meeting-lab/ROADMAP.md

Roadmap

No dates are assigned. Phases describe dependency order, not release promises.

Phase 1 - Stable Local Extraction

Goal:

• Establish reliable per-chunk extraction behavior for core meeting semantics.

Deliverables:

• Stronger Gold Standard coverage across facts, positions, decisions, todos, questions and technical details.
• Gold coverage for responsibility attribution: discussion, objection, role proximity and department mention must not become ownership.
• Improved category prompts.
• Repeatable evaluation workflow.
• Documented prompt experiment log.

Prerequisites:

• Existing chunk extraction flow.
• Existing Gold Standard runner and methodology.

Out of scope:

• Full-transcript LLM extraction.
• Larger context-window strategy changes without an explicit experiment.
• Canonicalization, semantic consolidation or final protocol rendering.

Phase 2 - Deterministic Canonicalization

Goal:

• Convert independent chunk extraction JSON into a validated, normalized, evidence-bearing intermediate representation without semantic guessing.

Deliverables:

• Canonicalizer V1 implemented in Python.
• Stable source references and IDs.
• Normalized category names and basic field structure.
• Safe deterministic cleanup.
• Exact duplicate grouping where unambiguous.
• Preservation of all source evidence.

Prerequisites:

• Stable local extraction baseline.
• Agreement on the extraction object shape that should be canonicalized.

Current status:

• Implemented as meeting_lab.consolidation.canonicalize.

Out of scope:

• Uncertain semantic merging.
• Topic synthesis.
• Protocol writing.
• LLM calls.

Phase 3 - Semantic Consolidation

Goal:

• Merge canonicalized extraction objects into a coherent semantic meeting representation while preserving evidence and uncertainty.

Deliverables:

• Semantic Consolidator V0 using the local LLM for facts-only duplicate detection.
• Semantically equivalent fact statement merging.
• Evidence preserved from all contributing chunks.
• Complete source fact coverage validation.
• Later broader semantic consolidation with topic grouping, contradiction and uncertainty markers, durable/transient separation and Canonical Meeting Knowledge preparation.

Prerequisites:

• Canonicalizer V1 output with stable IDs and source references.
• Gold or benchmark cases that expose duplication and category shifts.

Current status:

• Semantic Consolidator V0 is implemented and experimentally validated for facts-only conservative merging.
• The first accepted benchmark merged one correct pair among 33 facts and left 31 singleton groups.

Out of scope:

• Direct protocol writing.
• Topic synthesis in V0.
• Processing decisions, action items, questions, positions or technical details in V0.
• Canonical Meeting Knowledge generation in V0.
• Deriving output views from one another.
• Retrieval or RAG integration.

Phase 4 - Canonical Meeting Knowledge

Goal:

• Define and implement the semantic intermediate model that becomes the source of truth for downstream outputs.

Deliverables:

• Canonical Meeting Knowledge schema.
• Source evidence and traceability fields.
• Clear distinction between durable knowledge and meeting-specific actions.
• Migration path from consolidated extraction JSON into the canonical model.

Prerequisites:

• Semantic consolidation behavior that preserves evidence and uncertainty.
• Agreement on required semantic categories.

Out of scope:

• GUI.
• Export formats beyond those needed to validate the model.
• Knowledge-system storage design.

Phase 4A - Meeting Context V2 and Entity Registry

Goal:

• Replace primarily manual Meeting Context authoring with an interactive entity confirmation workflow backed by a persistent Entity Registry.

Accepted architecture:

Whisper
    ↓
Entity Detection
    ↓
User Confirmation
    ↓
Entity Registry Update
    ↓
Meeting Context Builder
    ↓
meeting_context.yaml
    ↓
Extraction Pipeline

Deliverables:

• Persistent Entity Registry independent from individual meetings as the cross-meeting knowledge source for confirmed entities, aliases and organizational metadata.
• Stable internal entity IDs for people, organizations, departments, products, projects, locations and abbreviations.
• First-class aliases, including spelling and transcription variants.
• User confirmation UI/workflow for unknown names.
• Meeting Context Builder that produces meeting-specific meeting_context.yaml from registry entries, user confirmations and meeting metadata.
• Generated meeting_context.yaml as the authoritative meeting-specific Point of Truth and reproducible input artifact for each meeting run.
• Similarity suggestions for spelling variants, Whisper variants, umlaut handling and OCR-like mistakes.

Prerequisites:

• Agreement on the Entity Registry data model.
• Review workflow for confirming unknown entities after Whisper transcription.
• Meeting Context V1 remains the extraction interface until V2 is implemented.

Current status:

• Accepted Architecture.
• Implementation deferred.

Out of scope:

• Autonomous learning.
• Silent registry updates.
• Registry overrides of explicit meeting-specific confirmations.
• Silent changes to historical Meeting Context after Registry updates.
• Inferring responsibility, decisions, ownership or attendance from registry metadata.

Phase 5 - Output Views

Goal:

• Render purpose-specific outputs from Canonical Meeting Knowledge without changing meaning.

Deliverables:

• Working Protocol / Arbeitsprotokoll renderer.
• Distribution Protocol / Verteilerprotokoll renderer.
• Knowledge Objects / Wissensdatenbankeintrag renderer or structured export.
• Later additional views such as action lists.
• Tests or checks showing that output views are parallel renderings of the same canonical model.
• Default output-language policy: rendered protocols normally match the dominant source language unless explicitly requested otherwise.

Prerequisites:

• Implemented Canonical Meeting Knowledge.
• Clear audience and completeness rules for each output view.

Out of scope:

• Additional analysis during rendering.
• Deriving one output view from another.
• Retrieval integration.

Phase 6 - Review and Quality Control

Goal:

• Add optional review stages that improve omission detection, consistency and model selection.

Deliverables:

• Optional whole-transcript review.
• Omission detection.
• Consistency checks.
• Model comparison workflow.
• Hardware and runtime benchmarks.

Prerequisites:

• Stable extraction, semantic consolidation and canonical model.
• Representative test meetings.

Out of scope:

• Automatic acceptance of review suggestions without evidence.
• Product UI work.
• Cloud deployment.

Phase 7 - Productization

Goal:

• Turn the validated pipeline into a usable local workflow.

Deliverables:

• Recording/transcription workflow.
• FFmpeg integration.
• Meeting metadata capture.
• Participant entry.
• Meeting Context V1 exists as a manually maintained YAML structure with validation, optional extraction prompt integration and extraction provenance; future work should add GUI entry and conservative integration with later pipeline stages.
• GUI.
• Stable deployment process.
• Export workflows.

Prerequisites:

• Stable pipeline stages and output views.
• Clear operational requirements for local use.

Out of scope:

• Enterprise knowledge retrieval.
• Future Meeting Assistant integration beyond export contracts.
• Cloud-first architecture.

Phase 8 - Knowledge-System Integration

Goal:

• Reuse durable meeting knowledge in broader knowledge systems.

Deliverables:

• Structured Knowledge Objects.
• Retrieval-ready storage format.
• Future RAG integration path.
• Reuse contracts for Meeting Assistant and other knowledge systems.

Prerequisites:

• Canonical Meeting Knowledge and Knowledge Objects are implemented and stable.
• Durable knowledge is separated from meeting-specific actions and discussion history.

Out of scope:

• Building a full enterprise search product inside Meeting Lab.
• Treating raw transcripts or generated protocols as the knowledge source of truth.