> 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.md).

# How to connect Workflows with...

### Overview

Birdie Workflows turn what your customers say into action where your teams already work: a comment on a Jira card, a new Linear issue, a report in a Slack channel, an Opportunity Solution Tree on a Miro board.

To do that, a workflow needs permission to act in those tools. This section explains, platform by platform, what to enable and which credential to create. Each article is written so you can **forward it as-is to the IT administrator** who manages that tool.

{% hint style="info" %}
This section is about **sending** insights and cards **out** of Birdie. To bring feedback **into** Birdie, see [How to integrate with...](/integrations-and-data-ingestion/how-to-integrate-with.md).
{% endhint %}

### Which platform do I need?

| Platform                                                                           | Used by workflows to                                  | Who sets it up                                    | Typical time |
| ---------------------------------------------------------------------------------- | ----------------------------------------------------- | ------------------------------------------------- | ------------ |
| [Slack](/integrations-and-data-ingestion/how-to-connect-workflows-with/slack.md)   | Post reports and ask for approvals in a channel       | A Slack admin (or anyone allowed to install apps) | 5 minutes    |
| [Jira](/integrations-and-data-ingestion/how-to-connect-workflows-with/jira.md)     | Read cards, comment with new evidence, create cards   | A Jira administrator                              | 10 minutes   |
| [Linear](/integrations-and-data-ingestion/how-to-connect-workflows-with/linear.md) | Read issues, comment with new evidence, create issues | A Linear workspace admin                          | 10 minutes   |
| [Miro](/integrations-and-data-ingestion/how-to-connect-workflows-with/miro.md)     | Draw the evidence as an Opportunity Solution Tree     | A Miro team admin                                 | 10 minutes   |

You only need the platforms your workflows use. Your Birdie contact will tell you which ones apply.

### What every article covers

* **What Birdie will do** – exactly which actions the workflow performs, so your security team can review them.
* **What you need** – the role or permission required to set it up.
* **Setup** – step-by-step in the third-party tool.
* **Connect to Birdie** – what to share and how.
* **Revoke or rotate** – how to cut access or replace the credential at any time.

### Principles that apply to all platforms

* **Use a dedicated "Birdie" account where the tool supports one.** Comments and cards then show clearly as coming from Birdie, and access can be revoked without affecting a person.
* **Least privilege.** Give access only to the project, team, board or channel the workflow works in.
* **Nothing is written during a dry run.** A new workflow first runs in dry-run mode: it reads and shows what it *would* do. It only comments, creates or posts after someone turns it live.
* **Credentials are stored encrypted** and are never displayed again once saved. See [Securely sharing credentials](/integrations-and-data-ingestion/securely-sharing-credentials-for-data-integration.md) for the safe ways to hand a secret over.


---

# 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.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.