How Recruiters Use AI Browsers for Candidate Sourcing

This guide is for recruiters who run candidate sourcing. It explains how an AI browser like Strawberry runs the workflow given the tools a recruiter actually uses every day, what the output should look like, and where the workflow fits in the recruiter's week.

Why this matters for recruiters

A recruiter spends time on this: source, screen, and close hires across multiple roles, often without a dedicated sourcer or coordinator. The pain that makes candidate sourcing feel slow is real: sourcing eats the day; screen calls compete with intake; coordination of interviews falls on the recruiter. The reason an AI browser helps is that recruiters already use multiple surfaces (LinkedIn (Recruiter when licensed), Greenhouse or Ashby or Teamtailor, Gmail, Google Sheets, Notion) 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 candidate sourcing is to build a shortlist of 10-30 candidates who match the role and have at least one signal of openness. For a recruiter, success metric is concrete: 30% reply rate to first outreach, 5+ first-call conversions per 30 sourced. A finished candidate sourcing run should look like this: a shortlist of 10-30 candidates with role-specific personalised openers, fit notes, and contact links.

Signals candidate sourcing needs

The workflow needs these signals: current role and tenure; recent role changes (often visible on LinkedIn); GitHub or content output for technical roles; company stage match (someone leaving a Series B is more likely to talk to a seed-stage co). For a recruiter the practical question is which signals come from the tools already in the stack (LinkedIn (Recruiter when licensed), Greenhouse or Ashby or Teamtailor, Gmail, Google Sheets, Notion) 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 recruiter stays in one surface.

Paste-ready Strawberry prompt

I'm a recruiter. Run candidate sourcing for me using LinkedIn (Recruiter when licensed), Greenhouse or Ashby or Teamtailor, Gmail and the browser, then save the draft.

What a finished candidate sourcing output looks like

Concrete example, not a placeholder:

• Role: Founding Engineer (Stockholm or remote EU)
• Candidate: Marek Novak - Senior Engineer @ Klarna, 4 years
• Fit: 5/5 (worked on payment systems, contributed to Rust open source, recent talk on type-safe APIs)
• Opening line: noticed his RustConf talk on type-safe API contracts and our backend lead's tweet about Marek's library
• Contact: LinkedIn DM + GitHub email

When this works, and when it does not

This workflow is right for recruiters when the work is repeatable and crosses multiple tools. It is wrong when spray-and-pray DMs that mention nothing specific about the candidate. In that case, the recruiter should keep doing the work manually until the pattern is clear enough to automate.

Three mistakes to avoid

• Spray-and-pray DMs that mention nothing specific
• Missing the obvious signals (someone just posted 'thinking about a change')
• No quality bar - putting 200 names on the list to look productive

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.