Use Gmail with an AI Browser for Campaign Research

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

Diagram of Strawberry AI browser workflow using Gmail for campaign research

If you use Gmail and you regularly need to research a campaign or partnership before it ships, the bottleneck is usually the same: Gmail 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 Gmail 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 Gmail is one of the inputs. It names the Gmail 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 Gmail needs to contribute to the workflow.

What signals campaign research actually needs

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

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

What Strawberry can do inside Gmail

Strawberry can read entire threads, follow attachments, search by query, and draft replies that match a prior writing style.

Gmail surfaces Strawberry uses for this workflow: unread threads, labels, drafts, search operators, attachments.

How Strawberry runs campaign research with Gmail

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

Example Strawberry prompt

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

Read this Gmail unread threads and any linked context.
Then run a full campaign research workflow on it. Use the browser to fill any gaps not in Gmail.
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 Gmail for this, and where to use a different tool

Gmail is strong for this workflow because Strawberry can read entire threads, follow attachments, search by query, and draft replies that match a prior writing style.

Where Gmail falls short Gmail rate-limits search-heavy queries; large inbox scans need pagination; sending requires explicit human approval to avoid spam risk.

Consider also a CRM for relationship history beyond a single thread.

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 Gmail to Strawberry

Gmail OAuth is a Strawberry native integration; no separate scopes setup needed once connected. 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 Gmail + Strawberry runs campaign research

1 Gmail

Read

Open the relevant Gmail unread threads; 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 - Gmail + AI browser for campaign research

Can Strawberry do campaign research entirely inside Gmail?

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

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

Not necessarily. Gmail 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 Gmail?

Read access to the surfaces you want Strawberry to use (unread threads, labels, drafts). Write permissions are only needed if you want Strawberry to update Gmail after a human approves the change. Gmail OAuth is a Strawberry native integration; no separate scopes setup needed once connected.

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.