home / use cases / it and developers / github-issue-triage

GitHub issue triage while you write code

The moment an issue opens, your Aivell reads it, labels it, hunts for duplicates and gives a useful first response — asking for the version and steps a bug report is missing. On Fridays it sweeps the backlog. It comments and labels; closing decisions beyond obvious duplicates stay human.

Watch the demo

starts when: A new issue opens on one of your repositories

The problem

Issue triage is a tax paid in context switches. A new issue lands mid-function: is it a duplicate of #482, a question the docs answer, or a real bug missing its version number? Working that out takes ten minutes of archaeology, so it gets postponed — and an issue tracker where nothing gets a first response for a week quietly tells users to stop reporting things.

The backlog compounds. Unlabeled issues can’t be filtered, near-duplicates breed independent comment threads, and the eventual cleanup weekend recurs like a bad habit. None of this is engineering; all of it steals engineering time.

How your Aivell does it

  1. The webhook fires on open. The instant an issue is created, the chore starts — no polling, no morning triage rota.
  2. The issue gets actually read. Body, pasted logs, linked context. The Aivell labels it by your taxonomy and searches past issues and your docs — indexed in the knowledge base on the box — for duplicates and existing answers.
  3. First response in minutes, not days. Duplicates get linked to the original and closed politely. Questions get the doc link. Bug reports missing the version or reproduction steps get asked — once, and friendlier than a bot template.
  4. The sharp cases go straight to a human. Anything smelling of a security report is never answered in public; Chiara gets it by mail immediately. And no bug or feature request is ever closed by the machine — the guardrail physically blocks it.
  5. Friday is housekeeping. The scheduled sweep lists issues gone quiet for sixty days and labels the strays, so the backlog stops silently accreting.

Reporters get answered while the report is still warm, maintainers get issues that arrive pre-sorted with the missing details already chased — and the triage rules stay a paragraph of plain language you can change over coffee.

The chore, as you'd write it.

No flowcharts, no code — a chore is just a message to your Aivell, in your own words. It shapes it into a solid, guarded procedure and follows it to the letter. This one:

Giulia Aivell · triage incoming issues ● active

when an issue opens, read it fully, including pasted logs

label it — bug, feature, question or support

hunt for duplicates; link the original and close the copy politely

questions the docs already answer get a first reply with the link

bug reports missing version or steps? ask for them, friendly, once

security reports get no public reply — mail Chiara immediately

never close a bug or feature request; humans decide those

friday, list issues silent for 60 days and label the unlabeled

You
Got it — I'll start right away, and check with you whenever something needs a human.
Giulia Aivell

The tools it uses.

Connected with single-click passkeys — no copied tokens, no OAuth hell.

Webhooks fires the chore when an issue opens
GitHub labels, comments, links duplicates
Knowledge Base checks the docs and past issues
Schedule runs the friday housekeeping sweep
Email escalates security reports privately

Sensible guardrails.

Every tool can be limited to exactly what this chore needs. For this one, you might set:

GitHub May label and comment on the repositories you listed. Closing is allowed only for duplicates it has linked to an original.
GitHub Issues and comments only — no pushes, no merges, no changes to code or settings.
Email Security escalations go to the maintainers' address, nowhere else.

Questions, answered.

Our repositories are private. Where does the issue text go? +

It comes to you. The box fetches the issue, and all the reading and reasoning happen onboard — the only things that travel back to GitHub are the label and the comment. No second AI service ever sees your tracker.

Will it close issues or argue with reporters? +

It closes exactly one thing — duplicates, with a link to the original — because the guardrail allows nothing more. Every other issue stays open for a human, and the tone of first replies is whatever you wrote in the chore.

What happens when someone reports a security hole? +

Silence in public, speed in private. The chore forbids a public reply and mails the maintainer directly instead — the one triage case where a fast templated response is exactly wrong.

Can it touch the code itself? +

No. A guardrail restricts it to issues and comments — no pushes, no merges. Triage is a librarian's job, and the Aivell is kept firmly at the librarian's desk.

Related.

What is an Aivell?

An Aivell is an on-premise AI colleague: a small box that plugs into your network, runs its own AI onboard and takes the repetitive work off your desk. Prompts, documents, data — nothing ever leaves your office. Unplug the internet: it keeps working.

You describe each task as a chore, in plain language. Your Aivell turns it into a solid, guarded procedure and runs it in the background — with guardrails on every tool, a complete audit trail, and approvals in your hand when you want them. One-time setup, fixed monthly fee. No tokens, no overages.

Watch the demo

onboard inference · air-gapped · fixed monthly fee