Use GitLab with an AI Browser for Support Triage

If you use GitLab and you regularly need to triage and respond to support, the bottleneck is usually the same: GitLab holds part of the context, but support triage also needs signals that live outside it - on the public web, in LinkedIn, in news, in other connected apps. Strawberry is built to combine the GitLab context with the rest of the browser, and run the full workflow as a companion you can re-trigger every week.

This page describes specifically how Strawberry handles support triage when GitLab is one of the inputs. It names the GitLab surfaces involved, the signals the workflow actually needs, an example prompt you can paste, and what a good output looks like.

The job a support engineer, founder doing support, CS lead is trying to do

The goal of support triage is to categorise inbound tickets, surface the urgent ones, and draft accurate replies grounded in product source-of-truth. The success metric is concrete: first-response time under 2 hours, accurate-categorisation rate above 95%, draft-edits-before-send under 20%. That definition matters because it shapes what GitLab needs to contribute to the workflow.

What signals support triage actually needs

For each signal below, here is whether GitLab can contribute directly or whether Strawberry has to find it via the browser:

• Ticket category (billing, bug, feature request, account, security) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Sentiment (positive, neutral, frustrated, churn-risk) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Product state (subscription tier, recent activity, feature flag) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• History (has this user reported the same before) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• GitHub/Linear status if it's a bug - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Team-mate replies already in the thread - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.

What Strawberry can do inside GitLab

Strawberry can read MRs, summarize issues, and trigger pipelines with approval.

GitLab surfaces Strawberry uses for this workflow: projects, merge requests, issues, pipelines, snippets.

How Strawberry runs support triage with GitLab

1. Strawberry opens the GitLab projects that contains the relevant context.
2. The companion pulls related context from GitLab (merge requests, history, attached files) where it exists.
3. For the parts GitLab does not store, Strawberry uses the browser - web search, LinkedIn, news, the prospect's website.
4. Strawberry synthesises the output in the shape this workflow needs: A draft reply per ticket, plus a category label and priority - human reviews before send.
5. A human reviews before any external action (send, update, post). Then the approved output is saved back to GitLab or your system of record.

Example Strawberry prompt

Paste this in a new Strawberry chat with GitLab connected. Adjust the specifics to your actual ICP, role, or topic.

Read this GitLab projects and any linked context.
Then run a full support triage workflow on it. Use the browser to fill any gaps not in GitLab.
Return the output in the shape we use for support triage: A draft reply per ticket, plus a category label and priority - human reviews before send.
Do not send anything externally. Save the draft to me to review.

What a good support triage output looks like

Here is what a finished output for support triage should look like in practice. The specifics will change for your use case, but the shape should look similar:

• Ticket #1962 - Marcus Rosenberg (marcus@clubstill.com)
• Category: billing - plan-state mismatch
• Priority: P1 (paying user, $118 charge vs Intern credits)
• Verified: Stripe shows Intern, charge log shows $118 Part-Time amount, credits granted at Intern rate
• Draft reply: confirm Intern is active, apologise for the rate mismatch, grant 22k credit balance to match Part-Time tier for current cycle, no refund promised

Why GitLab for this, and where to use a different tool

GitLab is strong for this workflow because Strawberry can read MRs, summarize issues, and trigger pipelines with approval.

Where GitLab falls short Self-hosted GitLab instances need separate OAuth config; cross-project queries can be slow.

Consider also the rest of your stack for the parts GitLab doesn't cover.

Common mistakes when running support triage

• Auto-replying with 'we'll look into it' without doing the work
• Ignoring teammate replies already in the thread
• Guessing about product behaviour instead of checking GitHub or source code
• Automated security-report replies (always a major mistake - escalate to a human only)

Connecting GitLab to Strawberry

GitLab OAuth. Once connected, the companion can read the surfaces above without re-authenticating, and any write action still requires explicit human approval the first time the workflow runs.

Caveats

Do not let any AI agent send emails, update CRM records, or change shared systems without a clear approval step. Strawberry is strongest when the workflow combines browser context with connected-app context and a human review for sensitive actions.