Use Microsoft Teams with an AI Browser for Campaign Research

Run campaign research in Strawberry using Microsoft Teams as one of the inputs. Specific surfaces, example prompt, real output, and tradeoffs vs alternatives.

Diagram of Strawberry AI browser workflow using Microsoft Teams for campaign research

If you use Microsoft Teams and you regularly need to research a campaign or partnership before it ships, the bottleneck is usually the same: Microsoft Teams holds part of the context, but campaign 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 Microsoft Teams 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 campaign research when Microsoft Teams is one of the inputs. It names the Microsoft Teams surfaces involved, the signals the workflow actually needs, an example prompt you can paste, and what a good output looks like.

The job a marketer, founder, partnership manager is trying to do

The goal of campaign research is to gather the context needed to brief, target, and de-risk a campaign before spending budget. The success metric is concrete: campaign launches on time, CAC within target, and creative does not need a rewrite mid-flight. That definition matters because it shapes what Microsoft Teams needs to contribute to the workflow.

What signals campaign research actually needs

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

  • Audience segmentation (who exactly buys this) - Microsoft Teams does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Competitor messaging already in the space - Microsoft Teams does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Winning ad examples (Meta Ad Library, LinkedIn) - Microsoft Teams does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Channel-fit (does the audience even read this channel) - Microsoft Teams stores or surfaces this directly. Strawberry reads it through the connected integration.
  • Creative reference library - Microsoft Teams does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
  • Compliance constraints (data, privacy, claims) - Microsoft Teams does not contain this directly. Strawberry uses the browser plus public sources to fetch it.

What Strawberry can do inside Microsoft Teams

Strawberry can read channel context and send approved messages; meeting prep can include recent channel activity.

Microsoft Teams surfaces Strawberry uses for this workflow: teams, channels, chats, meetings, files.

How Strawberry runs campaign research with Microsoft Teams

  1. Strawberry opens the Microsoft Teams teams that contains the relevant context.
  2. The companion pulls related context from Microsoft Teams (channels, history, attached files) where it exists.
  3. For the parts Microsoft Teams 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 campaign brief.
  5. A human reviews before any external action (send, update, post). Then the approved output is saved back to Microsoft Teams or your system of record.

Example Strawberry prompt

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

Read this Microsoft Teams teams and any linked context.
Then run a full campaign research workflow on it. Use the browser to fill any gaps not in Microsoft Teams.
Return the output in the shape we use for campaign research: A campaign brief: audience, channels, messaging hypotheses, creative refs, KPIs, risks.
Do not send anything externally. Save the draft to me to review.

What a good campaign research output looks like

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

  • Campaign: AI browser launch on Meta Ads - Nordic ICP
  • Audience: founders + ops leads at 10-200 person SaaS companies in SE/DK/NO
  • Channels: Meta Ads (primary), LinkedIn (secondary), founder LinkedIn organic
  • Messaging: 'The browser that does the boring work' - 3 variants
  • Risks: Meta still needs Business Verification stable; budget capped at €500/wk in test phase

Why Microsoft Teams for this, and where to use a different tool

Microsoft Teams is strong for this workflow because Strawberry can read channel context and send approved messages; meeting prep can include recent channel activity.

Where Microsoft Teams falls short Tenant permission policies often restrict cross-team visibility; meeting transcripts need separate licensing.

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

Common mistakes when running campaign research

  • Skipping competitor analysis and rebuilding a positioning someone else already won
  • Guessing at audience instead of pulling real segmentation
  • No creative references so the team designs in a vacuum

Connecting Microsoft Teams to Strawberry

Microsoft Graph OAuth - scope set per env (engineering pending Infisical update). 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 Microsoft Teams + Strawberry runs campaign research

1 Microsoft Teams

Read

Open the relevant Microsoft Teams teams; 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 campaign research shape: A campaign brief.

4 Human

Approve

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

FAQ - Microsoft Teams + AI browser for campaign research

Can Strawberry do campaign research entirely inside Microsoft Teams?

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

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

Not necessarily. Microsoft Teams 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 Microsoft Teams?

Read access to the surfaces you want Strawberry to use (teams, channels, chats). Write permissions are only needed if you want Strawberry to update Microsoft Teams after a human approves the change. Microsoft Graph OAuth - scope set per env (engineering pending Infisical update).

What is the realistic success metric for campaign research?

campaign launches on time, CAC within target, and creative does not need a rewrite mid-flight - that is the target Strawberry helps you hit, not the only thing it measures.

What is the biggest mistake to avoid?

Skipping competitor analysis and rebuilding a positioning someone else already won.

Run campaign research in 10 minutes with Strawberry and Microsoft Teams

  1. Open Microsoft Teams

    Connect Microsoft Teams so Strawberry can read teams, channels, chats, meetings, files, then combine them with the rest of the brief. Pin the specific records or views you want to start from so the agent does not drift.

  2. Tell Strawberry the brief

    Drop the prompt below. Replace the placeholder with the actual marketer, founder, partnership manager target - one name, one URL, or one Microsoft Teams reference is enough. Keep the goal explicit: gather the context needed to brief, target, and de-risk a campaign before spending budget

  3. Let it gather signals

    Strawberry pulls audience segmentation (who exactly buys this) and competitor messaging already in the space, then layers public web sources in parallel. You should see citations next to each fact - that is the audit trail. Watch the Microsoft Teams side: Tenant permission policies often restrict cross-team visibility; meeting transcripts need separate licensing

  4. Review before write-back

    Output lands in the shape you asked for: A campaign brief: audience, channels, messaging hypotheses, creative refs, KPIs, risks. Read it once. Fix anything off. The success metric is campaign launches on time, CAC within target, and creative does not need a rewrite mid-flight - if the draft does not hit that bar, send it back with a one-line correction.

  5. Save it as a routine

    If you will research a campaign or partnership before it ships again next week, click Save as routine. Pick a cadence (daily, weekly, on-trigger). Strawberry re-runs the whole flow on schedule and pings you when the new output is ready.

Paste-ready prompt for campaign research with Microsoft Teams

You are helping me research a campaign or partnership before it ships campaign research. Use Microsoft Teams as one input and the public web for the rest.

Target: [paste one marketer, founder, partnership manager target here - a Microsoft Teams reference, a name + company, or a URL]

Goal: gather the context needed to brief, target, and de-risk a campaign before spending budget

Signals to gather:
- audience segmentation (who exactly buys this)
- competitor messaging already in the space
- winning ad examples (Meta Ad Library, LinkedIn)
- channel-fit (does the audience even read this channel)
- creative reference library
- compliance constraints (data, privacy, claims)

Output shape: A campaign brief: audience, channels, messaging hypotheses, creative refs, KPIs, risks

Rules:
- Cite every fact with a link or a Microsoft Teams reference. If you cannot find a signal, say so explicitly rather than guessing.
- Do not invent specifics. Use real, dated signals from the last 90 days where possible.
- If a fact would change the outcome and is missing, pause and ask me before writing the final output.

When the output is ready, surface it in this chat. Do not write back to Microsoft Teams or send anything externally until I approve.

Paste this into Strawberry's chat field. Replace the target placeholder before running.

When Microsoft Teams + Strawberry is the right combo for campaign research

Strawberry can read channel context and send approved messages; meeting prep can include recent channel activity For campaign research specifically, that means the agent already has teams, channels, chats, meetings, files as starting context - you do not need to brief it from scratch.

When it is NOT a fit

  • You need a single number, not a synthesised brief. A SQL query against your warehouse is faster.
  • The decision is happening in the next 60 seconds. The agent is fast but it is not instant; for hard real-time use, do it manually.
  • The Microsoft Teams data you would feed in is stale or wrong. Garbage in, confident garbage out.

Three mistakes to avoid

  1. skipping competitor analysis and rebuilding a positioning someone else already won
  2. guessing at audience instead of pulling real segmentation
  3. no creative references so the team designs in a vacuum

Honest tradeoff

Tenant permission policies often restrict cross-team visibility; meeting transcripts need separate licensing If you are running this at scale (10+ briefs per day), batch the inputs and let Strawberry process them as a routine instead of one-by-one prompts - cheaper per brief and the output stays consistent.

What a real output looks like

Campaign: AI browser launch on Meta Ads - Nordic ICP,Audience: founders + ops leads at 10-200 person SaaS companies in SE/DK/NO,Channels: Meta Ads (primary), LinkedIn (secondary), founder LinkedIn organic,Messaging: 'The browser that does the boring work' - 3 variants,Risks: Meta still needs Business Verification stable; budget capped at €500/wk in test phase