Skip to Content

Changes for page Automation

Last modified by Robert Schaub on 2025/12/24 20:34
From version 1.3
edited by Robert Schaub
on 2025/12/11 21:34
Change comment: Renamed back-links.
To version 3.1
edited by Robert Schaub
on 2025/12/12 08:32
Change comment: Imported from XAR

Summary

Details

Page properties
Content
... ... @@ -4,17 +4,37 @@
4 4  All automated outputs require human review before publication.
5 5  
6 6  This chapter defines:
7 -
8 8  * What must remain human-only
9 9  * What AI (AKEL) can draft
10 10  * What can be fully automated
11 11  * How automation evolves through POC → Beta 0 → Release 1.0
12 12  
12 +== POC v1 (Fully Automated "Text to Truth Landscape") ==
13 +
14 +The goal of POC v1 is to validate the automated reasoning capabilities of the data model without human intervention.
15 +
16 +=== Workflow ===
17 +
18 +1. **Input**: User pastes a block of raw text.
19 +2. **Deep Analysis (Background)**: The system autonomously performs the full pipeline **before** displaying the text:
20 +** Extraction & Normalisation
21 +** Scenario & Sub-query generation
22 +** Evidence retrieval & Verdict computation
23 +3. **Visualisation (Extraction & Marking)**: The system displays the text with claims extracted and marked.
24 +** **Verdict-Based Coloring**: The extraction highlights (e.g. Orange/Green) are chosen **according to the computed verdict** for each claim.
25 +4. **Inspection**: User clicks a highlighted claim to see the **Reasoning Trail**, showing exactly which evidence and sub-queries led to that verdict.
26 +
27 +=== Technical Scope ===
28 +
29 +* **Fully Automated**: No human-in-the-loop for this phase.
30 +* **Structured Sub-Queries**: Logic is generated by decomposing claims into the FactHarbor data model.
31 +* **Latency**: Focus on accuracy of reasoning over real-time speed for v1.
32 +
13 13  ----
14 14  
15 -= Manual vs Automated Responsibilities =
35 +== Manual vs Automated Responsibilities ==
16 16  
17 -== Human-Only Tasks ==
37 +=== Human-Only Tasks ===
18 18  
19 19  These require human judgment, ethics, or contextual interpretation:
20 20  
... ... @@ -26,7 +26,7 @@
26 26  * High-risk domain oversight
27 27  * Ethical boundary decisions (especially medical, political, psychological)
28 28  
29 -== Semi-Automated (AI Draft → Human Review) ==
49 +=== Semi-Automated (AI Draft → Human Review) ===
30 30  
31 31  AKEL can draft these, but humans must refine/approve:
32 32  
... ... @@ -40,7 +40,7 @@
40 40  * Suggestions for merging or splitting scenarios
41 41  * Draft public summaries
42 42  
43 -== Fully Automated Structural Tasks ==
63 +=== Fully Automated Structural Tasks ===
44 44  
45 45  These require no human interpretation:
46 46  
... ... @@ -53,115 +53,39 @@
53 53  * Batch layout generation (diagrams, summaries)
54 54  * Federation integrity checks
55 55  
56 -----
76 +== Automation Roadmap ==
57 57  
58 -= Automation Roadmap =
59 -
60 60  Automation increases with maturity.
61 61  
62 -== POC (Low Automation) ==
80 +=== POC (Low Automation) ===
81 +* **Automated**: Claim normalization, Light scenario templates, Metadata extraction, Internal drafts.
82 +* **Human**: All scenario definitions, Evidence interpretation, Verdict creation, Governance.
63 63  
64 -=== Automated ===
84 +=== Beta 0 (Medium Automation) ===
85 +* **Automated**: Detailed scenario drafts, Evidence reliability scoring, Cross-scenario comparisons, Contradiction detection.
86 +* **Human**: Scenario approval, Final verdict validation.
65 65  
66 -* Claim normalization
67 -* Light scenario templates
68 -* Evidence metadata extraction
69 -* Simple verdict drafts (internal only)
88 +=== Release 1.0 (High Automation) ===
89 +* **Automated**: Full scenario generation, Evidence relevance ranking, Bayesian verdict scoring, Anomaly detection, Federation sync.
90 +* **Human**: Final approval, Ethical decisions, Oversight.
70 70  
71 -=== Human ===
92 +== Automation Levels ==
72 72  
73 -* All scenario definitions
74 -* Evidence interpretation
75 -* Verdict creation
76 -* Governance
94 +* **Level 0 — Human-Centric (POC)**: AI is purely advisory, nothing auto-published.
95 +* **Level 1 — Assisted (Beta 0)**: AI drafts structures; humans approve each part.
96 +* **Level 2 — Structured (Release 1.0)**: AI produces near-complete drafts; humans refine.
97 +* **Level 3 — Distributed Intelligence (Future)**: Nodes exchange embeddings and alerts; humans still approve.
77 77  
78 -== Beta 0 (Medium Automation) ==
99 +== Automation Matrix ==
79 79  
80 -=== Automated ===
101 +* **Always Human**: Final verdict, Scenario validity, Ethics, Disputes.
102 +* **Mostly AI**: Normalization, Clustering, Metadata, Heuristics, Alerts.
103 +* **Mixed**: Definitions, Boundaries, Assumptions, Reasoning.
81 81  
82 -* Detailed scenario drafts
83 -* Evidence reliability scoring
84 -* Cross-scenario comparisons
85 -* Contradiction detection (local + remote nodes)
86 -* Internal Truth Landscape drafts
105 +== Diagram References ==
87 87  
88 -=== Human ===
107 +{{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
89 89  
90 -* Scenario approval
91 -* Final verdict validation
109 +{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
92 92  
93 -== Release 1.0 (High Automation) ==
94 -
95 -=== Automated ===
96 -
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 ===
105 -
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) ==
115 -
116 -AI is purely advisory, nothing auto-published.
117 -
118 -== Level 1 — Assisted (Beta 0) ==
119 -
120 -AI drafts structures; humans approve each part.
121 -
122 -== Level 2 — Structured (Release 1.0) ==
123 -
124 -AI produces near-complete drafts; humans refine.
125 -
126 -== Level 3 — Distributed Intelligence (Future) ==
127 -
128 -Nodes exchange embeddings, contradiction alerts, and scenario templates.
129 -Humans still approve everything.
130 -
131 -----
132 -
133 -= Automation Matrix =
134 -
135 -== Always Human ==
136 -
137 -* Final verdict approval
138 -* Scenario validity
139 -* Ethical decisions
140 -* Dispute resolution
141 -
142 -== Mostly AI (Human Validation Needed) ==
143 -
144 -* Claim normalization
145 -* Clustering
146 -* Evidence metadata
147 -* Reliability heuristics
148 -* Scenario drafts
149 -* Contradiction detection
150 -
151 -== Mixed ==
152 -
153 -* Definitions of ambiguous terms
154 -* Boundary choices
155 -* Assumption evaluation
156 -* Evidence selection
157 -* Verdict reasoning
158 -
159 -----
160 -
161 -= Diagram References =
162 -
163 -{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Roadmap.WebHome"/}}
164 -
165 -{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Level.WebHome"/}}
166 -
167 167  {{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}