Way 1: without AI (the manual way)
Honest cost: 30-45 minutes a day, every day.
- Scan your pipeline sheet for who is owed a reply today.
- Re-read the last conversation per candidate so the email has context.
- Write each follow-up, tracking who asked to wait and who needs a nudge.
- Update the sheet after every send so tomorrow is accurate.
Remembering every loop works until a busy week. The walkthrough below builds a daily follow-up run with an assistant: keep the open-loops list current, draft each message with its history, and hold anything whose timing is wrong - you approve each send, and candidates feel looked after.
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
- 30-45 minutes a day, every day - 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 paste the tracking sheet into the chat every morning - it has no memory of yesterday.
- You must spell out your cadence rules each time or it nags candidates who asked for two days.
- You must watch for opt-outs yourself; a generic prompt will cheerfully re-email them.
Here is a starter prompt that works - copy it and bring the inputs listed:
Here is my candidate tracking sheet: [paste candidate, role, last touch date, status]. For every candidate whose follow-up is due today, draft the email using the context of their last touch. If a candidate asked for time, hold the draft and tell me when to send it instead. Do not send anything - drafts only.More on this prompt: the free candidate follow-up emails 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 (free, Free)
The Follow-up Agent is this job already designed: fixed evidence rules, output contract, test fixtures and stop points. You ask once:
Hello, send every candidate follow-up due today
And a finished, review-ready artifact lands in your own Drive:
| Candidate | Role | Last touch | Status | Next follow-up |
|---|---|---|---|---|
| Priya Raghavan | Sep 8 - phone screen done | Sep 13 | Email draft: next-steps note with interview slots (see below) | Ready to send |
| Marco Delgado | Sep 5 - take-home sent | Sep 12 | Email draft: gentle nudge with new deadline, hiring manager cc'd | Ready to send |
| Ana Petrova | Sep 11 - offer discussed | Sep 13 | Follow-up held - she asked for 2 days, due Sep 15 | Snoozed |
Sample data shown. Your workspace fills with your real work.
Setup takes about 10 minutes: download, hand the Included 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 free, 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: free agent | |
|---|---|---|---|
| Time to first result | 30-45 minutes a day, every day | 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 | Free, 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 Follow-up Agent product page · the candidate follow-up emails guide · AI agents for recruiters
Questions people ask
What is the fastest way to follow up with candidates?
The free ready-made agent: about 10 minutes of setup, then one short ask per run. Manual takes 30-45 minutes a day, every day; DIY prompting takes an afternoon of tuning plus upkeep.
Can I follow up with candidates without AI?
Yes - the manual steps are on this page. Expect 30-45 minutes a day, every day each time the job runs.
Is the free 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.