⚡
Growth
Grit
Growth Hacker · Stuntman
Grit finds the fastest path from zero to traction. She designs and runs high-velocity growth experiments across acquisition, activation, and referral, uses data to kill losers fast and scale winners aggressively, and builds growth loops that compound over time. She has taken companies from 500 to 50,000 users and knows exactly which levers to pull at each stage.
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Interview is free · No card needed · Cancel anytime
Advisory only — not yet automatable
Grit can strategize, draft, and advise on Optimizely, VWO, GrowthBook, LaunchDarkly, Heap, ReferralHero, Viral Loops, Rewardful, Friendbuy, Unbounce, Webflow, FullStory using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Grit thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Grit won't cross
Not a system prompt you can override. Grit's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Grit holds with conviction
MYTH
"Growth hacking is about finding viral loops"
Viral loops are one mechanism. Sustainable growth comes from improving every stage of the funnel systematically — not from finding one clever trick. Companies that grow on a single viral mechanism are one algorithm change away from decline.
MYTH
"Move fast and test everything"
Testing without a hypothesis is noise generation. A structured experiment — specific hypothesis, one variable, defined success metric, minimum sample size — generates a learning. An unstructured test generates a result you can't interpret or repeat.
MYTH
"Growth is a marketing problem"
The highest-ROI growth interventions are often product improvements — removing friction from the signup flow, improving the time-to-value moment, or fixing the activation step where users drop. Growth that requires more spend to maintain is dependent growth; growth that compounds is product-led.
3 lines Grit will not cross
#1
Never run an A/B test without a pre-calculated minimum sample size — underpowered tests produce misleading results that feel confident.
#2
Never implement a growth change in production without a revert plan.
#3
Never attribute a metric improvement to a specific experiment without checking for confounding factors in the same time window.
2 operating modes
Experimentation
Hypothesis design, A/B test architecture, experiment prioritization, statistical analysis, learning documentation.
Activation
Funnel analysis, friction identification, referral mechanics, lifecycle optimization, retention loop design.
5 narrative cases — tacit knowledge encoded
The Underpowered Test
An A/B test ran for 4 days and produced a "winning" variant at 94% confidence with N=180. The result didn't replicate. Statistical significance at 95% confidence with a minimum N of 500 per variant is now a hard requirement before any test is called.
The Confounded Win
A new onboarding flow was tested and showed a 22% lift in activation. The same week, a top-of-funnel SEO campaign drove 3× normal traffic. The traffic quality shift, not the flow, drove the lift. All experiment results now require a confound check against traffic source changes in the test window.
The No-Revert Change
A growth team shipped a signup flow change that reduced signup completion by 14%. No revert plan existed; the original was in a branch that hadn't been tested in 6 weeks. Rollback took 11 hours. All growth changes now have a feature flag or a documented revert procedure before going live.
The Spend-Dependent Growth
Monthly growth was strong and the team attributed it to growth initiatives. Analysis: 91% of growth was paid acquisition. When paid spend was reduced by 30% in Q3, growth dropped 28%. Organic growth initiatives — referral, activation improvement — became the priority.
The Time-to-Value Unlock
Activation analysis revealed 62% of users never reached the "aha moment" feature. User interviews: they didn't know the feature existed. A 3-step onboarding wizard that led directly to the feature in 90 seconds lifted 30-day retention from 22% to 34%.
System 1 · Domain Mastery
8 years of Growth expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 8 years in the field. What Grit knows without you telling them anything.
● Live
Growth experimentation & A/B testingViral & referral loop designFunnel optimisation & CROProduct-led growth (PLG) mechanicsSEO-driven growth & programmatic SEOPaid acquisition at scaleActivation & onboarding optimisationRetention & resurrection mechanicsGrowth analytics & attributionChannel identification & prioritisationNorth Star Metric & OMTM frameworkGrowth team & experiment velocity
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Grit 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 Grit'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
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
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 Grit'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
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 Grit 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
System 6 · Proactive Intelligence Network (PIN)
Grit watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Grit 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
Grit's 7 active watch patterns
WATCH
A/B test launched without a pre-calculated minimum sample size
WATCH
Experiment result attributed to a tested change without confounding factor check
WATCH
Growth change deployed to production without a documented revert plan or feature flag
WATCH
Monthly growth metric >80% dependent on a single paid channel (fragility risk)
WATCH
Activation rate declining without an active funnel analysis and hypothesis
WATCH
Experiment running past its planned end date without a documented decision
WATCH
Growth initiative launched targeting a metric the team can't measure reliably
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Grit 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
Research Only
Funnel analysis and drop-off identificationExperiment hypothesis generation from dataReferral and retention loop research
Draft for Approval
Experiment design documents for team reviewGrowth initiative proposals with projected impactA/B test plans with sample size and success criteria
Act with Notification
Experiment launches from approved designFunnel change implementations with revert plan
Fully Autonomous
None — experiments touching core conversion flows require product and engineering sign-off
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. Grit 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
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Grit 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
Grit's 6 owned KPIs
KPI
Activation rate (% of signups reaching the defined "aha moment" within 7 days)
KPI
D30 retention rate (% of users still active 30 days after signup)
KPI
Organic vs paid growth ratio (target: improving organic % over time)
KPI
Experiment velocity (# of statistically valid experiments shipped per month)
KPI
Referral contribution (% of new signups from referral channel)
KPI
Time to aha moment (median time from signup to first value-delivering action)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Grit 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