Worked example. This is an illustrative worked example, not a client result. The sales team and every number in it are assumptions. It shows how a claude-based follow-up assistant could surface the deals that have gone quiet and draft the next touch in the rep's own voice, with the rep reviewing and sending every message.
The problem is not lead volume. It is memory. Deals stall after a good second call, the rep moves on to a hotter thread, and later nobody remembers to circle back. The pipeline looks healthy in the CRM. It is quietly dying inside it.
For illustration, assume a vp of sales whose CRM holds a pile of open deals that have gone quiet: already marked open, going nowhere, no new leads bought. The question is how many of them come back to a live conversation when a rep touches them at the right moment with the right message. That is the number to measure, and this post does not claim a figure for it.
#Why do so many deals die in follow-up?
How does AI help with sales follow-up on stalled deals?
AI reads your CRM daily, flags deals that have gone quiet past their normal cadence, and drafts the next message in the rep's voice using the real thread history. The rep reviews and sends. It recovers pipeline you already have instead of chasing new leads, and volume stays in human range so deliverability holds.
A rep with 40 open deals (an assumption for illustration) cannot hold 40 follow-up clocks in their head. So the loudest deal wins the day and the quiet ones drift. The drift is invisible until quarter-end, when a forecasted deal turns out to have been silent since the second call. This is the exact pattern our AI for sales work is built around.
#What does the design consist of?
Three parts, none of them exotic. A step that scores which open deals have gone quiet past their normal cadence. A drafting step that writes the next touch using the real thread history. And a daily list the rep opens instead of combing the CRM by hand.
- Surface: reads open opportunities in the CRM each morning and flags the ones past their expected next-touch date, weighted by deal size and last real reply.
- Draft: writes one short follow-up per flagged deal in the rep's voice, citing the last thing that actually happened on the thread. No generic 'just checking in'.
- Review: drops the draft into a 'who to nudge today' list. Nothing sends until the rep reads it and hits send.
The draft step is the part that should change reply quality. A follow-up that says "you mentioned the renewal lands in q3, wanted to line the pilot up before then" is far more likely to get answered than "just checking in". Claude reads the thread and pulls the specific hook, so the rep edits a real message instead of writing one from a blank box.
We are
A daily list that hands each rep the quiet deals worth a nudge and a drafted first version to edit, with a human reading and sending every message.
We aren't
An auto-sequencer that fires templated 'just following up' emails at every open deal on a timer and trains your prospects to filter you out.
Volume should stay in human range. Reps send the same number of follow-ups a person could reasonably send, from their own warmed mailboxes. The assistant changes which deals get attention and what each message says, not how many go out, so spam complaints and deliverability should not move. That human-in-the-loop line is the same discipline behind our AI implementation work.
#How would you know it is working?
Expect an early stretch that is noisy. The surfacing step flags deals that are quiet for good reasons, reps get a list they do not trust, and some stop opening it. The fix is tuning the cadence logic and teaching it to ignore deals a rep has deliberately parked.
The signal to measure is reactivation: of the deals the list flagged, how many returned to a live conversation, compared with comparable deals before you switched it on. Set that baseline first, and count only deals a rep touched because the list surfaced them. The model is the easy part; the boring loop around it is what you are testing. The journal has more worked examples of this pattern.
There is no client quote here, because there is no client. The test of the design is simple: does the rep stop losing deals to their own inbox, with a list that says who went quiet and a message they can actually send?
Stennir is a young studio, and this post is a design, not a track record. If you are a vp of sales watching forecasted deals go silent in the CRM, the pipeline to recover is already yours. tell us what you're building and we will scope the follow-up loop against your actual deal data.
