# TTC-118 — Context, retrieval, visible memory, and model-weight fine-tuning

Context is what the model can use now; retrieval selects external material into that context; visible memory is persistent owner-controlled information; fine-tuning changes model parameters through training.

Level: advanced · Version: 1.0.0 · Last reviewed: 2026-10-03
Review status: reviewed

## Learning outcome
Choose among context, retrieval, visible memory, and fine-tuning for a problem and justify the choice using persistence, provenance, freshness, and evaluation needs.

## Explanation
These mechanisms solve different problems. Put task instructions and necessary facts in current context. Use retrieval when a larger, changing, attributable collection must be searched and selected for each task. Store a reviewed preference, rule, correction, or history as visible memory, then deliberately retrieve or load it when relevant. Consider fine-tuning only when a representative dataset and evaluation justify changing recurring behavior in a separately versioned model or adapter. Retrieval can return wrong passages; memory can be stale; context can omit key material; fine-tuning does not provide a reliable factual database. Uploading documents, chatting, or editing files does not by itself fine-tune model weights.

## Worked fictional example
Fictional case: a museum's one-time exhibit question uses context; its changing catalog uses retrieval with citations; an approved house-style correction becomes visible memory; a proposal to fine-tune tone is deferred until enough licensed examples and held-out tests exist. None of the first three changes model weights.

## Reusable exercise
Sort eight fictional needs into context, retrieval, visible memory, fine-tuning, or a combination. Include a current policy, one-time calculation, durable preference, style behavior, deletion request, conflicting source, frequently changing fact, and rare edge case. State persistence, update, provenance, and test plan for each.

## Observable success criteria
- Each choice correctly states where information lives and how it reaches the model for a response.
- The learner explicitly states that files, retrieval, and visible memory do not themselves update model weights.
- The design includes freshness, deletion or replacement, provenance, and evaluation appropriate to the mechanism.

## Limitations
- Real systems combine mechanisms and may use product-specific terms; inspect actual architecture and provider behavior.
- Fine-tuning can change behavior unpredictably and retrieval quality depends on indexing, query, permissions, and source quality.

## Next review
Provider behavior, product architecture, or terminology changes any mechanism's truthful persistence or update path.; A cited primary source is materially revised, replaced, or becomes unavailable.; Repeated learner results show that the exercise or success criteria are ambiguous.

## Copyable material
```text
# TTC-118 — Context, retrieval, visible memory, and model-weight fine-tuning
Objective: Use the mechanism that matches the task's freshness, persistence, provenance, and behavior needs.
Procedure: Use context for now, retrieval to select from external knowledge, visible memory for inspectable durable records, and fine-tuning only for evaluated parameter training.
Required evidence: Document storage location, selection path, source, version, update or deletion method, and mechanism-specific tests.
Boundaries: Never claim that chats, uploads, retrieval, or memory changed model weights; no mechanism guarantees truth.
Completion test: A reviewer can trace what persisted, what entered this context, and whether any identified trained model changed.
Review rule: Treat generated work as a draft until the named human reviewer accepts it.
```

## Primary sources
- Neural Information Processing Systems Foundation: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks — https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html
- Proceedings of Machine Learning Research: Parameter-Efficient Transfer Learning for NLP — https://proceedings.mlr.press/v97/houlsby19a.html
- National Institute of Standards and Technology: Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile — https://www.nist.gov/publications/artificial-intelligence-risk-management-framework-generative-artificial-intelligence

Canonical URL: https://teachthecompany.com/school/context-retrieval-memory-and-fine-tuning/
Related established guide: https://teachthecompany.com/agent-memory/