Use Slack with an AI Browser for Partnership Research

If you use Slack and you regularly need to research a potential partner, the bottleneck is usually the same: Slack holds part of the context, but partnership research 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 partnership research 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 founder, partnerships lead, BD is trying to do

The goal of partnership research is to decide if a partnership is worth pursuing and prepare a specific first conversation. The success metric is concrete: first meeting booked within 14 days, clear next step at the end of that meeting. That definition matters because it shapes what Slack needs to contribute to the workflow.

What signals partnership research actually needs

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

• Audience overlap (do their customers look like yours) - Slack does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Go-to-market motion (do they sell the way you'd want) - Slack does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• History of co-marketing (do they ship with partners or not) - Slack does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Current ecosystem partners (where do you fit relative to them) - Slack does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Executive sponsor identification - Slack does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Any prior conversations with their team - 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 partnership research 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 partnership brief.
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 partnership research workflow on it. Use the browser to fill any gaps not in Slack.
Return the output in the shape we use for partnership research: A partnership brief: fit thesis, audience overlap, proposed shape (integration, co-marketing, distribution), first ask.
Do not send anything externally. Save the draft to me to review.

What a good partnership research output looks like

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

• Partner: Kime (GEO platform)
• Fit thesis: their users (in-house marketers tracking AI-search visibility) need an AI browser to run the research workflows that produce the content Kime tracks
• Audience overlap: 30-40% based on Kime's customer list (Saxo, Superb, THEMAGIC5)
• Shape: mutual referral, 15% rev share, 18-month attribution
• First ask: a 30-min product demo from each side, decide if MCP integration is worth building

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 partnership research

• Treating every integration as a partnership when it's just a checkbox
• No clear thesis so the first meeting is a generic 'let's see how we can help each other'
• Skipping audience overlap and pursuing partners whose users don't buy what you sell

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.

When Slack + Strawberry is NOT the right fit for partnership research

Skip this setup if any of the following is true:

• You don't actually need Slack signals. If everything you need lives on the public web, drop the Slack step and let Strawberry run on URLs alone - it's faster.
• A known Slack constraint blocks the speed gain: Sending in Slack requires explicit approval.
• The buyer (founder, partnerships lead, BD) doesn't own the decision. If the brief gets handed to someone who'll redo the research, the audit-trail-in-Strawberry advantage is wasted.

3 mistakes that kill this workflow

1. Treating every integration as a partnership when it's just a checkbox. Slack is one input. Strawberry's edge is combining it with everything else. Stop at Slack-only signals and you'd have been faster with native Slack reports.
2. No clear thesis so the first meeting is a generic 'let's see how we can help each other'. Pre-check Slack for a recent touch or duplicate before Strawberry acts on the output. A duplicate hit burns the relationship.
3. Skipping audience overlap and pursuing partners whose users don't buy what you sell. Strawberry is built so a human reviews before any external action. Skipping that review to save time is how you ship a wrong fact to a real person.

Honest tradeoff vs alternatives

You could research a potential partner inside Slack alone using its native features, or with a dedicated partnership research tool. Slack alone gives you tighter data fidelity but misses every signal that lives off-platform. A specialised partnership research tool gives you better dashboards but its scope ends where its integrations end, and most of the real signal still lives on the open web.

Strawberry's edge with Slack: Strawberry can read recent channel activity, summarize a thread, and post approved updates back to a channel. The price you pay: an agent run takes 30-90 seconds; a native Slack action loads in 2. For a one-off question you already know the answer to, use Slack directly. For an output you'll redo every week or every account, route it through Strawberry as a saved routine so the synthesis happens once and re-runs automatically.

What a real output looks like

• Partner: Kime (GEO platform)
• Fit thesis: their users (in-house marketers tracking AI-search visibility) need an AI browser to run the research workflows that produce the content Kime tracks
• Audience overlap: 30-40% based on Kime's customer list (Saxo, Superb, THEMAGIC5)
• Shape: mutual referral, 15% rev share, 18-month attribution
• First ask: a 30-min product demo from each side, decide if MCP integration is worth building