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 5.1
edited by Robert Schaub
on 2025/12/12 15:41
Change comment: Imported from XAR

Summary

Details

Page properties
Content
... ... @@ -4,12 +4,32 @@
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 +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 +
13 13  ----
14 14  
15 15  = Manual vs Automated Responsibilities =
... ... @@ -62,7 +62,6 @@
62 62  == POC (Low Automation) ==
63 63  
64 64  === Automated ===
65 -
66 66  * Claim normalization
67 67  * Light scenario templates
68 68  * Evidence metadata extraction
... ... @@ -69,7 +69,6 @@
69 69  * Simple verdict drafts (internal only)
70 70  
71 71  === Human ===
72 -
73 73  * All scenario definitions
74 74  * Evidence interpretation
75 75  * Verdict creation
... ... @@ -78,7 +78,6 @@
78 78  == Beta 0 (Medium Automation) ==
79 79  
80 80  === Automated ===
81 -
82 82  * Detailed scenario drafts
83 83  * Evidence reliability scoring
84 84  * Cross-scenario comparisons
... ... @@ -86,7 +86,6 @@
86 86  * Internal Truth Landscape drafts
87 87  
88 88  === Human ===
89 -
90 90  * Scenario approval
91 91  * Final verdict validation
92 92  
... ... @@ -93,7 +93,6 @@
93 93  == Release 1.0 (High Automation) ==
94 94  
95 95  === Automated ===
96 -
97 97  * Full scenario generation (definitions, assumptions, boundaries)
98 98  * Evidence relevance scoring and ranking
99 99  * Bayesian verdict scoring across scenario sets
... ... @@ -102,7 +102,6 @@
102 102  * AKEL-assisted federated synchronization
103 103  
104 104  === Human ===
105 -
106 106  * Final approval of all scenarios and verdicts
107 107  * Ethical decisions
108 108  * Oversight and conflict resolution
... ... @@ -112,19 +112,15 @@
112 112  = Automation Levels =
113 113  
114 114  == Level 0 — Human-Centric (POC) ==
115 -
116 116  AI is purely advisory, nothing auto-published.
117 117  
118 118  == Level 1 — Assisted (Beta 0) ==
119 -
120 120  AI drafts structures; humans approve each part.
121 121  
122 122  == Level 2 — Structured (Release 1.0) ==
123 -
124 124  AI produces near-complete drafts; humans refine.
125 125  
126 126  == Level 3 — Distributed Intelligence (Future) ==
127 -
128 128  Nodes exchange embeddings, contradiction alerts, and scenario templates.
129 129  Humans still approve everything.
130 130  
... ... @@ -133,7 +133,6 @@
133 133  = Automation Matrix =
134 134  
135 135  == Always Human ==
136 -
137 137  * Final verdict approval
138 138  * Scenario validity
139 139  * Ethical decisions
... ... @@ -140,7 +140,6 @@
140 140  * Dispute resolution
141 141  
142 142  == Mostly AI (Human Validation Needed) ==
143 -
144 144  * Claim normalization
145 145  * Clustering
146 146  * Evidence metadata
... ... @@ -149,7 +149,6 @@
149 149  * Contradiction detection
150 150  
151 151  == Mixed ==
152 -
153 153  * Definitions of ambiguous terms
154 154  * Boundary choices
155 155  * Assumption evaluation
... ... @@ -160,8 +160,8 @@
160 160  
161 161  = Diagram References =
162 162  
163 -{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Roadmap.WebHome"/}}
170 +{{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
164 164  
165 -{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Level.WebHome"/}}
172 +{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
166 166  
167 167  {{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}