Use GitHub with an AI Browser for Client Reporting

Run client reporting in Strawberry using GitHub as one of the inputs. Specific surfaces, example prompt, real output, and tradeoffs vs alternatives.

Diagram of Strawberry AI browser workflow using GitHub for client reporting

If you use GitHub and you regularly need to produce a client report, the bottleneck is usually the same: GitHub holds part of the context, but client reporting 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 GitHub 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 client reporting when GitHub is one of the inputs. It names the GitHub surfaces involved, the signals the workflow actually needs, an example prompt you can paste, and what a good output looks like.

The job a agency owner, account manager, founder serving clients is trying to do

The goal of client reporting is to produce a clean, on-brand recap of what was done, what worked, and what is next for a client. The success metric is concrete: report turnaround under 1 day, client approval without major revision. That definition matters because it shapes what GitHub needs to contribute to the workflow.

What signals client reporting actually needs

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

  • Campaign or activity data from connected ad/analytics tools - GitHub does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Agreed KPIs and last-period comparison - GitHub does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Qualitative wins or losses - GitHub does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Next-period plan - GitHub does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Open questions for the client - GitHub does not contain this directly. Strawberry uses the browser plus public sources to fetch it.

What Strawberry can do inside GitHub

Strawberry can read PR diffs, summarize issues, comment with approval, and search code across repos.

GitHub surfaces Strawberry uses for this workflow: repos, PRs, issues, commits, Actions.

How Strawberry runs client reporting with GitHub

  1. Strawberry opens the GitHub repos that contains the relevant context.
  2. The companion pulls related context from GitHub (PRs, history, attached files) where it exists.
  3. For the parts GitHub 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 PDF or Google Doc structured by section.
  5. A human reviews before any external action (send, update, post). Then the approved output is saved back to GitHub or your system of record.

Example Strawberry prompt

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

Read this GitHub repos and any linked context.
Then run a full client reporting workflow on it. Use the browser to fill any gaps not in GitHub.
Return the output in the shape we use for client reporting: A PDF or Google Doc structured by section: summary, KPI table, highlights, plan, asks.
Do not send anything externally. Save the draft to me to review.

What a good client reporting output looks like

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

  • Client: Sparbanken Skåne - May 2026
  • KPIs: CPC -12%, CTR +0.4pt, total leads +18%
  • Highlights: new creative angle on retention won 60% of impressions
  • Plan for June: scale the winning creative, test a second segment
  • Asks: confirm copy review SLA for new creative

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

GitHub is strong for this workflow because Strawberry can read PR diffs, summarize issues, comment with approval, and search code across repos.

Where GitHub falls short Private orgs need a separate OAuth app; rate limits on large repo searches.

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

Common mistakes when running client reporting

  • Report is mostly screenshots of dashboards with no synthesis
  • Missing the comparison vs last period so the client can't tell if things are working
  • No 'what we're doing about it' section for bad KPI movements

Connecting GitHub to Strawberry

GitHub OAuth - currently three separate apps for prod/dev/local. 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.

How GitHub + Strawberry runs client reporting

1 GitHub

Read

Open the relevant GitHub repos; pull related context.

2 Browser

Augment

Use the browser, LinkedIn, news, and other connected apps for signals outside the CRM/tool.

3 Output

Compose

Synthesise into the client reporting shape: A PDF or Google Doc structured by section.

4 Human

Approve

Human reviews before any external action; approved output is saved back.

FAQ - GitHub + AI browser for client reporting

Can Strawberry do client reporting entirely inside GitHub?

No, and that is the point. client reporting needs signals GitHub does not store - public web, LinkedIn, news, other apps. Strawberry combines GitHub with the browser, which is where the real value comes from.

Does GitHub need to be the primary CRM or system of record?

Not necessarily. GitHub can be one input among several. Strawberry can read it as context even if your primary system of record is somewhere else.

What permissions do I need on GitHub?

Read access to the surfaces you want Strawberry to use (repos, PRs, issues). Write permissions are only needed if you want Strawberry to update GitHub after a human approves the change. GitHub OAuth - currently three separate apps for prod/dev/local.

What is the realistic success metric for client reporting?

report turnaround under 1 day, client approval without major revision - that is the target Strawberry helps you hit, not the only thing it measures.

What is the biggest mistake to avoid?

Report is mostly screenshots of dashboards with no synthesis.