Way 1: without AI (the manual way)
Honest cost: 45 minutes a day.
- Scan for deals with no recent activity.
- Re-read the thread, then write a follow-up that adds something new.
- Update stages so the forecast reflects this week.
Follow-up by memory means the loudest deal gets attention and the quiet one dies. The method below runs a weekly follow-up round with an assistant: sort by days since activity, draft per deal from its real history, and propose the stage changes - you approve the sends and the moves.
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
- 45 minutes a 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 pipeline and threads every morning.
- You must ban "just checking in" in the prompt, every time, or that is what you get.
- You must verify proposed stage changes against reality before trusting them.
Here is a starter prompt that works - copy it and bring the inputs listed:
Here is my pipeline with last activity dates: [paste]. List every deal with no activity in 14+ days, draft a follow-up for each that adds something new (not 'just checking in'), and propose stage changes with the evidence. Drafts and proposals only - do not send or change anything.More on this prompt: the free sales follow-ups and pipeline updates 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 & Pipeline Agent is this job already designed: fixed evidence rules, output contract, test fixtures and stop points. You ask once:
Hello, show me due follow-ups and proposed pipeline changes
And a finished, review-ready artifact lands in your own Drive:
| Lead | Last activity | Follow-up draft | Proposed stage | Approval status |
|---|---|---|---|---|
| Rachel Kim (Clearbit-like data co) | Demo Sep 9, asked for pricing | Follow-up draft: recap + 2 pricing options, send by Sep 13 | Proposal | Ready to send |
| Tom Alvarez (logistics startup) | Trial started Sep 4 | Check-in draft: day-10 usage summary + book onboarding call | Trial | Ready to send |
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 | 45 minutes a 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 & Pipeline Agent product page · the sales follow-ups and pipeline updates guide · AI agents for sales teams
Questions people ask
What is the fastest way to run sales follow-ups and pipeline updates?
The free ready-made agent: about 10 minutes of setup, then one short ask per run. Manual takes 45 minutes a day; DIY prompting takes an afternoon of tuning plus upkeep.
Can I run sales follow-ups and pipeline updates without AI?
Yes - the manual steps are on this page. Expect 45 minutes a 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.