Free, every week
Five real AI agent setups for sales, in your inbox weekly.
Written for sales leaders running leaner teams with AI. Setups, sources and failure modes. No hype.
Free. One email a week. Unsubscribe anytime.
5 picks
Five agent setups worth stealing, each with a two-line why-it-matters and a link to the source.
1 deep dive
One setup taken apart in detail: the problem, the setup, what tends to break and how to check it.
1 tool or prompt
One tool or prompt of the week you can try before Friday.
Recipe of the week
One sales goal and the few agents that get you there, chained in order, with the handoffs that break.
Sample issue
What an issue looks like.
A sample built only from entries already in the library. Not a real sent issue.
This week: an agent that drafts outbound for rep approval, a CRM cleanup that never writes without a tick, and why your watchdog has to alert on silence.
5 picks
- 1.Research every new lead and hand the rep an approve-or-edit draft in Slack
Reps spent a long stretch of research per lead across CRM, call history, LinkedIn and the web before writing a word, with no easy way to see whether a teammate had already reached out.
- Prospecting / Outbound
- advanced
- 2.Clean the CRM weekly with an agent that proposes fixes you approve
CRM cleanup is owned by RevOps but rarely scheduled, so it happens as a rushed purge before a board meeting. Duplicates, non-standard values and dead deals pile up in between.
- Pipeline Hygiene / CRM
- intermediate
- 3.Prep each weekly forecast one-on-one with a snapshot diff and question library
Managers lack time to walk each rep's pipeline before forecast one-on-ones, so prep skews toward the loud reps and the questions turn generic.
- Deal Review / Forecasting
- intermediate
- 4.Compare stated loss reasons with call evidence across every closed deal
The CRM loss-reason dropdown usually says price because it is the polite answer. The real reasons sit in call transcripts nobody rereads.
- RevOps Reporting
- advanced
- 5.Give every seller a voice AI buyer to rehearse tough conversations
Peer role-play depends on a willing, skilled partner and often ends with polite run-throughs, so completion and usefulness both suffer.
- Enablement
- intermediate
Deep dive
Scheduled sales agents fail quietly: a routine skips its window, errors out, or posts an empty digest, and nobody notices until a rep asks where the alert went. Without a heartbeat, the team learns about outages from users instead of from the system.
What broke: Empty outputs counted as success: a run that exits cleanly but finds nothing (an expired credential, a changed field name) looks healthy unless you check output size or item count against a per-routine floor.
Recipe of the week
Score each new form lead for fit, prep the rep before the first call, get call notes into the CRM automatically, and draft the follow-up for anyone who goes quiet.
1. Score inbound form leads for fit, alert Slack on hot ones, draft the reply · 2. Deliver a one-page account brief to the rep before every meeting · 3. Attach Fathom AI meeting summaries to the right Attio records · 4. Daily follow-up agent: checks for replies, drafts the nudge, waits for approval
Tool or prompt of the week
Build a buyer-persona roleplay partner as a Custom GPT. Reps want to rehearse a specific buyer conversation before a call but have nobody to practice with on short notice.
Running an agent worth sharing? Submit a use case.
Get the free weekly.
AI agent setups for sales leaders running leaner teams. Free, every week.
Free. One email a week. Unsubscribe anytime.
Archive
No issues sent yet. Past issues will be listed here.