> ## Documentation Index
> Fetch the complete documentation index at: https://docs.laneapp.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Automations

> Hand recurring product work to Lane. It checks your feedback, customers and tools on a schedule or when something changes, and tells your team what matters.

A lot of valuable product work is also easy to skip: reading what changed in feedback before Monday planning, checking whether customers actually asked for the thing engineering is about to start, noticing when a competitor ships what your biggest accounts requested. Automations turn those habits into jobs Lane does for you.

You describe the job once, in plain words. Lane runs it on a schedule or the moment something changes, with your feedback, customers, Signals, Opportunities and priorities in hand, and sends the result to Slack or email. Every run remembers the ones before it, so you hear what changed, not the same summary again.

Find them under **Automations** in the sidebar. They're available on every plan. Contributors don't see Automations.

## What teams use them for

* **A weekly read before planning.** What's rising, what's fading, and where customer demand is drifting from your priorities, waiting in your inbox or Slack channel on Monday morning.
* **A check before building.** When an issue moves into progress in Linear, Lane weighs the evidence behind it (who asked, the revenue behind them, how it fits your priorities) and comments on the issue, so the team doesn't build something nobody asked for.
* **Competitor tracking.** Lane watches for competitor launches and tells you which of your customers asked for the same thing.
* **Release notes that close the loop.** When a pull request merges, Lane drafts the release notes as a [Doc](/docs), linked to the customers who asked for the change.
* **Docs that keep up.** With Mintlify connected, Lane proposes updates to your docs as pull requests when the product changes.

## Create an automation

1. Open **Automations** and choose **New automation**.
2. Start from a template to get going quickly, or choose **Start from scratch**.
3. Write the **Instructions**, then choose when it runs, which tools it can use, and where results go.
4. Choose **Run now** to see a result. When it looks right, switch it from **Paused** to **Active**.

New automations start paused, so nothing runs until you're ready. Changes save as you make them.

## When it runs

* **On a schedule**: daily or weekly, at the time and time zone you choose.
* **When something changes**: when a Linear issue's status changes (narrowed to certain teams or statuses if you like), or when a pull request merges in GitHub (narrowed to a base branch, such as `main`).
* **On demand**: **Run now** starts it any time, even while it's paused.

Event runs start right away. If several changes land while a run is going, Lane handles them together in the next run. A trigger needs its app connected under **Settings → Integrations** before it can fire.

## Instructions

Write what the agent should do on each run the way you'd brief a teammate: what to look at, what to compare, and what a useful result looks like. For example: "List the three Signals that grew most this week, the customers behind each, and anything that contradicts our current priorities."

Because the automation remembers its earlier runs, instructions like "tell me what changed since last week" work as you'd expect. Type **/** to add a skill, a set of steps your team saved in **Settings → Skills**, so every run follows the same method.

## Connectors

On its own, an automation works with your Lane data. Connectors let it look further: code and pull requests in **GitHub**, issues in **Linear**, your docs in **Mintlify**, pages in **Notion**, and product usage in **PostHog**. An app must be connected in Lane before an automation can use it.

Each connector is **Read only** or **Read and write**. With **Read and write**, Lane makes changes without asking: it can comment on or update Linear issues, create or update Notion pages, and open docs pull requests in Mintlify. Turn it on only when the job needs it; each run makes only a small number of changes per app.

* **Notion** uses the Notion account of the person who created the automation, since Notion connections are personal.
* **Mintlify** changes arrive as pull requests. Nothing is published until someone merges them.
* **GitHub** and **PostHog** are read only.

## What an automation can change in Lane

Setting up an automation is your approval, so it doesn't stop to ask before acting. Inside Lane, a run can:

* Create [Docs](/docs), shown in the Docs list as made by Lane
* Rewrite or rename the Docs it created, and add to other Docs
* Create or update [Opportunities](/opportunities)
* Save new feedback when your instructions ask, for example from a Slack thread or a connected app, in the customer's own words
* Create Signals from [Evidence](/signals#highlights-and-evidence) when your instructions ask

It never edits existing Signals or feedback, and never deletes anything.

## Where results go

Under **Notify**, choose **+ Add channel**:

* **Email**: sends each result to the members you pick.
* **Slack**: posts each result to a channel. Slack needs to be connected under **Settings → Integrations**; see [Slack](/slack).

Notify is optional: every result is also kept on the automation's **Runs** tab. Only successful runs are sent, and each message ends with what Lane changed during that run.

## Advanced

* **Web search** lets the automation search and read the public web, which is what makes competitor tracking work. It's off by default.
* **Model** sets how much thinking a run gets: a faster model for straightforward jobs, a stronger one for weighing evidence or making judgement calls. New automations start on the fastest.

## Runs and credits

The **Runs** tab is the automation's history. Open a run to see whether it succeeded, the result, where it was delivered, the steps it took, and the credits it used.

Runs use AI credits from your workspace balance, and web search uses more. If there aren't enough credits when a run is due, it's skipped at no cost. See [Billing](/billing).

## Your first automation

New workspaces start with a weekly Opportunities brief, already switched on and emailed to the person who created the workspace. Edit it, pause it or delete it like any other automation.

## FAQs

**Q: Does an automation ask before it changes something?**<br />A: No. Choosing **Read and write** for a connector, or letting it create Docs and Opportunities, is the approval. Keep connectors on **Read only** unless the job needs to make changes.

**Q: Can I run it without waiting for the schedule?**<br />A: Yes. **Run now** works any time, even while the automation is paused.

**Q: Why was a run skipped?**<br />A: The workspace didn't have enough AI credits when it was due. Skipped runs cost nothing.

**Q: What happens when I delete an automation?**<br />A: Its run history and its memory of earlier runs are deleted too. This can't be undone.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.