Sales · Starter · updated 2026-10-23
Closed-lost "wake the dead" campaign
Pull last year's closed-lost deals and stalled meetings, have an LLM summarise why each prospect originally engaged from the pre-call notes, then send a short personal email that references the AE, the last meeting and that reason.
Building block of the Self-learning outbound machine and Closed-lost and competitor displacement engine.
1Is this my problem?
Old opportunities already know you. Specific context ("we spoke in March about X") gets replies that generic re-engagement never does.
You'll recognise this if…
- Closed-lost list never revisited.
- Old notes have useful context nobody reads.
- Win-back emails are generic.
2Is this solution worth it?
Reported results
- Sendoso: 16 meetings, 23 leads and a closed deal within two weeks of launch, at a 75% open rate and 11% response rate (source)
Quoted from the linked source; results vary.
Your ROI, with the assumptions shown
Prefilled with illustrative assumptions (5 h/week at $60/h, 70% automated, build $4,000). Change them to your numbers.
Limits and when not to build it
Skip it if: CRMs with empty notes.
- Exclude accounts that churned badly or asked not to be contacted.
- Check that notes are not shared verbatim in the email.
3How does it work?
One small internal tool does this for you. The same job, before and after:
Before · by hand
- One-off or quarterly: someone notices
- Export closed-lost + no-decision deals
- Summarise original interest from notes (by hand)
- Draft email with AE name, timing, reason (by hand)
- Spot-check a sample
- Send via sequencer, log in CRM
Closed-lost "wake the dead" campaignIllustrative
- Starts automatically: one-off or quarterly
- Export closed-lost + no-decision deals
- AI: Summarise original interest from notes
- AI: Draft email with AE name, timing, reason
- You: Spot-check a sample
- Send via sequencer, log in CRM
✦ AI step · ● human checkpoint · ✓ automatic
Compressing messy pre-call notes into one sentence about why they cared.
- Summarise original interest from notes
- Draft email with AE name, timing, reason
Your tool connects to
Under the hood: flow, architecture and vendors
- When: One-off or quarterly
- Export closed-lost + no-decision deals
- Summarise original interest from notes
- Draft email with AE name, timing, reason
- Spot-check a sample
- Send via sequencer, log in CRM
Architecture
Vendors commonly used
Maturity ladder
What each level adds. Most teams start at level 1 or 2 and climb. Highlighted: where this build sits.
- Level 1Basic automation
Trigger: one-off or quarterly. Fixed rules then export closed-lost + no-decision deals, spot-check a sample, send via sequencer, log in crm. No AI involved.
- Level 2AI-assisted
An LLM handles the judgement step (summarise original interest from notes) and a person reviews every output before it is used.
- Level 3Autonomous agent
The agent runs end to end on its own and only stops for exceptions. Sample review before launch.
- Level 4Self-learning system
Becomes part of the self-learning outbound machine: Every 6 hours a champion/challenger step reads Instantly stats, waits for 200+ sends per variant, and asks Claude to pick a winner and write one new challenger with a stated hypothesis, using the last 10 experiments as memory.
Level 4 lives in the Self-learning outbound machine: 8 stages with a learning loop.
Seen in the wild
Links checked 2026-10-23. We describe these builds from public material; we are not affiliated with these companies.
4Who can build it?
Matched on services, platforms and industries agencies list on their own sites, and on their published projects.
Why matched: CRM automation/sync; Email automation; uses Salesforce, Clay.
Related project: Snap Ads — Snap Ads discovered RevPack the same way many of their customers later discovered them: through a well-crafted outbound campaign.
No published price
Why matched: CRM automation/sync; Email automation; uses Salesforce, Clay.
Example project: Coastal Recruiting grew accepted candidate intros 4.7x with OneGTM — How OneGTM built Coastal Recruiting a candidate outbound engine that grew recruiter-accepted intros 4.7x in four months, with interested rep…
Published price: From $167
closedinWhy matched: CRM automation/sync; Email automation; uses Salesforce, Clay.
No published price
Automation Consulting ServicesNew York, United StatesWhy matched: CRM automation/sync; Email automation; uses Salesforce.
Example project: Meeting-to-action automation for a healthcare SaaS CEO — AI-powered meeting capture and action item extraction that returns 6-8 hours per week to a Series B healthcare SaaS CEO.
Published price: From $500
flowioGlasgow, United KingdomWhy matched: CRM automation/sync; Email automation; uses Salesforce.
Example project: AI Automation Case Study: Edinburgh Boiler Company — Discover how flowio used AI Voice and SMS agents to cut lead response times from 1 day to 5 minutes for The Edinburgh Boiler Company.
Published price: From £750
Projects, tools and prices come from each agency's own website (crawled October 2026). Not paid placements.
Part of the starter pack: First head of sales.
5What should I do next?
Questions
What does a "closed-lost "wake the dead" campaign" automation do?
Pull last year's closed-lost deals and stalled meetings, have an LLM summarise why each prospect originally engaged from the pre-call notes, then send a short personal email that references the AE, the last meeting and that reason.
Which tools can I use to build it?
Common choices are Clay, Salesforce, ChatGPT, Instantly. Teams often use Clay, Salesforce, ChatGPT together; the right mix depends on what you already pay for. n8n, Make and Zapier can all handle the workflow steps.
How much does it cost to build?
As a rough estimate, agencies often quote $1k–$4k for a first version of this workflow, plus monthly tool and AI usage fees. Your quote depends on how many systems are involved and how clean your data is.
How much time does it save?
Our estimate for a small team is about 3–6 hours a week. This is a rough guide, not a measured result; measure your own baseline before you start.
Where does AI actually help?
Compressing messy pre-call notes into one sentence about why they cared.
Who actually runs this?
Public examples include: Clay customer story: Sendoso. Reported: Sendoso: 16 meetings, 23 leads and a closed deal within two weeks of launch, at a 75% open rate and 11% response rate.
Where should a person stay in the loop?
Sample review before launch.
What usually goes wrong?
Exclude accounts that churned badly or asked not to be contacted. Check that notes are not shared verbatim in the email.
Related workflows
Ops builds enrichment and contact-finding workflows once (waterfall across many data vendors); reps call them from the AI chat they already use to get account context, buying signals and verified contacts..
Competitor displacement research across your TAMA-LIGN replaced a $60K/year manual research contract; 2,000 accounts researched, 1M+ data points, and $6.8M pipeline generated or identified in 6.5 months (as reported by Clay)For every target account, an AI web-research step checks which of your service categories they use, why, and which competitor provides it, then writes the answers into CRM fields reps can filter on..
Sales call transcripts to CRM fieldsAfter each recorded call, the transcript is filtered by deal stage, summarised, and specific fields (pain, competitors, next steps, objections) are written to the opportunity.
Inbound lead research and qualification agentVercel: one person now does the lead-triage work previously done by 10Every inbound form fill gets a deep-research pass on the person and company, a structured qualification verdict, and a drafted reply.