Use Google Docs with an AI Browser for Personalized Outreach

If you use Google Docs and you regularly need to draft personalised outbound, the bottleneck is usually the same: Google Docs holds part of the context, but personalized outreach 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 Google Docs 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 personalized outreach when Google Docs is one of the inputs. It names the Google Docs 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 or SDR sending high-intent cold email is trying to do

The goal of personalized outreach is to produce a short, specific message that references a real signal and asks one question. The success metric is concrete: reply rate above 8%, positive sentiment above 50%, meeting-booked rate above 20% of replies. That definition matters because it shapes what Google Docs needs to contribute to the workflow.

What signals personalized outreach actually needs

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

Concrete recent event (funding, hire, product, talk, post) - Google Docs does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
Personal angle: shared connection, mutual school, common topic - Google Docs does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
Company pain that maps to the seller's product - Google Docs does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
Preferred channel (email, LinkedIn DM, in-person at event) - Google Docs does not contain this directly. Strawberry uses the browser plus public sources to fetch it.

What Strawberry can do inside Google Docs

Strawberry can draft new Docs from research or update existing Docs with structured outputs (briefs, recaps, reports).

Google Docs surfaces Strawberry uses for this workflow: headings, comments, suggesting mode, tables, linked Sheets/Slides.

How Strawberry runs personalized outreach with Google Docs

Strawberry opens the Google Docs headings that contains the relevant context.
The companion pulls related context from Google Docs (comments, history, attached files) where it exists.
For the parts Google Docs does not store, Strawberry uses the browser - web search, LinkedIn, news, the prospect's website.
Strawberry synthesises the output in the shape this workflow needs: A draft email or DM with subject + 60-90 word body + clear one-line CTA.
A human reviews before any external action (send, update, post). Then the approved output is saved back to Google Docs or your system of record.

Example Strawberry prompt

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

Read this Google Docs headings and any linked context.
Then run a full personalized outreach workflow on it. Use the browser to fill any gaps not in Google Docs.
Return the output in the shape we use for personalized outreach: A draft email or DM with subject + 60-90 word body + clear one-line CTA.
Do not send anything externally. Save the draft to me to review.

What a good personalized outreach output looks like

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

Subject: Voi Germany pullout + retention
Hey Anna,
Saw your SuperVenture talk and the Germany news. Curious - is the retention team looking at AI-driven win-back flows yet, or still email-only?
If interesting, happy to send a 90-second screen recording of how a comparable scooter co cut churn 18%.
If not relevant, no worries, ignore.
Cheers, Laurits

Why Google Docs for this, and where to use a different tool

Google Docs is strong for this workflow because Strawberry can draft new Docs from research or update existing Docs with structured outputs (briefs, recaps, reports).

Where Google Docs falls short complex tables can lose formatting; comments are write-once and don't always trigger collaborator notifications.

Consider also a CRM for the relationship layer.

Common mistakes when running personalized outreach

Long messages that feel automated
Fake-flattery openers ("I love what you're building")
Asking for a 30-min call before any context
Obvious AI-language ("In today's fast-paced landscape...")

Connecting Google Docs to Strawberry

Bundled in Google OAuth scope. 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 Google Docs + Strawberry runs personalized outreach

1 Google Docs

Read

Open the relevant Google Docs headings; 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 personalized outreach shape: A draft email or DM with subject + 60-90 word body + clear one-line CTA.

4 Human

Approve

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

FAQ - Google Docs + AI browser for personalized outreach

Can Strawberry do personalized outreach entirely inside Google Docs?

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

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

Not necessarily. Google Docs 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 Google Docs?

Read access to the surfaces you want Strawberry to use (headings, comments, suggesting mode). Write permissions are only needed if you want Strawberry to update Google Docs after a human approves the change. Bundled in Google OAuth scope.

What is the realistic success metric for personalized outreach?

reply rate above 8%, positive sentiment above 50%, meeting-booked rate above 20% of replies - that is the target Strawberry helps you hit, not the only thing it measures.

What is the biggest mistake to avoid?

Long messages that feel automated.

Run personalized outreach in 10 minutes with Strawberry and Google Docs

Open Google Docs

Connect Google Docs so Strawberry can read headings, comments, suggesting mode, tables, linked Sheets/Slides and 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.
Tell Strawberry the brief

Drop the prompt below. Replace the placeholder with the actual founder or SDR sending high-intent cold email target - one name, one URL, or one Google Docs reference is enough. Keep the goal explicit: produce a short, specific message that references a real signal and asks one question
Let it gather signals

Strawberry pulls concrete recent event (funding, hire, product, talk, post) and personal angle: shared connection, mutual school, common topic, then layers public web sources in parallel. You should see citations next to each fact - that is the audit trail. Watch the Google Docs side: complex tables can lose formatting; comments are write-once and don't always trigger collaborator notifications
Review before write-back

Output lands in the shape you asked for: A draft email or DM with subject + 60-90 word body + clear one-line CTA. Read it once. Fix anything off. The success metric is reply rate above 8%, positive sentiment above 50%, meeting-booked rate above 20% of replies - if the draft does not hit that bar, send it back with a one-line correction.
Save it as a routine

If you will draft personalised outbound this 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 personalized outreach with Google Docs

You are helping me draft personalised outbound personalized outreach. Use Google Docs as one input and the public web for the rest.

Target: [paste one founder or SDR sending high-intent cold email target here - a Google Docs reference, a name + company, or a URL]

Goal: produce a short, specific message that references a real signal and asks one question

Signals to gather:
- concrete recent event (funding, hire, product, talk, post)
- personal angle: shared connection, mutual school, common topic
- company pain that maps to the seller's product
- preferred channel (email, LinkedIn DM, in-person at event)

Output shape: A draft email or DM with subject + 60-90 word body + clear one-line CTA

Rules:
- Cite every fact with a link or a Google Docs 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 Google Docs or send anything externally until I approve.

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

When Google Docs + Strawberry is the right combo for personalized outreach

Google Docs is the long-form output and shared reference doc. Strawberry can draft new Docs from research or update existing Docs with structured outputs (briefs, recaps, reports). For personalized outreach specifically, that means the agent already has headings, comments, suggesting mode, tables, linked Sheets/Slides 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 Google Docs data you would feed in is stale or wrong. Garbage in, confident garbage out.

Three mistakes to avoid

long messages that feel automated
fake-flattery openers ("I love what you're building")
asking for a 30-min call before any context

Honest tradeoff

complex tables can lose formatting; comments are write-once and don't always trigger collaborator notifications. 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

Subject: Voi Germany pullout + retention,Hey Anna,,Saw your SuperVenture talk and the Germany news. Curious - is the retention team looking at AI-driven win-back flows yet, or still email-only?,If interesting, happy to send a 90-second screen recording of how a comparable scooter co cut churn 18%.,If not relevant, no worries, ignore.,Cheers, Laurits