> For the complete documentation index, see [llms.txt](https://ask.birdie.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ask.birdie.ai/integrations-and-data-ingestion/how-to-connect-workflows-with/miro.md).

# Miro

{% hint style="warning" %}
The Miro output is rolling out. The steps below describe the intended setup; your Birdie contact will confirm each step with you during onboarding.
{% endhint %}

### Overview

A workflow can draw the customer evidence behind a card as an **Opportunity Solution Tree** on a Miro board, next to (or instead of) writing the report link back to Jira or Linear.

Birdie creates **one board for the workflow**. Every run adds to that board: each card gets its own framed cluster, and when the same card receives new evidence its cluster is redrawn in place, so the board always shows the latest picture.

### What Birdie draws

| Column        | What it shows                                                    |
| ------------- | ---------------------------------------------------------------- |
| Outcome       | What customers were trying to do                                 |
| Opportunities | Where it breaks, and where support falls short                   |
| Solutions     | What customers asked for, under the opportunity each ask answers |
| Evidence      | Customer quotes, under the opportunity they support              |

### What Birdie will do

* Create the workflow's board in the Miro team you choose (once).
* Add, update and remove **only the frames it created** on that board.
* Birdie does not read or change any other board.

Edits you make inside a Birdie-drawn cluster are replaced the next time that card gets new evidence. Notes and boards you create yourself are never touched.

### Requirements

* A Miro team where the board should live.
* A Miro team admin (or someone allowed to approve apps) in that team.
* A Miro user that will own the boards Birdie creates. We recommend a dedicated `Birdie` user, a member of that team.

### Setup

{% stepper %}
{% step %}

### Allow the Birdie app in your Miro team

A team admin approves the Birdie app in the team. It requests two permissions: **read boards** and **write boards**. If your organisation restricts third-party apps, add Birdie to the allowed list under the team's app settings.
{% endstep %}

{% step %}

### Choose the team and the owner

* Decide which Miro team will hold the board and which user will own it.
* Tell your Birdie contact the **team** and, if you want a specific name, the **board name**. By default the board is named after the workflow.
  {% endstep %}

{% step %}

### Authorise the connection

Your Birdie contact will start the sign-in with Miro. The Miro user who owns the boards approves it once. No token needs to be copied or shared.
{% endstep %}
{% endstepper %}

### Revoke or rotate

* In Miro, remove the Birdie app from the team's installed apps. Workflows stop drawing immediately; the board and its content stay yours.
* To reconnect, repeat the authorisation step.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://ask.birdie.ai/integrations-and-data-ingestion/how-to-connect-workflows-with/miro.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
