Relevance AI
Relevance AI
SalesforceHubSpotGmailLinkedIn

Closed-lost deals reopened when the reason dies

The Old Deal Re-engager knows why every deal was really lost. When a launch, a price change or a leadership change kills that reason, it re-engages with exactly that story.

SSO shipped in release 4.2
Old Deal Re-engager

SSO just shipped. Somewhere in closed-lost are the deals that died for exactly this.

Searching closed-lost reasons and notes5s

12 deals lost on SSO in the last year. 8 still match our ICP.

Checking which contacts are still in seat3s
Drafting objection-specific notes9s
Found 12 deals lost on SSO in the last year; 8 still fit ICP and 6 contacts are still in seat. Each draft opens with the objection from their own deal notes and the news that it shipped, not a generic product update. Biggest fish: Northpeak at $48k. Their VP Eng replied within the hour asking for a call.

How it works

SSO shipped · 4.2Pricing model changedNew VP at lost accountQuarterly lost-book sweep
Revival note draftedDeal reopenedStayed closed · reason loggedOwner briefed

Triggered by what changes

Product releases, pricing changes and buying-committee moves each start a sweep of the closed-lost book in Salesforce or HubSpot.

Matches the signal to the real objection

The agent reads the notes and emails behind each loss reason, decides whether the new signal actually kills that objection, and leaves the rest closed.

Re-engages through your CRM

Objection-specific drafts land ready to send, reopened deals go back on the pipeline with their history, and skipped deals get the reasoning logged.

Without Relevance

With Relevance

Closed-lost is a graveyard nobody revisits, except a yearly "any change on your end?" blast.

Every lost deal stays live as a watch: the real objection on record, waiting for the event that kills it.

The loss reason field says "price" because that was the easiest dropdown option at the time.

The agent reads the notes and emails behind the dropdown, and matches signals against what actually killed the deal.

A generic "lots has changed since we last spoke!" that reads like every other one they got that week.

Each note opens with their specific objection, quoted from their own deal, and the news that it is gone.

Re-engagement happens when someone remembers, usually quarters after the objection was resolved.

The day the release ships or the pricing changes, every deal lost on that exact reason is found and worked.

Reps remember their own recent losses. Deals from departed reps are lost twice.

The whole closed-lost book gets matched against every new signal, including the deals nobody owns anymore.

The blast hits everyone, including companies that pivoted, churned contacts, and deals lost for reasons still true.

Deals whose objection still stands are left closed, with the reason logged. A bad revival burns the contact for good.

Held to a quality bar, on every run

Every revival is checked against eval test cases written for this exact job before a note goes out. If a run fails the bar, it never ships.

Old Deal Re-engager

Pass rate · last 14 days

Sampling 2% of live runs · 92% passing this week

Revivals cite the deal’s own objection96%
The objection is verifiably resolved93%
Out-of-ICP deals stay closed94%
Departed contacts are never emailed91%

Train your agent like an employee

Onboard it with your playbooks and correct it in plain English. It learns the lesson for good, and nothing changes until you approve it.

Old Deal Re-engager
Instructions updated
Tool added
Closed-lost notes search
13 evals added
Revivals cite the deal’s own objectionThe objection is verifiably resolved+11 more
Publish version 4
PDFWin-Loss Review Notes.pdf240 KB
Use these win-loss patterns when deciding which lost deals to revive.
Read Win-Loss Review Notes.pdf. Updated my instructions, added a closed-lost notes search tool, and wrote 12 evals to check every run.
Never revive a deal on the loss-reason dropdown alone. Read the notes; the dropdown lies.
Understood. I added an eval that fails any revival justified only by the loss-reason field, so every re-engagement now traces to the notes behind it.
Teach it something new…
Ask

Built for enterprise teams

Run agents on your real data with the access controls, audit trails, and residency guarantees enterprises require all built in.

Monitoring

Real-time visibility into every agent’s activity, performance, and cost.

RBAC

Control who can use, build, edit, and deploy agents.

Data residency

Multi-region deployment keeps your data within your required geography.

Version control

Full version history on every agent. Roll back to any previous state.

Audit logs

Every action, every decision, every tool call logged and exportable.

Human-in-the-loop

Set approval gates on any action or allow agents to ask questions.

SSO / SAML

Enterprise single sign-on with SAML 2.0. Centralize identity & access.

PII masking

Detect and redact personally identifiable information.

SOC 2 Type IIGDPROTEL & Delta Sharing
KPMG
"The ability to be vendor agnostic and the ability to scale across a breadth of functions is a really key feature."

Levi Watters

Partner, KPMG Australia

Read more
Autodesk
"The key for us was how we can modularize industry knowledge and the best playbooks, and apply it."

Allen Roh

Senior Marketing Manager, Autodesk

Read more
Canva
"We're looking for every place where AI can allow sellers and customer success reps to be more engaged with customers."

Rob Giglio

Chief Customer Officer, Canva

Read more
"The ability to be vendor agnostic and the ability to scale across a breadth of functions is a really key feature."

Levi Watters

Partner, KPMG Australia

Read more

Team it up with more marketing agents

ICP match
Buying intent high
Budget unknown
Outside target region

MQL Qualifier

Scores and qualifies inbound leads against fit.

Does it handle 10k contacts?
Yes — here's a slot to see it live
Demo booked · Thu 2pm

Inbound Engager

Replies to inbound leads instantly and relevantly.

Viewed pricing 2×ROI case studyWeekly newsletter

Lifecycle Marketer

Runs personalized nurture campaigns across the full lifecycle.

Blog postLinkedInNewsletterSlack

Content Repurposer

Turns one asset into channel-native formats.

4.2%
Email
2.1%
Search
1.1%
Social
Shift budget to Email

Campaign Reporter

Pulls multi-channel campaign performance.

ai agents12k volHard
ai for cx8k volEasy
support ai5k volEasy

SEO Brief Writer

Researches keywords and writes content briefs.

248 attendees
112 hot leads
Emailed hot segment
18 demos booked

Event Follow-up

Segments attendees for targeted post-event outreach.

Every agent you add shares one stack

These agents all run on one platform: one gateway, one router, one eval suite, one audit trail. Every agent after the first ships faster.

  • Triggered by key events or signalslike Zapier
  • Given access to contextlike Zep
  • Connected to your appslike Composio
  • Access to all LLMslike OpenRouter
  • Performance evaluatedlike Braintrust
  • No-code agent builderlike Dust.tt
  • Coordinated into teamslike CrewAI
  • Chained into multi-step processeslike n8n
  • Kept alive through long-running worklike Temporal
  • Traced at every step of every runlike Langfuse

Put the Old Deal Re-engager to work this quarter

We partner with enterprise teams to take this work off their plate. An agent built with you, proven against your quality bar, and live in weeks.