AKEL — AI Knowledge Extraction Layer

AKEL is FactHarbor’s automated intelligence subsystem.  
Its purpose is to reduce human workload, enhance consistency, and enable scalable knowledge processing — without ever replacing human judgment.

All AKEL outputs are marked with AuthorType = AI and require human approval before publication.

AKEL operates in two modes:

• Single-node mode (POC & Beta 0)
• Federated multi-node mode (Release 1.0+)

Human reviewers, experts, and moderators always retain final authority.

Purpose and Role

AKEL transforms unstructured inputs into structured, review-ready drafts.

Core responsibilities:

• Claim extraction from arbitrary text
• Claim classification (domain, type, evaluability, safety)
• Scenario generation (definitions, boundaries, assumptions, methodology)
• Evidence summarization and metadata extraction
• Contradiction detection
• Re-evaluation proposal generation
• Cross-node embedding exchange (Release 1.0+)

Components

• AKEL Orchestrator – central coordinator
• Claim Extractor
• Claim Classifier
• Scenario Generator
• Evidence Summarizer
• Contradiction Detector
• Embedding Handler (Release 1.0+)
• Federation Sync Adapter (Release 1.0+)

Inputs and Outputs

Inputs

• User-submitted claims or evidence  
• Uploaded documents  
• URLs or citations  
• External LLM API (optional)  
• Embeddings (from local or federated peers)

Outputs (all require human approval)

• ClaimVersion (draft)  
• ScenarioVersion (draft)  
• EvidenceVersion (summary + metadata draft)  
• VerdictVersion (draft; internal only)  
• Contradiction alerts  
• Re-evaluation proposals  
• Updated embeddings

Architecture Overview

AKEL Architecture

graph TB
 User[User Submits Content
Text/URL/Single Claim]
 Extract[Claim Extraction
LLM identifies distinct claims]
 AKEL[AKEL Core Processing
Per Claim]
 Evidence[Evidence Gathering]
 Scenario[Scenario Generation]
 Verdict[Verdict Generation]
 Storage[(Storage Layer
PostgreSQL + S3)]
 Queue[Processing Queue
Parallel Claims]
 
 User --> Extract
 Extract -->|Multiple Claims| Queue
 Extract -->|Single Claim| AKEL
 Queue -->|Process Each| AKEL
 
 AKEL --> Evidence
 AKEL --> Scenario
 Evidence --> Verdict
 Scenario --> Verdict
 Verdict --> Storage
 
 style Extract fill:#e1f5ff
 style Queue fill:#fff4e1
 style AKEL fill:#f0f0f0

AKEL and Federation

In Release 1.0+, AKEL participates in cross-node knowledge alignment:

• Shares embeddings  
• Exchanges canonicalized claim forms  
• Exchanges scenario templates  
• Sends + receives contradiction alerts  
• Never shares model weights  
• Never overrides local governance

Nodes may choose trust levels for AKEL-related data:

• Trusted nodes: auto-merge embeddings + templates  
• Neutral nodes: require reviewer approval  
• Untrusted nodes: fully manual import

Human Approval Workflow

1. AKEL generates draft outputs (AuthorType = AI)  
   2. Reviewers inspect and approve/moderate the drafts  
   3. Experts validate high-risk or domain-specific outputs  
   4. Moderators finalize publication  
   5. Version numbers increment, history preserved

No AKEL output is ever published automatically.