Wiki source code of Automation
Version 1.4 by Robert Schaub on 2025/12/11 21:34
Hide last authors
| author | version | line-number | content |
|---|---|---|---|
 |
1.1 | 1 | = Automation = |
| 2 | |||
| 3 | Automation in FactHarbor amplifies human capability but never replaces human oversight. | ||
| 4 | All automated outputs require human review before publication. | ||
| 5 | |||
| 6 | This chapter defines: | ||
| |
1.2 | 7 | |
| |
1.1 | 8 | * What must remain human-only |
| 9 | * What AI (AKEL) can draft | ||
| 10 | * What can be fully automated | ||
| 11 | * How automation evolves through POC → Beta 0 → Release 1.0 | ||
| 12 | |||
| 13 | ---- | ||
| 14 | |||
| 15 | = Manual vs Automated Responsibilities = | ||
| 16 | |||
| 17 | == Human-Only Tasks == | ||
| 18 | |||
| 19 | These require human judgment, ethics, or contextual interpretation: | ||
| 20 | |||
| 21 | * Definition of key terms in claims | ||
| 22 | * Approval or rejection of scenarios | ||
| 23 | * Interpretation of evidence in context | ||
| 24 | * Final verdict approval | ||
| 25 | * Governance decisions and dispute resolution | ||
| 26 | * High-risk domain oversight | ||
| 27 | * Ethical boundary decisions (especially medical, political, psychological) | ||
| 28 | |||
| 29 | == Semi-Automated (AI Draft → Human Review) == | ||
| 30 | |||
| 31 | AKEL can draft these, but humans must refine/approve: | ||
| 32 | |||
| 33 | * Scenario structures (definitions, assumptions, context) | ||
| 34 | * Evaluation methods | ||
| 35 | * Evidence relevance suggestions | ||
| 36 | * Reliability hints | ||
| 37 | * Verdict reasoning chains | ||
| 38 | * Uncertainty and limitations | ||
| 39 | * Scenario comparison explanations | ||
| 40 | * Suggestions for merging or splitting scenarios | ||
| 41 | * Draft public summaries | ||
| 42 | |||
| 43 | == Fully Automated Structural Tasks == | ||
| 44 | |||
| 45 | These require no human interpretation: | ||
| 46 | |||
| 47 | * Claim normalization | ||
| 48 | * Duplicate & cluster detection (vector embeddings) | ||
| 49 | * Evidence metadata extraction | ||
| 50 | * Basic reliability heuristics | ||
| 51 | * Contradiction detection | ||
| 52 | * Re-evaluation triggers | ||
| 53 | * Batch layout generation (diagrams, summaries) | ||
| 54 | * Federation integrity checks | ||
| 55 | |||
| 56 | ---- | ||
| 57 | |||
| 58 | = Automation Roadmap = | ||
| 59 | |||
| 60 | Automation increases with maturity. | ||
| 61 | |||
| 62 | == POC (Low Automation) == | ||
| 63 | |||
| 64 | === Automated === | ||
| |
1.2 | 65 | |
| |
1.1 | 66 | * Claim normalization |
| 67 | * Light scenario templates | ||
| 68 | * Evidence metadata extraction | ||
| 69 | * Simple verdict drafts (internal only) | ||
| 70 | |||
| 71 | === Human === | ||
| |
1.2 | 72 | |
| |
1.1 | 73 | * All scenario definitions |
| 74 | * Evidence interpretation | ||
| 75 | * Verdict creation | ||
| 76 | * Governance | ||
| 77 | |||
| 78 | == Beta 0 (Medium Automation) == | ||
| 79 | |||
| 80 | === Automated === | ||
| |
1.2 | 81 | |
| |
1.1 | 82 | * Detailed scenario drafts |
| 83 | * Evidence reliability scoring | ||
| 84 | * Cross-scenario comparisons | ||
| 85 | * Contradiction detection (local + remote nodes) | ||
| 86 | * Internal Truth Landscape drafts | ||
| 87 | |||
| 88 | === Human === | ||
| |
1.2 | 89 | |
| |
1.1 | 90 | * Scenario approval |
| 91 | * Final verdict validation | ||
| 92 | |||
| 93 | == Release 1.0 (High Automation) == | ||
| 94 | |||
| 95 | === Automated === | ||
| |
1.2 | 96 | |
| |
1.1 | 97 | * Full scenario generation (definitions, assumptions, boundaries) |
| 98 | * Evidence relevance scoring and ranking | ||
| 99 | * Bayesian verdict scoring across scenario sets | ||
| 100 | * Multi-scenario summary generation | ||
| 101 | * Anomaly detection across nodes | ||
| 102 | * AKEL-assisted federated synchronization | ||
| 103 | |||
| 104 | === Human === | ||
| |
1.2 | 105 | |
| |
1.1 | 106 | * Final approval of all scenarios and verdicts |
| 107 | * Ethical decisions | ||
| 108 | * Oversight and conflict resolution | ||
| 109 | |||
| 110 | ---- | ||
| 111 | |||
| 112 | = Automation Levels = | ||
| 113 | |||
| 114 | == Level 0 — Human-Centric (POC) == | ||
| |
1.2 | 115 | |
| |
1.1 | 116 | AI is purely advisory, nothing auto-published. |
| 117 | |||
| 118 | == Level 1 — Assisted (Beta 0) == | ||
| |
1.2 | 119 | |
| |
1.1 | 120 | AI drafts structures; humans approve each part. |
| 121 | |||
| 122 | == Level 2 — Structured (Release 1.0) == | ||
| |
1.2 | 123 | |
| |
1.1 | 124 | AI produces near-complete drafts; humans refine. |
| 125 | |||
| 126 | == Level 3 — Distributed Intelligence (Future) == | ||
| |
1.2 | 127 | |
| |
1.1 | 128 | Nodes exchange embeddings, contradiction alerts, and scenario templates. |
| 129 | Humans still approve everything. | ||
| 130 | |||
| 131 | ---- | ||
| 132 | |||
| 133 | = Automation Matrix = | ||
| 134 | |||
| 135 | == Always Human == | ||
| |
1.2 | 136 | |
| |
1.1 | 137 | * Final verdict approval |
| 138 | * Scenario validity | ||
| 139 | * Ethical decisions | ||
| 140 | * Dispute resolution | ||
| 141 | |||
| 142 | == Mostly AI (Human Validation Needed) == | ||
| |
1.2 | 143 | |
| |
1.1 | 144 | * Claim normalization |
| 145 | * Clustering | ||
| 146 | * Evidence metadata | ||
| 147 | * Reliability heuristics | ||
| 148 | * Scenario drafts | ||
| 149 | * Contradiction detection | ||
| 150 | |||
| 151 | == Mixed == | ||
| |
1.2 | 152 | |
| |
1.1 | 153 | * Definitions of ambiguous terms |
| 154 | * Boundary choices | ||
| 155 | * Assumption evaluation | ||
| 156 | * Evidence selection | ||
| 157 | * Verdict reasoning | ||
| 158 | |||
| 159 | ---- | ||
| 160 | |||
| 161 | = Diagram References = | ||
| 162 | |||
| |
1.3 | 163 | {{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Roadmap.WebHome"/}} |
| |
1.1 | 164 | |
| |
1.2 | 165 | {{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Level.WebHome"/}} |
| |
1.1 | 166 | |
| |
1.4 | 167 | {{include reference="FactHarbor.Archive.Diagrams v0\.8q.Manual vs Automated matrix.WebHome"/}} |