How Chiefs Of Staff Use AI Browsers for Support Triage

This guide is for chiefs of staff who run support triage. It explains how an AI browser like Strawberry runs the workflow given the tools a chief of staff actually uses every day, what the output should look like, and where the workflow fits in the chief of staff's week.

Why this matters for chiefs of staff

A chief of staff spends time on this: shadow the CEO across every meeting, surface what is being lost in the noise, and turn decisions into shipped work. The pain that makes support triage feel slow is real: context lives in every channel at once; the chief of staff is the only one with cross-functional visibility but no time. The reason an AI browser helps is that chiefs of staff already use multiple surfaces (Notion, Gmail, Slack, Google Workspace, the company CRM and analytics tools) to do this work, and the browser is the only tool that can read across all of them and produce a finished output.

What success looks like

The goal of support triage is to categorise inbound tickets, surface the urgent ones, and draft accurate replies grounded in product source-of-truth. For a chief of staff, success metric is concrete: first-response time under 2 hours, accurate-categorisation rate above 95%, draft-edits-before-send under 20%. A finished support triage run should look like this: an exec brief, a meeting recap with owners, or a synthesised view of cross-functional state.

Signals support triage needs

The workflow needs these signals: ticket category (billing, bug, feature request, account, security); sentiment (positive, neutral, frustrated, churn-risk); product state (subscription tier, recent activity, feature flag); history (has this user reported the same before). For a chief of staff the practical question is which signals come from the tools already in the stack (Notion, Gmail, Slack, Google Workspace, the company CRM and analytics tools) versus what the browser has to fetch. Strawberry reads the in-stack tools through native integrations and uses the browser for the rest (LinkedIn, news, company websites, search). The chief of staff stays in one surface.

Paste-ready Strawberry prompt

I'm a chief of staff. Run support triage for me using Notion, Gmail, Slack and the browser, then save the draft.

What a finished support triage output looks like

Concrete example, not a placeholder:

• 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

When this works, and when it does not

This workflow is right for chiefs of staff when the work is repeatable and crosses multiple tools. It is wrong when anything that requires the CoS to become the bottleneck on a function that should own itself. In that case, the chief of staff should keep doing the work manually until the pattern is clear enough to automate.

Three mistakes to avoid

• 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

Caveats

Strawberry holds back on sending email, updating CRM records, or changing shared systems until a human approves the action. Treat the agent as a fast first-draft author, not an autopilot.

When this is NOT a fit for chiefs of staff

This workflow earns its keep when chiefs of staff run support triage more than once a week and the stack is mostly online. Skip it when the run depends on hand-held context Strawberry cannot see - private investor calls, off-the-record conversations, paywalled databases chiefs of staff have special access to. Run it manually those times and capture the playbook for the next iteration.

The other anti-pattern: anything that requires the CoS to become the bottleneck on a function that should own itself. Chiefs of staff that scale this workflow always pair Strawberry with a sharp opinion or hypothesis chiefs of staff bring. The agent is great at gathering. It is not great at picking a fight on your behalf.

3 mistakes that kill the run

• 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

Honest tradeoff

Strawberry will not invent missing signals. If a subject does not have a public hiring page, the agent says so - it does not pad the output with guesses. That is the right behaviour, but it means chiefs of staff sometimes see a shorter output than expected. The fix is upstream: feed it better sources, or accept that this subject is information-sparse and move on. Pretending the signal exists is what gets chiefs of staff into trouble; an empty section is a feature, not a bug.

What a finished output looks like

Chiefs of staff should be able to send the result to the next person in the chain (buyer, manager, client, hiring partner) without a major rewrite. If the draft needs more than ten minutes of editing, the input scope was too broad or the wrong signals were prioritised. Re-run with a tighter subject. Concretely, a strong support triage brief includes:

• 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

Anything thinner than that and the run is not done.