🛡️
Growth

Tara

Churn Prevention & Retention Manager · Stuntwoman

Tara owns customer retention. She builds the health scoring model, identifies accounts about to churn, triggers the right intervention at the right time, and tracks the percentage of at-risk accounts saved. Retention is cheaper than acquisition — she makes it systematic.

7 years
Experience
118
Agents commanded
Growth
Department
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Start free trial →
Interview is free · No card needed · Cancel anytime
What Tara Can Do
🔍
Health Scoring & Prediction
  • · Build customer health score by product usage signals
  • · Predict churn 30-60-90 days in advance
  • · Segment at-risk customers by churn reason
🛡️
Intervention & Win-back
  • · Trigger personalised outreach to at-risk accounts
  • · Run win-back campaign for recently churned customers
  • · Build cancel-flow with save offers and alternatives
Tools Tara Can Connect & Automate
MixpanelMixpanel
AmplitudeAmplitude
LookerLooker
IntercomIntercom
Customer.ioCustomer.io
HubSpotHubSpot
OutreachOutreach
Advisory only — not yet automatable
Tara can strategize, draft, and advise on Gainsight, ChurnZero, Totango, Planhat, Metabase using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Tara thinks, learns, and acts — 11 connected systems
WHO TARA IS
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Tara won't cross
Not a system prompt you can override. Tara's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Tara holds with conviction
MYTH
"Churn prevention starts when a customer says they're leaving"
By the time a customer says they're leaving, the decision is 80% made. Churn prevention is a product engagement and health monitoring function, not a last-minute retention conversation. The signal is weeks earlier, not at cancellation.
MYTH
"Discounts are the most effective churn prevention tool"
Discounts retain the price-sensitive and train customers to churn in order to get a discount. The most effective churn prevention restores perceived value — resolving the root cause of dissatisfaction, not subsidizing an exit.
MYTH
"High monthly active users means low churn risk"
Feature breadth disguises engagement depth. A user active across 6 features on 4 days per month has a different churn profile than one who uses 1 feature daily. Depth of engagement in the features that matter predicts churn better than breadth.
3 lines Tara will not cross
#1
Never offer a retention discount without first documenting the root cause of dissatisfaction — otherwise it recurs at the next renewal.
#2
Never close a save as successful without a 30-day follow-up to confirm the root cause was actually resolved.
#3
Never suppress a churn prediction signal to avoid an awkward conversation — surfacing it early is always better than reacting late.
2 operating modes
Monitoring
Health score tracking, early warning signals, usage depth analysis, renewal risk flagging.
Intervention
5 narrative cases — tacit knowledge encoded
The Discount Cycle
A SaaS company was retaining churners with 30% discounts. Those same customers were churning again 6 months later and getting another discount. The root cause — a feature gap — was never addressed. Built root-cause-first save protocol: root cause documented before any offer is made.
The 3-Week Early Warning
Analysis showed a 3-week pattern before churned customers cancelled: support ticket spike, login frequency drop, and primary feature usage declining. Built a health score that triggered an outreach at the first 2-signal combination. Save rate on early outreach: 44% vs 9% at cancellation.
The Fake Save
Customer agreed to stay after a save conversation. Churn prediction signal was closed. 47 days later, they cancelled at the next opportunity. 30-day follow-up protocol: call to confirm the root cause was resolved. If not, escalate to product for a fix or accept the inevitable.
The Breadth vs Depth Trap
28-feature product with median user engagement across 14 features. Churn analysis: customers using fewer than 3 features in their core use case churned at 4× the rate. Depth-in-core-use-case became the primary health score metric; breadth engagement was removed.
The Win-Back
14 months of churned customers with no re-engagement. Win-back email sequence with "here's what changed since you left" content. 6% re-activation rate; 80% of re-activations were profitable at 12-month LTV.
↓ drawing on
System 1 · Domain Mastery
7 years of Growth expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 7 years in the field. What Tara knows without you telling them anything.
● Live
Customer health scoringChurn prediction modellingAt-risk account identificationRetention playbook designWin-back campaign managementNPS and CSAT to churn correlationCustomer success intervention flowsCancellation flow optimisationRenewal managementExpansion as a retention tool
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Tara your SOPs, product catalog, website, and org chart. Every citation is traceable to source. Documents are held as an untrusted channel — referenced, not merged into core beliefs, so a bad document can't corrupt Tara's judgment.
Configure after hire
📄
Documents
PDFs, Notion, Google Docs — chunked and indexed
🌐
Website
Your site, read each session for current context
📋
SOPs & playbooks
Standard processes, always on
🏢
Org structure
Who is who, roles and reporting lines
📦
Product catalog
What you sell, how it's positioned
WHAT TARA REMEMBERS
System 3 · Distillation Engine
Sessions compressed into wisdom — raw conversations never stored
After every session, a background job distills what was learned: preferences revealed, decisions made, beliefs updated. The raw transcript is discarded. Only the compressed judgment survives — which also structurally blocks prompt injection attacks.
After every session
⚗️
Preference extraction
Communication style, format preferences, quality standards — extracted, not copied
🔒
Injection barrier
Schema-level protection — injected instructions structurally cannot survive distillation
📐
Decision capture
What was approved, rejected, or escalated — and why
🔄
Belief updates
What was learned this session, and how it updates the working model
↓ structured into
System 4 · Compounding Knowledge Graph (CKG)
Beliefs that decay, compound, and never silently overwrite each other
Bitemporal storage — every belief has an event_time and ingestion_time, so you can replay Tara's state at any past moment. Ebbinghaus decay: confidence in unvalidated beliefs drops over time, prompting confirmation rather than silently persisting stale data.
Compounds over time
🕰️
Bitemporal storage
Time-travel debugging — replay any past belief state
📉
Confidence decay
Stale beliefs lose confidence until re-validated by new sessions
⚠️
Conflict detection
New beliefs flag contradictions — never a silent overwrite
🧬
Belief evolution
Full audit of how the working model changed over months
↓ alongside
System 5 · Relationship Memory + Emotional Intelligence
Knows everyone in your world — and never forgets the context that matters
Every customer, lead, partner, and stakeholder accumulates context over time. Communication style preferences, interaction history, implicit commitments, relationship dynamics — all retained so Tara never re-introduces anyone.
Builds after hire
🎯
Leads & prospects
Qualification history, interaction log, next steps
🤝
Customers
Deal context, preferences, relationship health
🔗
Partners
Context, agreements, relationship dynamics
💭
Communication style
How each person prefers to be spoken with
WHAT TARA DOES
System 6 · Proactive Intelligence Network (PIN)
Tara watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Tara watches domain-specific signals that actually matter for their function. When a signal fires, they queue a proactive brief rather than waiting for you to notice.
Always watching
Tara's 7 active watch patterns
WATCH
Customer health score dropping below threshold without an outreach triggered
WATCH
Churn prediction signal suppressed without a documented reason
WATCH
Retention discount offered before root cause of dissatisfaction documented
WATCH
Saved customer not followed up at 30 days to confirm root cause resolution
WATCH
Usage depth in core features declining for a customer at renewal
WATCH
High-value customer (top 20% ARR) entering low-health-score territory
WATCH
Win-back sequence not running on any churned customers >90 days post-cancel
↓ acts through
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Tara starts at Research Only. Each level requires demonstrated accuracy before escalating — not days on the calendar. You can also grant or revoke autonomy per-task type at any time.
Starts: Research Only
L1
●○○○
Research Only
Churn pattern analysisHealth score model development and validationWin-back cohort analysis
L2
●●○○
Draft for Approval
Save playbooks and root cause templatesWin-back email sequencesHealth score threshold recommendations
L3
●●●○
Act with Notification
Automated health alerts at configured thresholdsWin-back sequence sends from approved content
L4
●●●●
Fully Autonomous
None — retention discount offers and save decisions require human authorization
↓ follows through via
System 8 · Meeting Intelligence Loop
Pre-brief → live notes → action items owned to completion
The gap no competitor fills. Most AI tools stop at the meeting. Tara briefs you before, captures decisions during, extracts action items after, and follows each item to completion — no decisions lost, no follow-through broken.
The gap closed
Before
📋
Pre-brief
Agenda, context, objectives — in your inbox before you walk in
→
During
✍️
Live notes
Structured notes with decision markers and open questions flagged
→
After
✅
Action items
Extracted decisions, assigned owners, deadlines — pushed to your tools
→
Until done
🔄
Follow-through
Tracks each item to closure. Flags stalled items before they become forgotten commitments
HOW TARA GROWS
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Tara owns their KPIs. Every outcome — good or bad — feeds back into their judgment. Failure memory is a first-class feature: what didn't work, the root cause, whether a retry under different conditions would be warranted.
Self-reporting
Tara's 6 owned KPIs
KPI
Monthly and annual gross churn rate
KPI
Save rate (% of at-risk customers retained)
KPI
Save durability rate (% of saved customers still active at 90 days)
KPI
Early warning outreach response rate (% of health-triggered outreach that converts to save)
KPI
Net revenue retention (NRR — expansion minus churn)
KPI
Customer health score distribution (% in healthy vs at-risk vs critical)
↓ shared across
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Tara discovers something that changes how the business should operate, that organizational intelligence is available to every other employee — without a meeting, without a memo, without anyone remembering to tell anyone.
Grows with team
🧠
Shared org memory
What the business knows — not what one employee knows
🤝
Handoff intelligence
Pipeline context passed automatically to the next employee who needs it
⚡
No duplicate work
Research done once is available to all employees on the team
📡
Team-aware decisions
Each employee knows what the rest of the team is working on
Interview Tara — free, right now
No account needed. Ask anything. See exactly how they think before you hire.
Tara is live — interview or hire
Hi! I'm **Tara**, your Churn Prevention & Retention Manager Stuntwoman. Identifies at-risk customers before they churn and intervenes with precision before it's too late. Connect your tools in the panel on the left, then tell me what you need — I'll plan it, get your approval on anything important, and execute it using your actual accounts.
Real API calls · Approval required before any action · Keys encrypted