Use GitLab with an AI Browser for Lead List Building

If you use GitLab and you regularly need to build a verified lead list, the bottleneck is usually the same: GitLab holds part of the context, but lead list building 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 lead list building 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 SDR, marketer, founder doing outbound is trying to do

The goal of lead list building is to produce a clean, enriched, dedup'd list of N contacts who match ICP and have at least one buying signal. The success metric is concrete: bounce rate below 5%, dedup rate above 95%, and at least 30% of leads with a fresh signal. That definition matters because it shapes what GitLab needs to contribute to the workflow.

What signals lead list building actually needs

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

• ICP criteria (industry, size, geo, stack) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Title match including variants (Head of, VP, Director of) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Verified email pattern - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Phone number (when reachable from source) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Recent buying signals (hiring, funding, product launch) - GitLab does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Existing CRM membership (to filter out already-contacted) - 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 lead list building 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 CSV or sheet with one row per lead.
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 lead list building workflow on it. Use the browser to fill any gaps not in GitLab.
Return the output in the shape we use for lead list building: A CSV or sheet with one row per lead: name, title, company, email, LinkedIn URL, signal, source.
Do not send anything externally. Save the draft to me to review.

What a good lead list building output looks like

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

• Goal: 75 Head of Growth contacts at Series A-B SaaS in DACH
• Sources: a CRM-clean filter, a ZoomInfo/Apollo enriched pull, and a LinkedIn sweep with manual review
• Output: Google Sheet 'DACH-growth-2026-W23' with columns name, title, company, work email, LinkedIn URL, signal (hiring or funding), source notes

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 lead list building

• Guessing email patterns and getting bounced
• Including duplicates because the source mixes work and personal emails
• Padding the list with leads who don't match ICP just to hit a count target

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.