Wiki source code of Manual vs Automated Matrix

Last modified by Robert Schaub on 2026/02/08 08:31

Show last authors
1 {{info}}
2 **Design Philosophy** - This matrix shows the intended division of responsibilities between AKEL and humans. v2.6.33 implements the automated claim evaluation; human responsibilities require the user system (not yet implemented).
3 {{/info}}
4
5 = Manual vs Automated Matrix =
6
7 {{mermaid}}
8
9 graph TD
10 subgraph Automated[Automated by AKEL]
11 A1[Claim Evaluation]
12 A2[Quality Assessment]
13 A3[Content Management]
14 end
15 subgraph Human[Human Responsibilities]
16 H1[Algorithm Improvement]
17 H2[Policy Governance]
18 H3[Exception Handling]
19 H4[Strategic Decisions]
20 end
21
22 {{/mermaid}}
23
24 = Automated by AKEL =
25
26 |= Function |= Details |= Status
27 | **Claim Evaluation** | Evidence extraction, source scoring, verdict generation, risk classification, publication | Implemented
28 | **Quality Assessment** | Contradiction detection, confidence scoring, pattern recognition, anomaly flagging | Partial (Gates 1 and 4)
29 | **Content Management** | KeyFactor generation, evidence linking, source tracking | Implemented
30
31 = Human Responsibilities =
32
33 |= Function |= Details |= Status
34 | **Algorithm Improvement** | Monitor metrics, identify issues, propose fixes, test, deploy | Via code changes
35 | **Policy Governance** | Set criteria, define risk tiers, establish thresholds, update guidelines | Not implemented (env vars only)
36 | **Exception Handling** | Review flagged items, handle abuse, address safety, manage legal | Not implemented
37 | **Strategic Decisions** | Budget, hiring, major policy, partnerships | N/A
38
39 = Key Principles =
40
41 **Never Manual:**
42 * Individual claim approval
43 * Routine content review
44 * Verdict overrides (fix algorithm instead)
45 * Publication gates
46
47 **Key Principle:** AKEL handles all content decisions. Humans improve the system, not the data.