> For the complete documentation index, see [llms.txt](https://docs.mediafier.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mediafier.ai/platform/decision-tracing-and-learning-loop.md).

# Decision Tracing & Learning Loop

Every approval, override, and edit becomes searchable precedent; the learning loop proposes, humans approve.

> **Every approval, override, escalation, and edit becomes searchable precedent.** The Context Decision Graph is the platform's decision-memory layer; the Learning Loop is what turns that memory into compounding skill.

***

## Context Decision Graph

At commit time — the moment a person approves, overrides, escalates, or edits what an agent proposed — the platform captures the **why** alongside the **what**: the rationale, the policy that applied at the time, the approver, and the resulting action. That bundle of signals is the platform's decision-memory layer.

Decision nodes are append-only, immutable, and trace-correlated to the call that produced them. The highest-value nodes are the ones created at moments of human judgment — overrides and exceptions, where senior operators historically left their context only in their heads. Captured as searchable precedent, that judgment becomes shared institutional knowledge.

***

## Learning Loop

The Learning Loop reads completed runs and the decision-memory layer and surfaces patterns worth promoting. Every output is a **proposal**. Proposals are reviewed and validated before they become active, and a human approves them.

The Learning Loop **does not** modify model weights. It does not fine-tune. The model is whichever foundation model the team has chosen; the Learning Loop changes only the **library** of governed skills and the **directives** that wrap their use.

***

## What this gives operators

| Question an operator used to answer manually   | What the Decision Graph + Learning Loop gives them  |
| ---------------------------------------------- | --------------------------------------------------- |
| "Has anyone approved a case like this before?" | Searchable precedent across the org.                |
| "Why did the agent pick this tool?"            | The decision node trace for the call.               |
| "How is the agent getting better?"             | A reviewable list of promoted heuristics over time. |

***

## What stays out of bounds

* **Customer data leaving the tenant.** Decision nodes and Evidence Cards are org-scoped. Cross-tenant precedent is not exposed.
* **Autonomous skill promotion.** The Learning Loop proposes; humans approve. A proposed change does not affect production output until it is approved.
* **Model fine-tuning.** Changes are recorded in the skill library and directives; they are not pushed back to model weights.

***

## Where to go next

For what operators see day to day, read [Agent Operations](/platform/agent-operations.md); for what stays inside your organization, read [Learning & Data Boundaries](/trust/learning-and-data-boundaries.md).

## Related pages

| If you're…                                                 | Read next                                                                         |
| ---------------------------------------------------------- | --------------------------------------------------------------------------------- |
| Looking for the MediaClaw container that produces evidence | [MediaClaw Super-Agents](/platform/mediaclaw-super-agents.md)                     |
| Looking for the Media Library this layer reads from        | [Media Library](/platform/media-library.md)                                       |
| Studying audit, observability, and compliance posture      | [Audit, Observability & Compliance](/trust/audit-observability-and-compliance.md) |
| Studying the discovery model for decision-node surfaces    | [Governed Resources & Discovery](/platform/governed-resource-substrate.md)        |