How to automate issue metadata with GitHub issue intents

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: How to automate issue metadata with GitHub issue intents · Channel: GitHub · 03:20 · Watch on YouTube

Topics: AI agents, Task and workflow automation

Summary

Issue intent automates issue metadata while giving maintainers control over what changes are applied. Suggestions include a confidence level and rationale, and maintainers can accept or decline them individually or all at once. Repository settings offer automation levels, including a balanced option that automatically applies routine, clear-cut changes. The video shows how to configure issue intent in an agent workflow and inspect its recommended actions and results in GitHub Actions.

Key points

Use the “has suggestions” filter to find issues with pending issue intent suggestions.
Each suggestion includes a confidence level and reasoning.
Maintainers can accept or decline suggestions individually, or accept all.
Automation levels in repository settings let maintainers choose how much control to retain.
The balanced level automatically applies routine, clear-cut changes.
The example workflow classifies issues, suggests a priority, and includes a short rationale.
Setting issue intent to true for the safe output actions requires the agent to provide a rationale and confidence level.
GitHub Actions shows which safe outputs were recommended and whether they succeeded.
Issue intent can also be used with Copilot Cloud Agent Automations or custom agents using supported GitHub MCP, REST, or GraphQL capabilities.

Chapters

Start	Chapter	Summary
00:00	Reviewing and managing issue intent suggestions	The video introduces issue intent and demonstrates how to find suggestions and accept or decline them.
00:34	Choosing an automation level	The presenter switches the repository setting to balanced and reruns the issue workflow to trigger automation.
01:39	Configuring the agent workflow	The example workflow uses natural-language instructions, triggers, permissions, tools, and safe outputs to classify issues and suggest a priority.
02:16	Inspecting safe outputs and issue intent	The presenter explains how setting issue intent to true requires rationale and confidence, then inspects workflow recommendations and results.
02:46	Reviewing results and other agent options	The workflow output shows confidence and rationale for both actions, and the video notes other ways to use issue intent.

Quotes

To answer this exact pain point, we shipped issue intent. — 00:00

I’m going to switch to balanced, which applies routine clear-cut changes automatically. — 00:34

And ours is just three steps to classify the issue, suggest a priority, and include a short rationale. — 01:39

we are setting issue intent to true — 02:16

This is just one example of the many tasks that issue intent can help you automate. — 03:20

Concepts and entities

issue intent, GitHub, GitHub Actions, Agentic workflows, Copilot Cloud Agent Automations, GitHub MCP, safe outputs, REST, GraphQL

Full transcript (original language)

00:00 As a maintainer, you know that keeping incoming issues up to date when it comes to metadata can be tedious work. We can of course use agents to help us automate this, but how do we manage control with agency? How do we find that right balance? To answer this exact pain point, we shipped issue intent. Let me show you how it works. In the issues tab, we can use the has suggestions filter in order to view issues that have pending issue intent suggestions. I’ll open this issue up here and we can see for the suggestions, we have a confidence level and a reasoning. And we can also accept or decline each

00:34 suggestion individually, or we can accept all up here. In our repository settings under planning, the current automation level is set to full control, meaning no suggestions will be auto applied. And you can begin at this level or at the cautious level and then change as your trust in the automations grow. I’m going to switch to balanced, which applies routine clear-cut changes automatically. Let’s hit save. And now let’s return to that same issue. I’ll close it and reopen it so we can trigger the automation again. Great, the

01:07 workflow for our triage new issues has completed. Let’s revisit the issue and see what has changed. I’ve got the issue open. I’m going to scroll down and we can see that GitHub Actions added the bug label. We hover over the information icon, it says the report describes inconsistent existing behavior across pages, not a new capability request, which is the reasoning as to why that was applied. And then we have the low priority set here. And here it says the impact is limited to annoying UX inconsistency with no stated functional blocker. So we can see that our issue intent automation has worked. But how

01:39 did we set this up, you may ask? Well, let’s take a look at that right now. For our example, we used a GitHub Agentech workflow, which as you can see, allow us to create automations using natural language in markdown. And ours is just three steps to classify the issue, suggest a priority, and include a short rationale. Up top, we have the workflows front matter, and here is where we define the triggers. So, in our case, when an issue is opened or reopened, permissions that our workflow has, the tools, and the safe outputs, which are

02:16 the recommended actions a workflow can conclude with. And the secret sauce is in here. So, for both the set issue type and set issue field actions, we are setting issue intent to true, which means that we need to make sure the agent provides a rationale and confidence level for these actions to be done. We can now take [clears throat] a look at the last run of that workflow in our actions tab. I will scroll down, and I’m going to expand the safe outputs

02:46 under the agent summary, and we can see indeed that both set issue type and set issue field were recommended for the workflow to conclude with. If I scroll down and load the summary of safe outputs, we can see that both the set issue type was success and set issue field, and those were applied to that issue that I reopened 897. I’ve clicked on the agent job, and I’ve expanded in just agent output, and here is exactly where we can see what issue intent set to true provides. We have that confidence and rationale, and we

03:20 have it for both of the safe outputs. So, set issue type and set issue field. For our demo, we use the agent workflows, but you can leverage Copilot Cloud Agent Automations or build your own custom agents using supported GitHub MCP REST or GraphQL capabilities. This is just one example of the many tasks that issue intent can help you automate. I’ll make sure to link docs with all the information that you will need, and please let us know any feedback that you have.