Skip to Content

Changes for page Automation

Last modified by Robert Schaub on 2025/12/24 20:34
From version 5.1
edited by Robert Schaub
on 2025/12/12 15:41
Change comment: Imported from XAR
To version 1.2
edited by Robert Schaub
on 2025/12/11 21:34
Change comment: Renamed back-links.

Summary

Details

Page properties
Content
... ... @@ -4,32 +4,12 @@
4 4  All automated outputs require human review before publication.
5 5  
6 6  This chapter defines:
7 +
7 7  * What must remain human-only
8 8  * What AI (AKEL) can draft
9 9  * What can be fully automated
10 10  * How automation evolves through POC → Beta 0 → Release 1.0
11 11  
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 -1. **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 -1. **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 -1. **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 -
33 33  ----
34 34  
35 35  = Manual vs Automated Responsibilities =
... ... @@ -82,6 +82,7 @@
82 82  == POC (Low Automation) ==
83 83  
84 84  === Automated ===
65 +
85 85  * Claim normalization
86 86  * Light scenario templates
87 87  * Evidence metadata extraction
... ... @@ -88,6 +88,7 @@
88 88  * Simple verdict drafts (internal only)
89 89  
90 90  === Human ===
72 +
91 91  * All scenario definitions
92 92  * Evidence interpretation
93 93  * Verdict creation
... ... @@ -96,6 +96,7 @@
96 96  == Beta 0 (Medium Automation) ==
97 97  
98 98  === Automated ===
81 +
99 99  * Detailed scenario drafts
100 100  * Evidence reliability scoring
101 101  * Cross-scenario comparisons
... ... @@ -103,6 +103,7 @@
103 103  * Internal Truth Landscape drafts
104 104  
105 105  === Human ===
89 +
106 106  * Scenario approval
107 107  * Final verdict validation
108 108  
... ... @@ -109,6 +109,7 @@
109 109  == Release 1.0 (High Automation) ==
110 110  
111 111  === Automated ===
96 +
112 112  * Full scenario generation (definitions, assumptions, boundaries)
113 113  * Evidence relevance scoring and ranking
114 114  * Bayesian verdict scoring across scenario sets
... ... @@ -117,6 +117,7 @@
117 117  * AKEL-assisted federated synchronization
118 118  
119 119  === Human ===
105 +
120 120  * Final approval of all scenarios and verdicts
121 121  * Ethical decisions
122 122  * Oversight and conflict resolution
... ... @@ -126,15 +126,19 @@
126 126  = Automation Levels =
127 127  
128 128  == Level 0 — Human-Centric (POC) ==
115 +
129 129  AI is purely advisory, nothing auto-published.
130 130  
131 131  == Level 1 — Assisted (Beta 0) ==
119 +
132 132  AI drafts structures; humans approve each part.
133 133  
134 134  == Level 2 — Structured (Release 1.0) ==
123 +
135 135  AI produces near-complete drafts; humans refine.
136 136  
137 137  == Level 3 — Distributed Intelligence (Future) ==
127 +
138 138  Nodes exchange embeddings, contradiction alerts, and scenario templates.
139 139  Humans still approve everything.
140 140  
... ... @@ -143,6 +143,7 @@
143 143  = Automation Matrix =
144 144  
145 145  == Always Human ==
136 +
146 146  * Final verdict approval
147 147  * Scenario validity
148 148  * Ethical decisions
... ... @@ -149,6 +149,7 @@
149 149  * Dispute resolution
150 150  
151 151  == Mostly AI (Human Validation Needed) ==
143 +
152 152  * Claim normalization
153 153  * Clustering
154 154  * Evidence metadata
... ... @@ -157,6 +157,7 @@
157 157  * Contradiction detection
158 158  
159 159  == Mixed ==
152 +
160 160  * Definitions of ambiguous terms
161 161  * Boundary choices
162 162  * Assumption evaluation
... ... @@ -169,6 +169,6 @@
169 169  
170 170  {{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
171 171  
172 -{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
165 +{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Level.WebHome"/}}
173 173  
174 174  {{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}