Use Gmail with an AI Browser for Support Triage

If you use Gmail and you regularly need to triage and respond to support, the bottleneck is usually the same: Gmail holds part of the context, but support triage 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 support triage 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 support engineer, founder doing support, CS lead is trying to do

The goal of support triage is to categorise inbound tickets, surface the urgent ones, and draft accurate replies grounded in product source-of-truth. The success metric is concrete: first-response time under 2 hours, accurate-categorisation rate above 95%, draft-edits-before-send under 20%. That definition matters because it shapes what Gmail needs to contribute to the workflow.

What signals support triage actually needs

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

• Ticket category (billing, bug, feature request, account, security) - Gmail does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Sentiment (positive, neutral, frustrated, churn-risk) - Gmail does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Product state (subscription tier, recent activity, feature flag) - Gmail does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• History (has this user reported the same before) - Gmail does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• GitHub/Linear status if it's a bug - Gmail does not contain this directly. Strawberry uses the browser plus public sources to fetch it.
• Team-mate replies already in the thread - Gmail stores or surfaces this directly. Strawberry reads it through the connected integration.

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 support triage 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 draft reply per ticket, plus a category label and priority - human reviews before send.
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 support triage workflow on it. Use the browser to fill any gaps not in Gmail.
Return the output in the shape we use for support triage: A draft reply per ticket, plus a category label and priority - human reviews before send.
Do not send anything externally. Save the draft to me to review.

What a good support triage output looks like

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

• Ticket #1962 - Marcus Rosenberg (marcus@clubstill.com)
• Category: billing - plan-state mismatch
• Priority: P1 (paying user, $118 charge vs Intern credits)
• Verified: Stripe shows Intern, charge log shows $118 Part-Time amount, credits granted at Intern rate
• Draft reply: confirm Intern is active, apologise for the rate mismatch, grant 22k credit balance to match Part-Time tier for current cycle, no refund promised

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 support triage

• Auto-replying with 'we'll look into it' without doing the work
• Ignoring teammate replies already in the thread
• Guessing about product behaviour instead of checking GitHub or source code
• Automated security-report replies (always a major mistake - escalate to a human only)

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.

When Gmail + Strawberry is the right combo for support triage

the system of record for outbound and inbound conversations Strawberry can read entire threads, follow attachments, search by query, and draft replies that match a prior writing style For support triage specifically, that means the agent already has unread threads, labels, drafts, search operators, attachments, scheduled sends 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 Gmail data you would feed in is stale or wrong. Garbage in, confident garbage out.

Three mistakes to avoid

1. auto-replying with 'we'll look into it' without doing the work
2. ignoring teammate replies already in the thread
3. guessing about product behaviour instead of checking github or source code

Honest tradeoff

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

Ticket #1962 - Marcus Rosenberg (marcus@clubstill.com),Category: billing - plan-state mismatch,Priority: P1 (paying user, $118 charge vs Intern credits),Verified: Stripe shows Intern, charge log shows $118 Part-Time amount, credits granted at Intern rate,Draft reply: confirm Intern is active, apologise for the rate mismatch, grant 22k credit balance to match Part-Time tier for current cycle, no refund promised