Skip to Content

AKEL Triple-Path Architecture (v2.6.33)

Version 1.1 by Robert Schaub on 2026/01/20 21:40
Information

Current Implementation (v2.6.33) - Triple-Path Pipeline Architecture. Three pipeline variants share common modules for scope detection, aggregation, and claim processing.

Triple-Path Pipeline Architecture


graph TB
    subgraph Input[User Input]
        URL[URL Input]
        TEXT[Text Input]
    end

    subgraph Shared[Shared Modules]
        SCOPES[scopes.ts Scope Detection]
        AGG[aggregation.ts Verdict Aggregation]
        CLAIM_D[claim-decomposition.ts]
    end

    subgraph Dispatch[Pipeline Dispatch]
        SELECT{Select Pipeline}
    end

    subgraph Pipelines[Pipeline Implementations]
        ORCH[Orchestrated Pipeline]
        CANON[Monolithic Canonical]
        DYN[Monolithic Dynamic]
    end

    subgraph LLM[LLM Layer]
        PROVIDER[AI SDK Provider]
    end

    subgraph Output[Result]
        RESULT[AnalysisResult JSON]
        REPORT[Markdown Report]
    end

    URL --> SELECT
    TEXT --> SELECT
    SELECT -->|orchestrated| ORCH
    SELECT -->|monolithic_canonical| CANON
    SELECT -->|monolithic_dynamic| DYN
    SCOPES --> ORCH
    SCOPES --> CANON
    AGG --> ORCH
    AGG --> CANON
    CLAIM_D --> ORCH
    CLAIM_D --> CANON
    ORCH --> PROVIDER
    CANON --> PROVIDER
    DYN --> PROVIDER
    ORCH --> RESULT
    CANON --> RESULT
    DYN --> RESULT
    RESULT --> REPORT

Pipeline Variants

 Variant  File  Approach  Output Schema
 Orchestrated  orchestrated.ts  Multi-step workflow with explicit stages  Canonical (structured)
 Monolithic Canonical  monolithic-canonical.ts  Single LLM tool-loop call  Canonical (structured)
 Monolithic Dynamic  monolithic-dynamic.ts  Single LLM tool-loop call  Dynamic (flexible)

Shared Modules

 Module  Purpose
 scopes.ts  Heuristic scope pre-detection before LLM
 aggregation.ts  Verdict weighting, contestation validation
 claim-decomposition.ts  Claim text parsing and normalization

Orchestrated Pipeline Steps

  1. Understand - Detect input type, extract claims, identify dependencies
    2. Research (iterative) - Generate queries, fetch sources, extract facts
    3. Verdict Generation - Generate claim and article verdicts
    4. Summary - Build two-panel summary
    5. Report - Generate markdown report