Sort new GitHub issues automatically and alert your team in Slack

The system reads each new GitHub issue with AI, labels it by type and priority, and pings the right Slack channel.

How the work actually flows

It branches. Every path runs.

Pattern: Parallel Split (2) ยท Exclusive Choice (4)

flowchart TD trig>"new GitHub issue created"]:::trig s0["Read new GitHub issue"]:::task s1["Classify type and priority"]:::svc trig --> s0 s0 --> s1 gx{"+ what actions to take"}:::gate s1 --> gx p00["Apply type and priority labels"]:::task gx -->|"Label in GitHub"| p00 p10["Post to urgent or general channel"]:::task gx -->|"Notify Slack"| p10 p20["Add row to spreadsheet"]:::task gx -->|"Log record"| p20 p00 --> out p10 --> out p20 --> out out[/"issue labeled and team alerted"/]:::out pay{{"faster triage without manual reading"}}:::pay out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepAn outside serviceEvery pathResultPayoff
Build size
Standard

A mid-size build with several tools working together.

Business functions
Messaging & NotificationsSpreadsheet & Database OpsAPI & Webhook IntegrationDevOps & IT Operations
Connects
GitHubGeminiSlackGoogle Sheets

The problem it solves

Your team drowns in a flood of GitHub issues with no consistent way to sort bugs from feature requests. Important, urgent problems sit in the queue next to minor ones, and nobody notices until a customer complains. Manually reading and labeling every issue eats into time your developers should spend building.

Who it fits

Engineering leads and open source maintainers who handle a steady stream of GitHub issues across one or more repositories.

How it works

  1. A new GitHub issue is created
  2. Gemini AI reads the title and description and classifies the issue type and priority
  3. The issue is automatically labeled in GitHub
  4. High-priority issues are posted to an urgent Slack channel, others to a general channel
  5. Every classification is logged to Google Sheets with a timestamp
What you get

Issues your team spots before they pile up

New issues get labeled by type and priority the moment they're opened, and the right people hear about urgent ones in Slack right away.

What you get

A labeled GitHub issue, a Slack alert for urgent items, and a running log of every issue classified in Google Sheets.

What you need

A GitHub account, a Google Gemini API key, a Slack workspace, and Google Sheets access.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Automatically review and label GitHub pull requests with AI

AI reviews every new pull request, labels it by size and type, and sends a summary straight to Slack.

Advanced

Get an AI risk assessment before adopting an open-source package

Researches an open-source package's activity and health, then has AI recommend whether it's safe to use.

Advanced

Catch GitHub configuration errors automatically and alert your team

AI compares your config files against documentation on every push and flags mismatches in Sheets and Slack.

Advanced

Auto-generate and publish blog posts from a content topic list

AI researches and writes a blog post from your topic list, then publishes it to your blog automatically.

Advanced
Back to the AI Playbook