From Conversation to Capability
The deep-dive companion to WS-08. How meeting transcripts become trustworthy memory — the resolution layer that turns raw talk into a knowledge asset, end-to-end. Three passes, two storage layers, one identity spine. 18 slides, 30 minutes.
- Without a resolution layer, every new raw document adds duplicates, conflicts, and ambiguities. The larger the pile, the faster the search index turns into a heap of garbage.
- Choose one pile to resolve. Do not build a 'company brain' overnight. Pick one folder — transcripts or a customer success log — and resolve it first.
- The deep-dive companion to WS-08. How meeting transcripts become trustworthy memory — the resolution layer that turns raw talk into a knowledge asset, end-to-end. Three passes, two storage layers, one identity spine. 18 slides, 30 minutes.
From Conversation to Capability
How meeting transcripts become trustworthy memory.
A summary is not memory.
'AI takes my notes' sounds solved. It isn't. A summary is localized and isolated. Memory must be unified.
Where the raw pile fractures.
These five failure modes are not limits of the LLM's model size. They are limits of the data structure. You cannot resolve entities at query-time.
More meetings.
Less trust.
Resolved entity memory holds the line.
Raw transcripts decay into a hallucination zone.
Data volume without metadata resolution
guarantees logical entropy.
One structure, two views.
How humans browse (Obsidian links) and how the machine reasons (ontology entities) are not competing systems. They are different projections of the exact same resolved logical structures. The resolution engine establishes entity types (Person, Decision, System, Commitment) under one strict ontology schema.
The resolution engine is the middle layer.
Do not let your LLM read raw files directly. You must insert a validation filter that cleans and structuralizes every object and name before writing to corporate memory. Raw audio is cheap. Clean, indexed facts are priceless.
The gatekeeper of truth.
The resolution layer is the logical gatekeeper sitting between raw transcription outputs and database memory. It enforces deterministic rules over unstructured text — the border between unstructured conversational noise and grounded factual storage.
Is it an attribute, or a relationship?
If you store 'Mike' as a string property inside a meeting record, it remains isolated. If you map it to stable entity ID per_0042, you can ask questions that traverse years of records instantly. A string is a dead end. A link is a path.
Three steps to a trusted database.
The pipeline is transactional: if Pass 2 fails to resolve and lacks human input, Pass 3 is suspended to protect database integrity. Strict isolation between candidate generation and data committing is a key architectural safety pattern.
Aliases resolve to a single ID.
Never let your search index get polluted by multiple records representing the same human being. The identity spine binds all historical and future names to a single, stable pointer. The foundation of a clear search index is standardizing human and system entities.
Grounded and human-readable.
YAML is perfect for identity logs. It is clean, declarative, natively parsed by modern LLMs, and simple for engineers and humans to read back and audit during data checks. Declarative structure blocks replace long natural text files.
Commitments need owners.
Mandatory constraint — action items must have both an assigned owner ID and target deadline. If either field is missing, the resolver flags a schema validation error. Logical temporal trace — decisions are strictly timestamped and carry explicit reference links to prior actions they modify or reverse.
Ask, don't guess.
If your pipeline is unsure, it shouldn't guess or choose blindly. Low-confidence matches drop into human verification queues. When answered, the system locks that rule forever. Uncertainty is processed as structured feedback, not silent failure.
Continuous logical linting.
Your database is a live organism. Just as software needs compilation checks and lint rules to verify code structure, knowledge graphs must continuously lint logic, contradictions, and orphaned entities. Continuous logical validation keeps corporate knowledge reliable.
How a meeting becomes memory.
Nothing is recorded until every name is known — or a person has answered. This is the core transactional pipeline. It ensures that no ambiguity is committed to global memory. The result is total factual consistency.
Raw archived. Resolved queried.
Golden rule: keep the raw forever; query the resolved. Linked by a shared key ID. Do not let your search system query long raw transcripts. Archive them as safe copies. Your production models query only the resolved entity nodes, protecting your budget and context. Separate the raw text history from the verified database representation.
The resolution payoff.
Factual consistency is the difference between a novel toy and an enterprise-grade platform. When entities are resolved, your database becomes a single source of reliable, queryable truth. From raw, unstructured conversations to reliable business capability.
Build capability from conversation.
- 1Choose one pile to resolve. Do not build a 'company brain' overnight. Pick one folder — transcripts or a customer success log — and resolve it first.
- 2Standardize the entity registry first. Compile a clean registry of names, roles, and legacy system codes. All files must bind to these keys. The registry is the foundation.
- 3Enable 'ask, don't guess' policies. When fuzzy matches fall below 0.90, halt automated entries and route to human feedback forms. Uncertainty is structured feedback, not silent failure.
- 4Ask the test question: 'When your AI is unsure, does it ask — or quietly pick one?' If the answer is the second, the rollout is not enterprise-ready.
Frequently Asked Questions
- What is the core idea of From Conversation to Capability?
- Without a resolution layer, every new raw document adds duplicates, conflicts, and ambiguities. The larger the pile, the faster the search index turns into a heap of garbage.
- What should a CEO do Monday morning after reading From Conversation to Capability?
- Start here: Choose one pile to resolve. Do not build a 'company brain' overnight. Pick one folder — transcripts or a customer success log — and resolve it first; Standardize the entity registry first. Compile a clean registry of names, roles, and legacy system codes. All files must bind to these keys. The registry is the foundation; Enable 'ask, don't guess' policies. When fuzzy matches fall below 0.90, halt automated entries and route to human feedback forms. Uncertainty is structured feedback, not silent failure.
- What are the steps in From Conversation to Capability?
- 1) Same person, multiple aliases; 2) Split company and system names; 3) Anonymous commitments; 4) Silent decision reversals; 5) Unverifiable claims.
- Where do the claims in From Conversation to Capability come from?
- The playbook cites Internal workshop source material.
Ready to turn your meeting transcripts into a trustworthy knowledge asset?
Company Brain implements the three-pass resolution layer — identity spine, storage split, and the commitment decision — end to end.