System displays numbered list
  **Critical:** NO MANUAL EDITING ALLOWED
--
  * AI selects which claims to extract
  * AI identifies factual vs. non-factual
  * System processes claims as extracted
@@ -709,13 +709,11 @@
  * No human curation or correction
  **Error Handling:**
--
  * If extraction fails: Display error message
  * User can retry with different input
  * No manual intervention to fix extraction
  **Acceptance Criteria:**
--
  * AI extracts 3-5 claims automatically
  * Claims are factual (not opinions)
  * Claims are clearly stated
@@ -726,17 +726,15 @@
  **Requirement:** AI automatically generates verdict for each claim
  **Functionality:**
--
  * For each claim, AI:
--* Evaluates claim based on available evidence/knowledge
--* Determines verdict: WELL-SUPPORTED / PARTIALLY SUPPORTED / UNCERTAIN / REFUTED
--* Assigns confidence score (0-100%)
--* Assigns risk tier (A/B/C)
--* Writes brief reasoning (1-3 sentences)
++ * Evaluates claim based on available evidence/knowledge
++ * Determines verdict: WELL-SUPPORTED / PARTIALLY SUPPORTED / UNCERTAIN / REFUTED
++ * Assigns confidence score (0-100%)
++ * Assigns risk tier (A/B/C)
++ * Writes brief reasoning (1-3 sentences)
  * System displays verdict for each claim
  **Critical:** NO MANUAL EDITING ALLOWED
--
  * AI computes verdicts based on evidence
  * AI generates confidence scores
  * AI writes reasoning
@@ -743,13 +743,11 @@
  * No human review or adjustment
  **Error Handling:**
--
  * If verdict generation fails: Display error message
  * User can retry
  * No manual intervention to adjust verdicts
  **Acceptance Criteria:**
--
  * Each claim has a verdict
  * Confidence score is displayed (0-100%)
  * Risk tier is displayed (A/B/C)
@@ -762,17 +762,15 @@
  **Requirement:** AI generates brief summary of analysis
  **Functionality:**
--
  * AI summarizes findings in 3-5 sentences:
--* How many claims found
--* Distribution of verdicts
--* Overall assessment
++ * How many claims found
++ * Distribution of verdicts
++ * Overall assessment
  * System displays at top of results
  **Critical:** NO MANUAL EDITING ALLOWED
  **Acceptance Criteria:**
--
  * Summary is coherent
  * Accurately reflects analysis
  * 3-5 sentences
@@ -783,7 +783,6 @@
  **Requirement:** AI generates brief summary of original article
  **Functionality:**
--
  * AI summarizes article content (not FactHarbor's analysis)
  * 3-5 sentences
  * System displays
@@ -793,7 +793,6 @@
  **Critical:** NO MANUAL EDITING ALLOWED
  **Acceptance Criteria:**
--
  * Summary is neutral (article's position)
  * Accurately reflects article content
  * 3-5 sentences
@@ -804,7 +804,6 @@
  **Requirement:** Clear labeling of AI-generated content
  **Functionality:**
--
  * Display Mode 2 publication label
  * Show POC/Demo disclaimer
  * Display risk tiers per claim
@@ -812,7 +812,6 @@
  * Display timestamp
  **Acceptance Criteria:**
--
  * Label is prominent and clear
  * User understands this is AI-generated POC output
  * Risk tiers are color-coded
@@ -823,7 +823,6 @@
  **Requirement:** Execute simplified quality gates
  **Functionality:**
--
  * Check source quality (basic)
  * Attempt contradiction search (basic)
  * Calculate confidence scores
@@ -831,7 +831,6 @@
  * Display gate results
  **Acceptance Criteria:**
--
  * All 4 gates attempted
  * Pass/fail status displayed
  * Failures explained to user
@@ -846,7 +846,6 @@
  **Critical Rule:** NO MANUAL EDITING AT ANY STAGE
  **What this means:**
--
  * Claims: AI selects (no human curation)
  * Scenarios: N/A (deferred to POC2)
  * Evidence: AI evaluates (no human selection)
@@ -854,12 +854,13 @@
  * Summaries: AI writes (no human editing)
  **Pipeline:**
--{{code}}User Input → AKEL Processing → Output Display
++{{code}}
++User Input → AKEL Processing → Output Display
   ↓
-- ZERO human editing{{/code}}
++ ZERO human editing
++{{/code}}
  **If AI output is poor:**
--
  * ❌ Do NOT manually fix it
  * ✅ Document the failure
  * ✅ Improve prompts and retry
@@ -866,7 +866,6 @@
  * ✅ Accept that POC might fail
  **Why this matters:**
--
  * Tests whether AI can do this without humans
  * Validates scalability (humans can't review every analysis)
  * Honest test of technical feasibility
@@ -876,19 +876,16 @@
  **Requirement:** Analysis completes in reasonable time
  **Acceptable Performance:**
--
  * Processing time: 1-5 minutes (acceptable for POC)
  * Display loading indicator to user
  * Show progress if possible ("Extracting claims...", "Generating verdicts...")
  **Not Required:**
--
  * Production-level speed (< 30 seconds)
  * Optimization for scale
  * Caching
  **Acceptance Criteria:**
--
  * Analysis completes within 5 minutes
  * User sees loading indicator
  * No timeout errors
@@ -898,19 +898,16 @@
  **Requirement:** System works for manual testing sessions
  **Acceptable:**
--
  * Occasional errors (< 20% failure rate)
  * Manual restart if needed
  * Display error messages clearly
  **Not Required:**
--
  * 99.9% uptime
  * Automatic error recovery
  * Production monitoring
  **Acceptance Criteria:**
--
  * System works for test demonstrations
  * Errors are handled gracefully
  * User receives clear error messages
@@ -920,7 +920,6 @@
  **Requirement:** Runs on simple infrastructure
  **Acceptable:**
--
  * Single machine or simple cloud setup
  * No distributed architecture
  * No load balancing
@@ -928,7 +928,6 @@
  * Local development environment viable
  **Not Required:**
--
  * Production infrastructure
  * Multi-region deployment
  * Auto-scaling
@@ -939,7 +939,6 @@
  **Requirement:** Track and display LLM usage metrics to inform optimization decisions
  **Must Track:**
--
  * Input tokens (article + prompt)
  * Output tokens (generated analysis)
  * Total tokens
@@ -948,19 +948,16 @@
  * Article length (words/characters)
  **Must Display:**
--
  * Usage statistics in UI (Component 5)
  * Cost per analysis
  * Cost per claim extracted
  **Must Log:**
--
  * Aggregate metrics for analysis
  * Cost distribution by article length
  * Token efficiency trends
  **Purpose:**
--
  * Understand unit economics
  * Identify optimization opportunities
  * Project costs at scale
@@ -967,7 +967,6 @@
  * Inform architecture decisions (caching, model selection, etc.)
  **Acceptance Criteria:**
--
  * ✅ Usage data displayed after each analysis
  * ✅ Metrics logged for aggregate analysis
  * ✅ Cost calculated accurately (Claude API pricing)
@@ -975,7 +975,6 @@
  * ✅ POC1 report includes cost analysis section
  **Success Target:**
--
  * Average cost per analysis < $0.05 USD
  * Cost scaling behavior understood (linear/exponential)
  * 2+ optimization opportunities identified
@@ -987,13 +987,11 @@
  === 10.1 System Components ===
  **Frontend:**
--
  * Simple HTML form (text input + URL input + button)
  * Loading indicator
  * Results display page (single page, no tabs/navigation)
  **Backend:**
--
  * Single API endpoint
  * Calls Claude API (Sonnet 4.5 or latest)
  * Parses response
@@ -1000,12 +1000,10 @@
  * Returns JSON to frontend
  **Data Storage:**
--
  * None required (stateless POC)
  * Optional: Simple file storage or SQLite for demo examples
  **External Services:**
--
  * Claude API (Anthropic) - required
  * Optional: URL fetch service for article text extraction
@@ -1038,7 +1038,8 @@
  === 10.3 AI Prompt Strategy ===
  **Single Comprehensive Prompt:**
--{{code}}Task: Analyze this article and provide:
++{{code}}
++Task: Analyze this article and provide:
 . Identify the article's main thesis/conclusion
   - What is the article trying to argue or prove?
@@ -1074,7 +1074,8 @@
 . Write article summary (3-5 sentences: neutral summary of article content)
--Return as structured JSON with quality gate results.{{/code}}
++Return as structured JSON with quality gate results.
++{{/code}}
  **One prompt generates everything.**
@@ -1085,30 +1085,25 @@
  === 10.4 Technology Stack Suggestions ===
  **Frontend:**
--
  * HTML + CSS + JavaScript (minimal framework)
  * OR: Next.js (if team prefers)
  * Hosted: Local machine OR Vercel/Netlify free tier
  **Backend:**
--
  * Python Flask/FastAPI (simple REST API)
  * OR: Next.js API routes (if using Next.js)
  * Hosted: Local machine OR Railway/Render free tier
  **AKEL Integration:**
--
  * Claude API via Anthropic SDK
  * Model: Claude Sonnet 4.5 or latest available
  **Database:**
--
  * None (stateless acceptable)
  * OR: SQLite if want to store demo examples
  * OR: JSON files on disk
  **Deployment:**
--
  * Local development environment sufficient for POC
  * Optional: Deploy to cloud for remote demos
@@ -1117,7 +1117,6 @@
  === 11.1 Minimum Success (POC Passes) ===
  **Required for GO decision:**
--
  * ✅ AI extracts 3-5 factual claims automatically
  * ✅ AI provides verdict for each claim automatically
  * ✅ Verdicts are reasonable (≥70% make logical sense)
@@ -1131,7 +1131,6 @@
  * ✅ **Optimization opportunities identified** (≥2 potential improvements documented)
  **Quality Definition:**
--
  * "Reasonable verdict" = Defensible given general knowledge
  * "Coherent summary" = Logically structured, grammatically correct
  * "Comprehensible" = Reviewers understand what analysis means
@@ -1139,7 +1139,6 @@
  === 11.2 POC Fails If ===
  **Automatic NO-GO if any of these:**
--
  * ❌ Claim extraction poor (< 60% accuracy - extracts non-claims or misses obvious ones)
  * ❌ Verdicts nonsensical (< 60% reasonable - contradictory or random)
  * ❌ Output incomprehensible (reviewers can't understand analysis)
@@ -1151,15 +1151,14 @@
  **POC quality expectations:**
  |=Component|=Quality Threshold|=Definition
--|Claim Extraction|(% class="success" %)≥70% accuracy |Identifies obvious factual claims, may miss some edge cases
--|Verdict Logic|(% class="success" %)≥70% defensible |Verdicts are logical given reasoning provided
--|Reasoning Clarity|(% class="success" %)≥70% clear |1-3 sentences are understandable and relevant
--|Overall Analysis|(% class="success" %)≥70% useful |Output helps user understand article claims
++|Claim Extraction|(% class="success" %)≥70% accuracy(%%) |Identifies obvious factual claims, may miss some edge cases
++|Verdict Logic|(% class="success" %)≥70% defensible(%%) |Verdicts are logical given reasoning provided
++|Reasoning Clarity|(% class="success" %)≥70% clear(%%) |1-3 sentences are understandable and relevant
++|Overall Analysis|(% class="success" %)≥70% useful(%%) |Output helps user understand article claims
  **Analogy:** "B student" quality (70-80%), not "A+" perfection yet
  **Not expecting:**
--
  * 100% accuracy
  * Perfect claim coverage
  * Comprehensive evidence gathering
@@ -1167,7 +1167,6 @@
  * Production polish
  **Expecting:**
--
  * Reasonable claim extraction
  * Defensible verdicts
  * Understandable reasoning
@@ -1180,7 +1180,6 @@
  **Input:** "Coffee reduces the risk of type 2 diabetes by 30%"
  **Expected Output:**
--
  * Extract claim correctly
  * Provide verdict: WELL-SUPPORTED or PARTIALLY SUPPORTED
  * Confidence: 70-90%
@@ -1194,7 +1194,6 @@
  **Input:** News article URL with multiple claims about politics/health/science
  **Expected Output:**
--
  * Extract 3-5 key claims
  * Verdict for each (may vary: some supported, some uncertain, some refuted)
  * Coherent analysis summary
@@ -1208,7 +1208,6 @@
  **Input:** Article on contested political or scientific topic
  **Expected Output:**
--
  * Balanced analysis
  * Acknowledges uncertainty where appropriate
  * Doesn't overstate confidence
@@ -1221,7 +1221,6 @@
  **Input:** Article with obviously false claim (e.g., "The Earth is flat")
  **Expected Output:**
--
  * Extract claim
  * Verdict: REFUTED
  * High confidence (> 90%)
@@ -1235,7 +1235,6 @@
  **Input:** Article with claim where evidence is genuinely mixed
  **Expected Output:**
--
  * Extract claim
  * Verdict: UNCERTAIN
  * Moderate confidence (40-60%)
@@ -1248,7 +1248,6 @@
  **Input:** Article making medical claims
  **Expected Output:**
--
  * Extract claim
  * Verdict: [appropriate based on evidence]
  * Risk tier: A (High - medical)
@@ -1266,7 +1266,6 @@
  **Option A: GO (Proceed to POC2)**
  **Conditions:**
--
  * AI quality ≥70% without manual editing
  * Basic claim → verdict pipeline validated
  * Internal + advisor feedback positive
@@ -1275,7 +1275,6 @@
  * Clear path to improving AI quality to ≥90%
  **Next Steps:**
--
  * Plan POC2 development (add scenarios)
  * Design scenario architecture
  * Expand to Evidence Model structure
@@ -1284,7 +1284,6 @@
  **Option B: NO-GO (Pivot or Stop)**
  **Conditions:**
--
  * AI quality < 60%
  * Requires manual editing for most analyses (> 50%)
  * Feedback indicates fundamental flaws
@@ -1292,7 +1292,6 @@
  * No clear path to improvement
  **Next Steps:**
--
  * **Pivot:** Change to hybrid human-AI approach (accept manual review required)
  * **Stop:** Conclude approach not viable, revisit later
@@ -1299,7 +1299,6 @@
  **Option C: ITERATE (Improve POC)**
  **Conditions:**
--
  * Concept has merit but execution needs work
  * Specific improvements identified
  * Addressable with better prompts/approach
@@ -1306,7 +1306,6 @@
  * AI quality between 60-70%
  **Next Steps:**
--
  * Improve AI prompts
  * Test different approaches
  * Re-run POC with improvements
@@ -1328,7 +1328,6 @@
  **Impact:** POC fails
  **Mitigation:**
--
  * Extensive prompt engineering and testing
  * Use best available AI models (Sonnet 4.5)
  * Test with diverse article types
@@ -1342,7 +1342,6 @@
  **Impact:** Works sometimes, fails other times
  **Mitigation:**
--
  * Test with 10+ diverse articles
  * Measure success rate honestly
  * Improve prompts to increase consistency
@@ -1355,7 +1355,6 @@
  **Impact:** Users can't understand analysis
  **Mitigation:**
--
  * Create clear explainer document
  * Iterate on output format
  * Test with non-technical reviewers
@@ -1369,7 +1369,6 @@
  **Impact:** System slow or expensive
  **Mitigation:**
--
  * Monitor API usage
  * Implement retry logic
  * Estimate costs before scaling
@@ -1382,7 +1382,6 @@
  **Impact:** POC becomes too complex
  **Mitigation:**
--
  * Strict scope discipline
  * Say NO to feature additions
  * Keep focus on core question
@@ -1393,15 +1393,12 @@
  === 15.1 Core Principles ===
--*
--**
--**1. Build Less, Learn More
++**1. Build Less, Learn More**
  * Minimum features to test hypothesis
  * Don't build unvalidated features
  * Focus on core question only
  **2. Fail Fast**
--
  * Quick test of hardest part (AI capability)
  * Accept that POC might fail
  * Better to discover issues early
@@ -1408,19 +1408,16 @@
  * Honest assessment over optimistic hope
  **3. Test First, Build Second**
--
  * Validate AI can do this before building platform
  * Don't assume it will work
  * Let results guide decisions
  **4. Automation First**
--
  * No manual editing allowed
  * Tests scalability, not just feasibility
  * Proves approach can work at scale
  **5. Honest Assessment**
--
  * Don't cherry-pick examples
  * Don't manually fix bad outputs
  * Document failures openly
@@ -1441,12 +1441,9 @@
  ❌ Perfectly accurate analysis
  ❌ Polished user experience
--== 16. Success ==
++== 16. Success = Clear Path Forward ==
-- Clear Path Forward ==
--
  **If POC succeeds (≥70% AI quality):**
--
  * ✅ Approach validated
  * ✅ Proceed to POC2 (add scenarios)
  * ✅ Design full Evidence Model structure
@@ -1454,7 +1454,6 @@
  * ✅ Focus on improving AI quality from 70% → 90%
  **If POC fails (< 60% AI quality):**
--
  * ✅ Learn what doesn't work
  * ✅ Pivot to different approach
  * ✅ OR wait for better AI technology
@@ -1481,16 +1481,16 @@
  **POC1 Implementation:**
  * **Primary Provider:** Anthropic Claude API
--* Stage 1: Claude Haiku 4
--* Stage 2: Claude Sonnet 3.5 (cached)
--* Stage 3: Claude Sonnet 3.5
++ * Stage 1: Claude Haiku 4
++ * Stage 2: Claude Sonnet 3.5 (cached)
++ * Stage 3: Claude Sonnet 3.5
  * **Provider Interface:** Abstract LLMProvider interface implemented
  * **Configuration:** Environment variables for provider selection
--* {{code}}LLM_PRIMARY_PROVIDER=anthropic{{/code}}
--* {{code}}LLM_STAGE1_MODEL=claude-haiku-4{{/code}}
--* {{code}}LLM_STAGE2_MODEL=claude-sonnet-3-5{{/code}}
++ * {{code}}LLM_PRIMARY_PROVIDER=anthropic{{/code}}
++ * {{code}}LLM_STAGE1_MODEL=claude-haiku-4{{/code}}
++ * {{code}}LLM_STAGE2_MODEL=claude-sonnet-3-5{{/code}}
  * **Failover:** Basic error handling with cache fallback for Stage 2
@@ -1510,10 +1510,9 @@
  * Cost tracking includes provider name in logs
  * Stage 2 falls back to cache on provider failure
--**Implementation:** See [[POC1 API & Schemas Specification>>Test.FactHarbor V0\.9\.105.Specification.POC.API-and-Schemas.WebHome]] Section 6
++**Implementation:** See [[POC1 API & Schemas Specification>>Test.FactHarbor.Specification.POC.API-and-Schemas.WebHome]] Section 6
  **Dependencies:**
--
  * NFR-14 (Main Requirements)
  * Design Decision 9
  * Architecture Section 2.2
@@ -1521,3 +1521,5 @@
  **Priority:** HIGH (P1)
  **Rationale:** Even though POC1 uses single provider, abstraction must be in place from start to avoid costly refactoring later.
++
++

Changes for page POC Requirements (POC1 & POC2)

Summary

Details

Applications

Navigation

Need help?