Use Slack with an AI Browser for Client Reporting

If you use Slack and you regularly need to produce a client report, the bottleneck is usually the same: Slack 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 Slack 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 Slack is one of the inputs. It names the Slack 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 Slack needs to contribute to the workflow.

What signals client reporting actually needs

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

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

What Strawberry can do inside Slack

Strawberry can read recent channel activity, summarize a thread, and post approved updates back to a channel.

Slack surfaces Strawberry uses for this workflow: channels, DMs, threads, saved items, user list.

How Strawberry runs client reporting with Slack

1. Strawberry opens the Slack channels that contains the relevant context.
2. The companion pulls related context from Slack (DMs, history, attached files) where it exists.
3. For the parts Slack 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 Slack or your system of record.

Example Strawberry prompt

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

Read this Slack channels and any linked context.
Then run a full client reporting workflow on it. Use the browser to fill any gaps not in Slack.
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 Slack for this, and where to use a different tool

Slack is strong for this workflow because Strawberry can read recent channel activity, summarize a thread, and post approved updates back to a channel.

Where Slack falls short Sending in Slack requires explicit approval; private channels need explicit invitation; search retention depends on plan.

Consider also a CRM or project tool for tracked follow-up.

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 Slack to Strawberry

Native OAuth, read + write scopes are separate. 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.