Connectors

/

GitHub

/

Close GitHub issues for fixed Bugsnag errors
Write
Cross-Connector

Close GitHub issues once their Bugsnag errors are fixed

For engineering and project leads whose backlog overstates what is broken, who want fixed errors closed out by their AI assistant.

Try PopdockAI free
Get a live demo
Close GitHub issues for fixed Bugsnag errors
Close any GitHub issues for errors marked fixed in the Contoso Web Bugsnag project in the last 14 days.
3 errors marked fixed in Contoso Web still have an open GitHub issue. - #231: TypeError in CartSummary, assigned to Jordan Lee - #227: Timeout in checkout API, unassigned - #219: Null reference in profile page, assigned to Sam Patel Which of these should I comment on and close?
GitHub
Sample figures. Your results come from your own account.
bugsnag-get-error
github-get-issue
github-add-issue-comment
github-update-issue

On this page

The problem

The problem

The prompt

Who it's for

How it works

Tools used

Connector

GitHub

GitHub
Run it on your own GitHub data.

Connect GitHub, pick your AI tool and paste the prompt.

Try PopdockAI free

The problem

Fixed errors leave open issues behind

Errors get marked fixed in Bugsnag while their GitHub issues stay open, so the backlog overstates what is broken. Closing by hand means matching each error to its issue, and a loose title match closes the wrong one.

Without PopdockAI

  • List fixed errors in Bugsnag
  • Search GitHub for each one's issue
  • Close issues that only look similar
  • Leave the rest open

With PopdockAI

  • Errors marked fixed in your window are listed
  • Open issues are matched only by the exact error id in the title
  • You choose which pairs to close
  • Each gets a comment with the Bugsnag link, then is closed

The prompt

Use this prompt

Copy it into any AI tool connected to PopdockAI. Swap the values in braces for your own.

Prompt
**Objective:** For the Bugsnag project `{project-name}`, find errors marked fixed in the last `{lookback-days}` days (default 14) whose GitHub issue is still open, and close those issues with a comment once the user confirms.

**Step 1: List fixed errors in Bugsnag**

Call `bugsnag-get-error` with `project-name` set to `{project-name}`, `status` set to fixed, and `last-seen.from` set to `{lookback-days}` days before today. Record error-id, error-class, message, last-seen-date and error-url.

**Step 2: Find their issues on GitHub**

For each error, call `github-get-issue` with `title.contains` set to the error-id and `status` set to open. Keep only issues whose title contains `[Bugsnag <error-id>]`. Do not fall back to matching by error-class here: closing an issue on a fuzzy match is how the wrong issue gets closed.

**Step 3: Confirm**

Show a table of the pairs: error-class, error-id, last-seen-date, issue-number, issue title, assignee. Ask the user which to close (all, some, or none). Wait for an explicit answer.

**Step 4: Close the confirmed issues on GitHub**

For each confirmed issue, in this order:

1. Call `github-add-issue-comment` with `issue-number` and a `body` saying the error was marked fixed in Bugsnag, with its error-url and last-seen-date.
2. Call `github-update-issue` with `issue-number` and `state` set to closed. Pass nothing else, so no other field changes.

**Step 5: Report**

The issues closed, the ones skipped, and any failures.

**Rules & Guidelines:**

* `bugsnag-get-error` is on the bugsnag server. `github-get-issue`, `github-add-issue-comment` and `github-update-issue` are on the github server.
* The only write tools this prompt may call are `github-add-issue-comment` and `github-update-issue`, and only for the issues the user confirmed. Do not call any Bugsnag Action tool, such as `bugsnag-open-error` or `bugsnag-fix-error`, and do not call `github-lock-issue`.

**Validation:**

* If no errors were fixed in the window, say so and stop.
* If a fixed error has no open issue, it needs nothing; count it but do not list it.
* If the comment succeeds but the close fails, report the issue as commented and still open. Do not post the comment again on retry.

Who it's for

One answer, three teams that use it

Project managers

Keep the backlog honest

Issues for fixed errors are closed with a note, so the open count means something.

Close GitHub issues for Bugsnag errors fixed in the Fabrikam API project this month.

Developers

Tidy up after a fix

Exact error id matching means only the right issues are closed.

Which open GitHub issues match errors marked fixed in Bugsnag project Contoso Mobile in the last 7 days?

Engineering managers

Close with a paper trail

Each closed issue gets a comment with the Bugsnag link and last seen date.

Close the GitHub issues for fixed Northwind Web errors and add the Bugsnag link to each.

How it works

What PopdockAI does when you ask

You name the Bugsnag project and a period, and your AI assistant pairs fixed errors with their issues. Only the issues you confirm are commented and closed.

01

Ask

You name the Bugsnag project and a look-back period.

Your AI tool

02

Match

It lists errors marked fixed and finds open GitHub issues with each exact error id.

bugsnag-get-error
github-get-issue

03

Confirm

You see the pairs with assignees and choose which to close.

No items found.

04

Close

It comments with the Bugsnag link and last seen date, then closes each confirmed issue.

Your AI tool

What PopdockAI provides

The tools behind the answer

Ready made tools for GitHub and one secure connection to your AI tool. No code, no exports.

get-data

bugsnag-get-error

Returns errors from Bugsnag projects, including severity, status and occurrence counts. Read-only.
get-data

github-get-issue

Returns GitHub issues from a repository. Filter by issue number, title text, state, labels, assignee, author, milestone, and created or updated date range.
run-action

github-add-issue-comment

Posts a comment on a GitHub issue or pull request, identified by issue number.
run-action

github-update-issue

Changes an existing GitHub issue's title, body, state, assignee, label or milestone, identified by issue number. Only the values you pass are changed; set the state to close or reopen the issue.
Read only.Nothing in GitHub Changes

This report is built from Get data tools only. PopdockAI applies the row, field and parameter rules your admin sets, and every query is written to the audit trail.

How Popdock AI secures your data

The outcome

A backlog that reflects what is still broken

Try PopdockAI free
Get a live demo

Related use cases

More ways to put this data to work

All Ramp use cases

One prompt template with infinite possibilities.

‍

Your AI assistant adapts its approach, tone, and capabilities to match each unique context while you maintain a single, manageable workflow.

Join forward-thinking companies that are transforming their operations with intelligent, secure AI automation.

Try PopdockAI Free
See Documentation