> For the complete documentation index, see [llms.txt](https://api.docs.blockbrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://api.docs.blockbrain.ai/concepts/insight/contributing-knowledge.md).

# Contributing Knowledge

This guide explains how to use **Insights** to contribute durable knowledge to your organization’s knowledge base. Insights capture verified takeaways from conversations with provenance, making them ideal for publishing, indexing, and reuse across teams and systems.

#### Why contribute with Insights

* **Trustworthy summaries**: Curated, human-readable outputs with links back to sources and messages.
* **Reusable artifacts**: Portable across tools and teams (e.g., CRM, wiki, reporting, RAG indices).
* **Governed access**: Inherit conversation/bot permissions and sharing rules.

#### What you contribute

* **Titles and summaries** that encapsulate the knowledge.
* **Provenance** via message excerpts and document references.
* **Contextual metadata** (owner, timestamps, model used, curation flags).

### Contribution workflow

1. Generate or curate insights in a conversation
   * Use your agent/bot to synthesize key findings; refine as needed.
   * Select which insights should be connected to the data room.
2. Review selected insights
   * Validate title, summary, and provenance.
3. Enrich and normalize
   * Ensure the summary is self-contained and actionable.
   * Map metadata (owners, tags, categories) to your knowledge base schema.
4. Publish to knowledge destinations
   * Export to a wiki/portal (e.g., create pages with summary + references).
   * Index into search/RAG systems (store summary, embeddings, and doc refs).
5. Maintain and update
   * Pin, edit, or re-generate insights as understanding evolves.
   * Replace expired document refs by re-fetching insight details.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://api.docs.blockbrain.ai/concepts/insight/contributing-knowledge.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.