Wiki source code of POC Requirements (POC1 & POC2)
Version 2.1 by Robert Schaub on 2025/12/23 17:44
Hide last authors
| author | version | line-number | content |
|---|---|---|---|
 |
1.1 | 1 | = POC Requirements = |
| 2 | |||
| 3 | **Status:** ✅ Approved for Development | ||
| |
2.1 | 4 | **Version:** 3.0 (Aligned with Main Requirements) |
| |
1.1 | 5 | **Goal:** Prove that AI can extract claims and determine verdicts automatically without human intervention |
| 6 | |||
| |
2.1 | 7 | {{info}} |
| 8 | **Core Philosophy:** POC validates the [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]] through simplified implementation. All POC features map to formal FR/NFR requirements. | ||
| 9 | {{/info}} | ||
| |
1.1 | 10 | |
| |
2.1 | 11 | |
| |
1.1 | 12 | == 1. POC Overview == |
| 13 | |||
| 14 | === 1.1 What POC Tests === | ||
| 15 | |||
| 16 | **Core Question:** | ||
| 17 | > Can AI automatically extract factual claims from articles and evaluate them with reasonable verdicts? | ||
| 18 | |||
| 19 | **What we're proving:** | ||
| 20 | * AI can identify factual claims from text | ||
| |
2.1 | 21 | * AI can evaluate those claims with structured evidence |
| 22 | * Quality gates can filter unreliable outputs | ||
| 23 | * The core workflow is technically feasible | ||
| |
1.1 | 24 | |
| |
2.1 | 25 | **What we're NOT proving:** |
| 26 | * Production-ready reliability (that's POC2) | ||
| 27 | * User-facing features (that's Beta 0) | ||
| 28 | * Full IFCN compliance (that's V1.0) | ||
| |
1.1 | 29 | |
| |
2.1 | 30 | === 1.2 Requirements Mapping === |
| |
1.1 | 31 | |
| |
2.1 | 32 | POC1 implements a **subset** of the full system requirements defined in [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]]. |
| |
1.1 | 33 | |
| |
2.1 | 34 | **Scope Summary:** |
| 35 | * **In Scope:** 8 requirements (7 FRs + 1 NFR) | ||
| 36 | * **Partial:** 3 NFRs (simplified versions) | ||
| 37 | * **Out of Scope:** 19 requirements (deferred to later phases) | ||
| |
1.1 | 38 | |
| 39 | |||
| |
2.1 | 40 | == 2. POC1 Scope == |
| |
1.1 | 41 | |
| |
2.1 | 42 | {{success}} |
| 43 | **Authoritative Source for Phase Mapping:** [[Requirements Roadmap Matrix>>Test.FactHarbor.Roadmap.Requirements-Roadmap-Matrix.WebHome]] | ||
| |
1.1 | 44 | |
| |
2.1 | 45 | The Roadmap Matrix is the single source of truth for which requirements are implemented in which phases. This page provides POC1-specific implementation details only. |
| 46 | {{/success}} | ||
| |
1.1 | 47 | |
| |
2.1 | 48 | **POC1 implements these formal requirements:** |
| |
1.1 | 49 | |
| |
2.1 | 50 | |= Formal Req |= Implementation in POC1 |= Notes |
| 51 | | **FR4** | Analysis Summary | Basic format; quality metadata deferred to POC2 | ||
| 52 | | **FR7** | Automated Verdicts | Full implementation with quality gates (NFR11) | ||
| 53 | | **NFR11** | Quality Assurance Framework | 4 quality gates implemented | ||
| |
1.1 | 54 | |
| |
2.1 | 55 | **POC1 also implements these workflow components** (detailed as FR1-FR6 in implementation sections below) |
| |
1.1 | 56 | |
| |
2.1 | 57 | {{info}} |
| 58 | **Note:** FR11 (Audit Trail) and FR13 (In-Article Claim Highlighting) are deferred to Beta 0 for production readiness and user experience enhancement. | ||
| 59 | {{/info}}: | ||
| 60 | * Claim extraction (FR1) | ||
| 61 | * Claim context (FR2) | ||
| 62 | * Multiple scenarios (FR3) | ||
| 63 | * Evidence collection (FR5) | ||
| 64 | * Source quality assessment (FR6) | ||
| 65 | * Time evolution tracking (FR8) - deferred to POC2 | ||
| 66 | * Audit trail (FR11) - deferred to Beta 0 | ||
| 67 | * In-article highlighting (FR13) - deferred to Beta 0 | ||
| |
1.1 | 68 | |
| |
2.1 | 69 | **Partial implementations:** |
| 70 | * NFR1 (Explainability) - Basic only | ||
| 71 | * NFR2 (Performance) - Functional but not optimized | ||
| 72 | * NFR3 (Transparency) - Basic only | ||
| |
1.1 | 73 | |
| |
2.1 | 74 | **Detailed POC1 implementation specifications continue below...** |
| |
1.1 | 75 | |
| 76 | |||
| 77 | |||
| |
2.1 | 78 | == 3. POC Simplifications == |
| |
1.1 | 79 | |
| |
2.1 | 80 | === 3.1 FR1: Claim Extraction (Full Implementation) === |
| |
1.1 | 81 | |
| |
2.1 | 82 | **Main Requirement:** AI extracts factual claims from input text |
| |
1.1 | 83 | |
| 84 | **POC Implementation:** | ||
| |
2.1 | 85 | * ✅ AKEL extracts claims using LLM |
| 86 | * ✅ Each claim includes original text reference | ||
| 87 | * ✅ Claims are identified as factual/non-factual | ||
| 88 | * ❌ No advanced claim parsing (added in POC2) | ||
| |
1.1 | 89 | |
| |
2.1 | 90 | **Acceptance Criteria:** |
| 91 | * Extracts 3-5 claims from typical article | ||
| 92 | * Identifies factual vs non-factual claims | ||
| 93 | * Quality Gate 1 validates extraction | ||
| |
1.1 | 94 | |
| 95 | |||
| |
2.1 | 96 | === 3.2 FR3: Multiple Scenarios (Full Implementation) === |
| |
1.1 | 97 | |
| |
2.1 | 98 | **Main Requirement:** Generate multiple interpretation scenarios for ambiguous claims |
| |
1.1 | 99 | |
| 100 | **POC Implementation:** | ||
| |
2.1 | 101 | * ✅ AKEL generates 2-3 scenarios per claim |
| 102 | * ✅ Scenarios capture different interpretations | ||
| 103 | * ✅ Each scenario is evaluated separately | ||
| 104 | * ✅ Verdict considers all scenarios | ||
| |
1.1 | 105 | |
| |
2.1 | 106 | **Acceptance Criteria:** |
| 107 | * Generates 2+ scenarios for ambiguous claims | ||
| 108 | * Scenarios are meaningfully different | ||
| 109 | * All scenarios are evaluated | ||
| |
1.1 | 110 | |
| 111 | |||
| |
2.1 | 112 | === 3.3 FR4: Analysis Summary (Basic Implementation) === |
| |
1.1 | 113 | |
| |
2.1 | 114 | **Main Requirement:** Provide user-friendly summary of analysis |
| |
1.1 | 115 | |
| 116 | **POC Implementation:** | ||
| |
2.1 | 117 | * ✅ Simple text summary generated |
| 118 | * ❌ No rich formatting (added in Beta 0) | ||
| 119 | * ❌ No visual elements (added in Beta 0) | ||
| 120 | * ❌ No interactive features (added in Beta 0) | ||
| |
1.1 | 121 | |
| |
2.1 | 122 | **POC Format:** |
| 123 | ``` | ||
| 124 | Claim: [extracted claim] | ||
| 125 | Scenarios: [list of scenarios] | ||
| 126 | Evidence: [supporting/opposing evidence] | ||
| 127 | Verdict: [probability with uncertainty] | ||
| 128 | ``` | ||
| |
1.1 | 129 | |
| 130 | |||
| |
2.1 | 131 | === 3.4 FR5-FR6: Evidence Collection & Evaluation (Full Implementation) === |
| |
1.1 | 132 | |
| |
2.1 | 133 | **Main Requirements:** |
| 134 | * FR5: Collect supporting and opposing evidence | ||
| 135 | * FR6: Evaluate evidence source reliability | ||
| |
1.1 | 136 | |
| 137 | **POC Implementation:** | ||
| |
2.1 | 138 | * ✅ AKEL searches for evidence (web/knowledge base) |
| 139 | * ✅ **Mandatory contradiction search** (finds opposing evidence) | ||
| 140 | * ✅ Source reliability scoring | ||
| 141 | * ❌ No evidence deduplication (added in POC2) | ||
| 142 | * ❌ No advanced source verification (added in POC2) | ||
| |
1.1 | 143 | |
| 144 | **Acceptance Criteria:** | ||
| |
2.1 | 145 | * Finds 2+ supporting evidence items |
| 146 | * Finds 1+ opposing evidence (if exists) | ||
| 147 | * Sources scored for reliability | ||
| |
1.1 | 148 | |
| 149 | |||
| |
2.1 | 150 | === 3.5 FR7: Automated Verdicts (Full Implementation) === |
| |
1.1 | 151 | |
| |
2.1 | 152 | **Main Requirement:** AI computes verdicts with uncertainty quantification |
| |
1.1 | 153 | |
| |
2.1 | 154 | **POC Implementation:** |
| 155 | * ✅ Probabilistic verdicts (0-100% confidence) | ||
| 156 | * ✅ Uncertainty explicitly stated | ||
| 157 | * ✅ Reasoning chain provided | ||
| 158 | * ✅ Quality Gate 4 validates verdict confidence | ||
| |
1.1 | 159 | |
| |
2.1 | 160 | **POC Output:** |
| 161 | ``` | ||
| 162 | Verdict: 70% likely true | ||
| 163 | Uncertainty: ±15% (moderate confidence) | ||
| 164 | Reasoning: Based on 3 high-quality sources... | ||
| 165 | Confidence Level: MEDIUM | ||
| 166 | ``` | ||
| |
1.1 | 167 | |
| 168 | **Acceptance Criteria:** | ||
| |
2.1 | 169 | * Verdicts include probability (0-100%) |
| 170 | * Uncertainty explicitly quantified | ||
| 171 | * Reasoning chain explains verdict | ||
| |
1.1 | 172 | |
| 173 | |||
| |
2.1 | 174 | === 3.6 NFR11: Quality Assurance Framework (LITE VERSION) === |
| |
1.1 | 175 | |
| |
2.1 | 176 | **Main Requirement:** Complete quality assurance with 7 quality gates |
| |
1.1 | 177 | |
| |
2.1 | 178 | **POC Implementation:** **2 gates only** |
| |
1.1 | 179 | |
| |
2.1 | 180 | **Quality Gate 1: Claim Validation** |
| 181 | * ✅ Validates claim is factual and verifiable | ||
| 182 | * ✅ Blocks non-factual claims (opinion/prediction/ambiguous) | ||
| 183 | * ✅ Provides clear rejection reason | ||
| |
1.1 | 184 | |
| |
2.1 | 185 | **Quality Gate 4: Verdict Confidence Assessment** |
| 186 | * ✅ Validates ≥2 sources found | ||
| 187 | * ✅ Validates quality score ≥0.6 | ||
| 188 | * ✅ Blocks low-confidence verdicts | ||
| 189 | * ✅ Provides clear rejection reason | ||
| |
1.1 | 190 | |
| |
2.1 | 191 | **Out of Scope (POC2+):** |
| 192 | * ❌ Gate 2: Evidence Relevance | ||
| 193 | * ❌ Gate 3: Scenario Coherence | ||
| 194 | * ❌ Gate 5: Source Diversity | ||
| 195 | * ❌ Gate 6: Reasoning Validity | ||
| 196 | * ❌ Gate 7: Output Completeness | ||
| |
1.1 | 197 | |
| |
2.1 | 198 | **Rationale:** Prove gate concept works. Add remaining gates in POC2 after validating approach. |
| |
1.1 | 199 | |
| 200 | |||
| |
2.1 | 201 | === 3.7 NFR1-3: Performance, Scalability, Reliability (Basic) === |
| |
1.1 | 202 | |
| |
2.1 | 203 | **Main Requirements:** |
| 204 | * NFR1: Response time < 30 seconds | ||
| 205 | * NFR2: Handle 1000+ concurrent users | ||
| 206 | * NFR3: 99.9% uptime | ||
| |
1.1 | 207 | |
| |
2.1 | 208 | **POC Implementation:** |
| 209 | * ⚠️ **Response time monitored** (not optimized) | ||
| 210 | * ⚠️ **Single-threaded processing** (no concurrency) | ||
| 211 | * ⚠️ **Basic error handling** (no advanced retry logic) | ||
| |
1.1 | 212 | |
| |
2.1 | 213 | **Rationale:** POC proves functionality. Performance optimization happens in POC2. |
| |
1.1 | 214 | |
| |
2.1 | 215 | **POC Acceptance:** |
| 216 | * Analysis completes (no timeout requirement) | ||
| 217 | * Errors don't crash system | ||
| 218 | * Basic logging in place | ||
| |
1.1 | 219 | |
| 220 | |||
| |
2.1 | 221 | == 4. What's NOT in POC Scope == |
| |
1.1 | 222 | |
| |
2.1 | 223 | === 4.1 User-Facing Features (Beta 0+) === |
| |
1.1 | 224 | |
| |
2.1 | 225 | {{warning}} |
| 226 | **Deferred to Beta 0:** | ||
| 227 | {{/warning}} | ||
| |
1.1 | 228 | |
| |
2.1 | 229 | **Out of Scope:** |
| 230 | * ❌ User accounts and authentication (FR8) | ||
| 231 | * ❌ User corrections system (FR9, FR45-46) | ||
| 232 | * ❌ Public publishing interface (FR10) | ||
| 233 | * ❌ Social sharing (FR11) | ||
| 234 | * ❌ Email notifications (FR12) | ||
| 235 | * ❌ API access (FR13) | ||
| |
1.1 | 236 | |
| |
2.1 | 237 | **Rationale:** POC validates AI capabilities. User features added in Beta 0. |
| |
1.1 | 238 | |
| 239 | |||
| |
2.1 | 240 | === 4.2 Advanced Features (V1.0+) === |
| |
1.1 | 241 | |
| |
2.1 | 242 | **Out of Scope:** |
| 243 | * ❌ IFCN compliance (FR47) | ||
| 244 | * ❌ ClaimReview schema (FR48) | ||
| 245 | * ❌ Archive.org integration (FR49) | ||
| 246 | * ❌ OSINT toolkit (FR50) | ||
| 247 | * ❌ Video verification (FR51) | ||
| 248 | * ❌ Deepfake detection (FR52) | ||
| 249 | * ❌ Cross-org sharing (FR53) | ||
| |
1.1 | 250 | |
| |
2.1 | 251 | **Rationale:** Advanced features require proven platform. Added post-V1.0. |
| |
1.1 | 252 | |
| 253 | |||
| |
2.1 | 254 | === 4.3 Production Requirements (POC2, Beta 0) === |
| |
1.1 | 255 | |
| |
2.1 | 256 | **Out of Scope:** |
| 257 | * ❌ Security controls (NFR4, NFR12) | ||
| 258 | * ❌ Code maintainability (NFR5) | ||
| 259 | * ❌ System monitoring (NFR13) | ||
| 260 | * ❌ Evidence deduplication | ||
| 261 | * ❌ Advanced source verification | ||
| 262 | * ❌ Full 7-gate quality framework | ||
| |
1.1 | 263 | |
| |
2.1 | 264 | **Rationale:** POC proves concept. Production hardening happens in POC2 and Beta 0. |
| |
1.1 | 265 | |
| 266 | |||
| |
2.1 | 267 | == 5. POC Output Specification == |
| |
1.1 | 268 | |
| |
2.1 | 269 | === 5.1 Required Output Elements === |
| |
1.1 | 270 | |
| |
2.1 | 271 | For each analyzed claim, POC must produce: |
| |
1.1 | 272 | |
| |
2.1 | 273 | **1. Claim** |
| 274 | * Original text | ||
| 275 | * Classification (factual/non-factual/ambiguous) | ||
| 276 | * If non-factual: Clear reason why | ||
| |
1.1 | 277 | |
| |
2.1 | 278 | **2. Scenarios** (if factual) |
| 279 | * 2-3 interpretation scenarios | ||
| 280 | * Each scenario clearly described | ||
| |
1.1 | 281 | |
| |
2.1 | 282 | **3. Evidence** (if factual) |
| 283 | * Supporting evidence (2+ items) | ||
| 284 | * Opposing evidence (if exists) | ||
| 285 | * Source URLs and reliability scores | ||
| |
1.1 | 286 | |
| |
2.1 | 287 | **4. Verdict** (if factual) |
| 288 | * Probability (0-100%) | ||
| 289 | * Uncertainty quantification | ||
| 290 | * Confidence level (LOW/MEDIUM/HIGH) | ||
| 291 | * Reasoning chain | ||
| |
1.1 | 292 | |
| |
2.1 | 293 | **5. Quality Status** |
| 294 | * Which gates passed/failed | ||
| 295 | * If failed: Clear explanation why | ||
| |
1.1 | 296 | |
| 297 | |||
| |
2.1 | 298 | === 5.2 Example POC Output === |
| |
1.1 | 299 | |
| |
2.1 | 300 | {{code language="json"}} |
| 301 | { | ||
| 302 | "claim": { | ||
| 303 | "text": "Switzerland has the highest life expectancy in Europe", | ||
| 304 | "type": "factual", | ||
| 305 | "gate1_status": "PASS" | ||
| 306 | }, | ||
| 307 | "scenarios": [ | ||
| 308 | "Switzerland's overall life expectancy is highest", | ||
| 309 | "Switzerland ranks highest for specific age groups" | ||
| 310 | ], | ||
| 311 | "evidence": { | ||
| 312 | "supporting": [ | ||
| 313 | { | ||
| 314 | "source": "WHO Report 2023", | ||
| 315 | "reliability": 0.95, | ||
| 316 | "excerpt": "Switzerland: 83.4 years average..." | ||
| 317 | } | ||
| 318 | ], | ||
| 319 | "opposing": [ | ||
| 320 | { | ||
| 321 | "source": "Eurostat 2024", | ||
| 322 | "reliability": 0.90, | ||
| 323 | "excerpt": "Spain leads at 83.5 years..." | ||
| 324 | } | ||
| 325 | ] | ||
| 326 | }, | ||
| 327 | "verdict": { | ||
| 328 | "probability": 0.65, | ||
| 329 | "uncertainty": 0.15, | ||
| 330 | "confidence": "MEDIUM", | ||
| 331 | "reasoning": "WHO and Eurostat show similar but conflicting data...", | ||
| 332 | "gate4_status": "PASS" | ||
| 333 | } | ||
| 334 | } | ||
| |
1.1 | 335 | {{/code}} |
| 336 | |||
| 337 | |||
| |
2.1 | 338 | == 6. Success Criteria == |
| |
1.1 | 339 | |
| |
2.1 | 340 | {{success}} |
| 341 | **POC Success Definition:** POC validates that AI can extract claims, find balanced evidence, and compute reasonable verdicts with quality gates improving output quality. | ||
| 342 | {{/success}} | ||
| |
1.1 | 343 | |
| |
2.1 | 344 | === 6.1 Functional Success === |
| |
1.1 | 345 | |
| |
2.1 | 346 | POC is successful if: |
| |
1.1 | 347 | |
| |
2.1 | 348 | ✅ **FR1-FR7 Requirements Met:** |
| 349 | 1. Extracts 3-5 factual claims from test articles | ||
| 350 | 2. Generates 2-3 scenarios per ambiguous claim | ||
| 351 | 3. Finds supporting AND opposing evidence | ||
| 352 | 4. Computes probabilistic verdicts with uncertainty | ||
| 353 | 5. Provides clear reasoning chains | ||
| |
1.1 | 354 | |
| |
2.1 | 355 | ✅ **Quality Gates Work:** |
| 356 | 1. Gate 1 blocks non-factual claims (100% block rate) | ||
| 357 | 2. Gate 4 blocks low-quality verdicts (blocks if <2 sources or quality <0.6) | ||
| 358 | 3. Clear rejection reasons provided | ||
| |
1.1 | 359 | |
| |
2.1 | 360 | ✅ **NFR11 Met:** |
| 361 | 1. Quality gates reduce hallucination rate | ||
| 362 | 2. Blocked outputs have clear explanations | ||
| 363 | 3. Quality metrics are logged | ||
| |
1.1 | 364 | |
| 365 | |||
| |
2.1 | 366 | === 6.2 Quality Thresholds === |
| |
1.1 | 367 | |
| |
2.1 | 368 | **Minimum Acceptable:** |
| 369 | * ≥70% of test claims correctly classified (factual/non-factual) | ||
| 370 | * ≥60% of verdicts are reasonable (human evaluation) | ||
| 371 | * Gate 1 blocks 100% of non-factual claims | ||
| 372 | * Gate 4 blocks verdicts with <2 sources | ||
| |
1.1 | 373 | |
| |
2.1 | 374 | **Target:** |
| 375 | * ≥80% claims correctly classified | ||
| 376 | * ≥75% verdicts are reasonable | ||
| 377 | * <10% false positives (blocking good claims) | ||
| |
1.1 | 378 | |
| 379 | |||
| |
2.1 | 380 | === 6.3 POC Decision Gate === |
| |
1.1 | 381 | |
| |
2.1 | 382 | **After POC1, we decide:** |
| |
1.1 | 383 | |
| |
2.1 | 384 | **✅ PROCEED to POC2** if: |
| 385 | * Success criteria met | ||
| 386 | * Quality gates demonstrably improve output | ||
| 387 | * Core workflow is technically sound | ||
| 388 | * Clear path to production quality | ||
| |
1.1 | 389 | |
| |
2.1 | 390 | **⚠️ ITERATE POC1** if: |
| 391 | * Success criteria partially met | ||
| 392 | * Gates work but need tuning | ||
| 393 | * Core issues identified but fixable | ||
| |
1.1 | 394 | |
| |
2.1 | 395 | **❌ PIVOT APPROACH** if: |
| 396 | * Success criteria not met | ||
| 397 | * Fundamental AI limitations discovered | ||
| 398 | * Quality gates insufficient | ||
| 399 | * Alternative approach needed | ||
| |
1.1 | 400 | |
| 401 | |||
| |
2.1 | 402 | == 7. Test Cases == |
| |
1.1 | 403 | |
| |
2.1 | 404 | === 7.1 Happy Path === |
| |
1.1 | 405 | |
| |
2.1 | 406 | **Test 1: Simple Factual Claim** |
| 407 | * Input: "Paris is the capital of France" | ||
| 408 | * Expected: Factual, 1 scenario, verdict ~95% true | ||
| |
1.1 | 409 | |
| |
2.1 | 410 | **Test 2: Ambiguous Claim** |
| 411 | * Input: "Switzerland has the highest income in Europe" | ||
| 412 | * Expected: Factual, 2-3 scenarios, verdict with uncertainty | ||
| |
1.1 | 413 | |
| |
2.1 | 414 | **Test 3: Statistical Claim** |
| 415 | * Input: "10% of people have condition X" | ||
| 416 | * Expected: Factual, evidence with numbers, probabilistic verdict | ||
| |
1.1 | 417 | |
| 418 | |||
| |
2.1 | 419 | === 7.2 Edge Cases === |
| |
1.1 | 420 | |
| |
2.1 | 421 | **Test 4: Opinion** |
| 422 | * Input: "Paris is the best city" | ||
| 423 | * Expected: Non-factual (opinion), blocked by Gate 1 | ||
| |
1.1 | 424 | |
| |
2.1 | 425 | **Test 5: Prediction** |
| 426 | * Input: "Bitcoin will reach $100,000 next year" | ||
| 427 | * Expected: Non-factual (prediction), blocked by Gate 1 | ||
| |
1.1 | 428 | |
| |
2.1 | 429 | **Test 6: Insufficient Evidence** |
| 430 | * Input: Obscure factual claim with no sources | ||
| 431 | * Expected: Blocked by Gate 4 (<2 sources) | ||
| |
1.1 | 432 | |
| 433 | |||
| |
2.1 | 434 | === 7.3 Quality Gate Tests === |
| |
1.1 | 435 | |
| |
2.1 | 436 | **Test 7: Gate 1 Effectiveness** |
| 437 | * Input: Mix of 10 factual + 10 non-factual claims | ||
| 438 | * Expected: Gate 1 blocks all 10 non-factual (100% precision) | ||
| |
1.1 | 439 | |
| |
2.1 | 440 | **Test 8: Gate 4 Effectiveness** |
| 441 | * Input: Claims with varying evidence availability | ||
| 442 | * Expected: Gate 4 blocks low-confidence verdicts | ||
| |
1.1 | 443 | |
| 444 | |||
| |
2.1 | 445 | == 8. Technical Architecture (POC) == |
| |
1.1 | 446 | |
| |
2.1 | 447 | === 8.1 Simplified Architecture === |
| |
1.1 | 448 | |
| |
2.1 | 449 | **POC Tech Stack:** |
| 450 | * **Frontend:** Simple web interface (Next.js + TypeScript) | ||
| 451 | * **Backend:** Single API endpoint | ||
| 452 | * **AI:** Claude API (Sonnet 4.5) | ||
| 453 | * **Database:** Local JSON files (no database) | ||
| 454 | * **Deployment:** Single server | ||
| |
1.1 | 455 | |
| |
2.1 | 456 | **Architecture Diagram:** See [[POC1 Specification>>FactHarbor.Specification.POC.Specification]] |
| |
1.1 | 457 | |
| 458 | |||
| |
2.1 | 459 | === 8.2 AKEL Implementation === |
| |
1.1 | 460 | |
| |
2.1 | 461 | **POC AKEL:** |
| 462 | * Single-threaded processing | ||
| 463 | * Synchronous API calls | ||
| 464 | * No caching | ||
| 465 | * Basic error handling | ||
| 466 | * Console logging | ||
| |
1.1 | 467 | |
| |
2.1 | 468 | **Full AKEL (POC2+):** |
| 469 | * Multi-threaded processing | ||
| 470 | * Async API calls | ||
| 471 | * Evidence caching | ||
| 472 | * Advanced error handling with retry | ||
| 473 | * Structured logging + monitoring | ||
| |
1.1 | 474 | |
| 475 | |||
| |
2.1 | 476 | == 9. POC Philosophy == |
| |
1.1 | 477 | |
| |
2.1 | 478 | {{info}} |
| 479 | **Important:** POC validates concept, not production readiness. Focus is on proving AI can do the job, with production quality coming in later phases. | ||
| 480 | {{/info}} | ||
| |
1.1 | 481 | |
| |
2.1 | 482 | === 9.1 Core Principles === |
| |
1.1 | 483 | |
| |
2.1 | 484 | **1. Prove Concept, Not Production** |
| 485 | * POC validates AI can do the job | ||
| 486 | * Production quality comes in POC2 and Beta 0 | ||
| 487 | * Focus on "does it work?" not "is it perfect?" | ||
| |
1.1 | 488 | |
| |
2.1 | 489 | **2. Implement Subset of Requirements** |
| 490 | * POC covers FR1-7, NFR11 (lite) | ||
| 491 | * All other requirements deferred | ||
| 492 | * Clear mapping to [[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]] | ||
| |
1.1 | 493 | |
| |
2.1 | 494 | **3. Quality Gates Validate Approach** |
| 495 | * 2 gates prove the concept | ||
| 496 | * Remaining 5 gates added in POC2 | ||
| 497 | * Gates must demonstrably improve quality | ||
| |
1.1 | 498 | |
| |
2.1 | 499 | **4. Iterate Based on Results** |
| 500 | * POC results determine next steps | ||
| 501 | * Decision gate after POC1 | ||
| 502 | * Flexibility to pivot if needed | ||
| |
1.1 | 503 | |
| 504 | |||
| |
2.1 | 505 | === 9.2 Success = Clear Path Forward === |
| |
1.1 | 506 | |
| |
2.1 | 507 | POC succeeds if we can confidently answer: |
| |
1.1 | 508 | |
| |
2.1 | 509 | ✅ **Technical Feasibility:** |
| 510 | * Can AI extract claims reliably? | ||
| 511 | * Can AI find balanced evidence? | ||
| 512 | * Can AI compute reasonable verdicts? | ||
| |
1.1 | 513 | |
| |
2.1 | 514 | ✅ **Quality Approach:** |
| 515 | * Do quality gates improve output? | ||
| 516 | * Can we measure and track quality? | ||
| 517 | * Is the gate approach scalable? | ||
| |
1.1 | 518 | |
| |
2.1 | 519 | ✅ **Production Path:** |
| 520 | * Is the core architecture sound? | ||
| 521 | * What needs improvement for production? | ||
| 522 | * Is POC2 the right next step? | ||
| |
1.1 | 523 | |
| 524 | |||
| |
2.1 | 525 | == 10. Related Pages == |
| |
1.1 | 526 | |
| |
2.1 | 527 | * **[[Main Requirements>>FactHarbor.Specification.Requirements.WebHome]]** - Full system requirements (this POC implements a subset) |
| 528 | * **[[POC1 Specification (Detailed)>>FactHarbor.Specification.POC.Specification]]** - Detailed POC1 technical specs | ||
| 529 | * **[[POC Summary>>FactHarbor.Specification.POC.Summary]]** - High-level POC overview | ||
| 530 | * **[[Implementation Roadmap>>FactHarbor.Roadmap.WebHome]]** - POC1, POC2, Beta 0, V1.0 phases | ||
| 531 | * **[[User Needs>>FactHarbor.Specification.Requirements.User Needs.WebHome]]** - What users need (drives requirements) | ||
| |
1.1 | 532 | |
| 533 | |||
| |
2.1 | 534 | **Document Owner:** Technical Team |
| 535 | **Review Frequency:** After each POC iteration | ||
| 536 | **Version History:** | ||
| 537 | * v1.0 - Initial POC requirements | ||
| 538 | * v2.0 - Updated after specification cross-check | ||
| 539 | * v3.0 - Aligned with Main Requirements (FR/NFR IDs added) | ||
| |
1.1 | 540 |