Way 1: without AI (the manual way)
Honest cost: 2-3 hours per role.
- Run LinkedIn searches by hand, trying different title spellings and filters.
- Open every promising profile in a tab and read it against the role.
- Copy names and profile URLs into a spreadsheet one by one.
- Add an evidence note per row from memory, while the tab is still open.
Sourcing means opening tabs, running the same LinkedIn searches, copying profile URLs into a sheet and trying to remember why each person looked right. Two hours later you have nine rows, no evidence column, and a hiring manager asking where the shortlist is.
Pros of doing it manually
- Free except your time - no tools, no accounts.
- You learn the job deeply and control every detail.
- No data leaves your hands.
Cons of doing it manually
- 2-3 hours per role - every single time the job runs.
- Quality depends on your energy that day.
- More volume just means more hours; it does not scale.
Way 2: with AI, but without AI Agent Skills (DIY prompting)
A chat assistant genuinely helps here. The catch is that you become the workflow designer. What you have to figure out yourself:
- You must write the sourcing prompt yourself and keep tightening it when results drift.
- You must define the output columns and evidence rules, or every run comes back shaped differently.
- You must re-paste the role, the sheet and the rules every single run - nothing persists between sessions.
Here is a starter prompt that works - copy it and bring the inputs listed:
Find 10 candidates for this role: [paste role summary and must-have skills]. For each candidate give me: name, LinkedIn profile URL, and one line of job-relevant evidence with the source you used. Present it as a table. Do not contact anyone and do not invent profiles - if you cannot verify a profile exists, say so instead of listing it.More on this prompt: the free ai candidate sourcing for recruiters prompt page.
Pros of DIY prompting
- Free, or nearly - any chat assistant works.
- A first draft in minutes instead of hours.
- Fully flexible: tweak the prompt for any edge case.
Cons of DIY prompting
- You become the workflow designer: prompts, test data and output rules are yours to write, test and maintain.
- Output drifts between sessions unless you re-paste the rules every run.
- Nothing is saved for you - sheets, structure and context are rebuilt each time.
Way 3: with AI Agent Skills ($19, one-time)
The Sourcing Agent is this job already designed: fixed evidence rules, output contract, test fixtures and stop points. You ask once:
Hello, find me 10 product designers
And a finished, review-ready artifact lands in your own Drive:
| Name | Evidence | |
|---|---|---|
| Sample candidate A | linkedin.com/in/sample-product-designer-a | Product systems work at two B2B SaaS teams; source checked |
| Sample candidate B | linkedin.com/in/sample-product-designer-b | Mobile design portfolio and relevant role history; source checked |
Sample data shown. Your workspace fills with your real work.
Setup takes about 10 minutes: buy, hand the three files to the assistant you already use (Instinct, ChatGPT, Claude, Gemini or any other assistant that reads files), approve the fictional-data test. Then it runs on a standing cycle or a one-line ask, and stops at every human gate. Full method.
Pros of the ready-made agent
- About 10 minutes to a tested setup, not an afternoon of prompt tuning.
- The same output shape every run - evidence rules and stop points are already designed.
- Runs on a standing cycle or a one-line ask; files land in your own Drive.
Cons of the ready-made agent
- Costs $19 once, where DIY prompting is free.
- The output format is opinionated - you adapt the template rather than rebuild it.
- It still stops and waits for your approval at decision points; it is not zero-touch.
The honest comparison
| Way 1: manual | Way 2: DIY AI | Way 3: $19 agent | |
|---|---|---|---|
| Time to first result | 2-3 hours per role | An afternoon of prompt tuning | About 10 minutes, tested setup |
| Every run after | Same hours, every time | Re-paste the rules, sheet and context each run | One short ask, or a standing cycle |
| Consistency | Depends on the day | Drifts between sessions | Same output shape every run |
| Cost | Your hours | Free, plus your time | $19 once, files kept forever |
The manual way teaches you the job. DIY prompting is fine for a one-off. The agent wins when the job repeats every week.
More: the Sourcing Agent product page · the AI candidate sourcing for recruiters guide · AI agents for recruiters
Questions people ask
What is the fastest way to source candidates?
The $19 ready-made agent: about 10 minutes of setup, then one short ask per run. Manual takes 2-3 hours per role; DIY prompting takes an afternoon of tuning plus upkeep.
Can I source candidates without AI?
Yes - the manual steps are on this page. Expect 2-3 hours per role each time the job runs.
Is the $19 agent worth it over DIY prompting?
If the job repeats weekly, yes: you stop rebuilding prompts and re-pasting context every run. For a one-off, DIY prompting is fine and free.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.