Find the growth loop

Memo: How Tutorly actually grows, and why I would not triple paid

To: Rachel Dunn, exec team From: Staff PM, Growth

Bottom line

1. Our engine is the organic search → profile → review loop. It is stalling at the review step, not at the top of the funnel.
2. Don't triple paid. The last $30k/month we added bought parents at about $319 each, against a $120 paid-parent LTV.
3. 50,000 by the raise isn't reachable with either plan. A credible number is about 41–43k, with a better quality story for diligence.

1. Growth loops

``` PRIMARY: Search/review loop (52% of new parents) Tutor profile -> bookings -> paid lessons -> 3+ reviews ^ | | v more tutors <- tutor earnings <- new parents <- organic profile sessions LEAK: 61% of new profiles get no booking in 60 days -> no reviews -> 4% of sessions

SECONDARY: Parent referral (9%) active parent -> 0.31 invites/mo -> 14% book -> new parent

SUPPLY FEED: Tutor referral (44% of new tutors, $50 at onboarding) -> more profiles

NOT A LOOP: Paid (39%) spend -> parent -> 22% still booking at 6 months. Stops when spend stops. ```

Why organic is primary. It is the largest source and has the best retention, and its output (reviews) feeds its own input (ranking and trust). It compounds for tutors who already have reviews. Profiles with 3+ reviews get 81% of organic sessions, and those with none get 4%.

Why it is weakening: - Tutors grew 62% against parents' 20%, so bookings per tutor fell from 9.1 to 6.8. - Most new supply never gets a first booking, so it never gets reviews or traffic. - Organic sessions grew 40% but parents only 20%. - Top-200-keyword click-through fell from 6.1% to 5.0% (−18%) after the results-page changes.

Parent referral is real but small. Each active parent yields about 0.043 new booking parents a month (0.31 × 14%). Even over 12 months that is about 0.5 per parent, so k is below 1 and it contributes rather than compounds. It is also cheap ($20 credit) and retains well, so it is worth improving.

Data flag: 37,000 parents × 0.043 implies about 1,600 referred parents a month. The 9% attribution implies roughly 150–190. One of these is wrong, and we must reconcile it before it appears in a Series B deck.

Tutor referral pays $50 for onboarding, not for a booking. At least 3,900 of last year's net 8,800 new tutors came this way, so we spent at least ~$190k buying supply that mostly isn't booked.

2. Response to tripling paid

The 2.2 isn't the paid ratio. It divides blended LTV ($210) by paid CAC ($95). Paid parents are worth $120, so paid LTV:CAC is 1.3 on average and 1.1 at the current $109.

The marginal number is worse. Spend went from $60k to $90k, and CPA went from $82 to $109: - New paid parents moved from about 732 to 826 a month. - So $30k bought about 94 extra parents, or roughly $319 each. That is 0.38× their LTV.

If the same curve holds (CPA scaling with spend^0.7, my extrapolation), $270k gives a CPA near $235 and about 1,150 parents a month. The extra $180k a month then buys about 320 parents, roughly $560 each.

The 50k math doesn't work: - We need +13,000 active parents in six months. Last year we added 6,000 in twelve. - Trend alone gets us to about 40k. - The extra ~$1.1M buys about 1,900 gross parents. With 22% still booking at six months, that is roughly +1,000 active parents at the raise, so about 41k. - Even with CPA frozen at $109, which won't happen, it is about 4–5k active and ~45k.

It also dilutes quality. Paid would rise from 39% to roughly 47% of new parents, and blended LTV would fall from $210 to about $195. Series B diligence will cut by source and cohort, and this is the cut that looks worst.

Caveats: this is one quarter of data. Seasonality, competitors and the CTR drop may explain part of the CPA rise. A holdout will tell us how much.

Recommendation: - Return paid to about $60k/month now. - Re-fund only campaigns where measured marginal CAC is ≤$60 (2:1 on $120). - Redeploy about $30k/month into the tests below. - Reframe the raise target as about 42k active parents, rising organic share, and recovering bookings per tutor. I would rather show that than 45k bought at 1.1×.

3. Squads for the next two quarters

Squad 1: New-tutor activation (fix the review leak)

• Test:
• Reserve a results/matching slot for quality-gated tutors with fewer than 3 reviews on new parents' first-lesson bookings.
• Fund a small first-lesson credit for the parent, from the redeployed paid budget.
• The credit is paid at booking, never conditioned on a review. Ask only neutral post-lesson review prompts. Legal should sign off before launch.
• Second arm: move the $50 tutor-referral payout from onboarding to the referred tutor's first completed lesson.
• Threshold:
• The 60-day first-booking rate for new profiles rises from 39% to ≥50% versus control.
• Routed first lessons' rebooking and ratings stay within 3 points of control.
• Cost per referred tutor who gets a booking falls ≥30%.
• Stop: the lift is under 5 points at week 6, or the rebooking/rating guardrail is breached. Then drop the routing and keep only the payout change if that arm hit its threshold.

Squad 2: Search recovery

• Test:
• First, serve the pre-March results layout to 20% of traffic to find out whether the March change caused the CTR drop.
• In parallel, improve snippets on the top 200 keywords (rating and review count, titles, structured data), with keyword-level holdouts.
• Threshold:
• Treated-keyword CTR is ≥5.6% by week 6 while holdouts stay near 5.0%.
• Session-to-booking conversion is flat or better.
• Restoring 6.1% is worth up to +22% clicks on those terms, which is our cheapest growth.
• Stop: under +0.3 points after two iterations (about 8 weeks), or conversion falls. Then move the squad to Squad 1's ranking work.

Squad 3: Parent referral and paid measurement

• Weeks 1–2: reconcile the referral attribution gap, and set up the paid holdout (geo or campaign-level) with analytics.
• Test:
• Trigger the invite prompt after a 5-star or third completed lesson.
• Run a two-sided $20 credit arm against the current one-sided credit.
• Threshold:
• Referred share of new parents rises from 9% to ≥13%.
• Cost per referred booking parent is ≤$45.
• 90-day retention is on track for ≥45% at six months.
• Stop: cost per referred parent exceeds $60, or invites per parent are under 0.36 after six weeks. Then cut referral work to maintenance and move the squad to first-90-day retention of paid cohorts (22% at six months is our biggest leak).

What I'd ask the offsite to decide

1. Cut paid back to $60k and fund the holdout.
2. Approve the squad plan and the tutor-referral payout change.
3. Accept about 42k as the committed target, and have finance model the raise story on retained parents, organic share and bookings per tutor.

I'd revisit paid at the end of Q1 with holdout data. If marginal CAC is ≤$60 in any segment, I'd scale it there.

To: Rachel Dunn and Executive Team From: Staff PM, Tutorly Subject: Grow booking demand, not acquisition spend Planning horizon: Next two quarters

Recommendation

Do not commit to $270,000/month in paid acquisition. Our primary growth engine is organic discovery of proven tutors, reinforced by completed lessons and reviews. That engine is growing, but its distribution is concentrated and its conversion into bookings is weakening. Meanwhile, tutor supply is growing much faster than demand, and paid acquisition has deteriorating marginal economics.

Put our three squads on organic discovery, demand-led tutor activation, and parent referrals. Keep paid acquisition as a tightly gated contributor—not the engine assumed to deliver 50,000 booking parents.

1. How we actually grow

```text PRIMARY: Organic discovery / reputation Search → tutor profile → booking → completed paid lesson → genuine review → stronger discovery/conversion → more bookings

Parent referrals Booking parent → invitation → new booking parent → invitations

Tutor referrals Active tutor → referred tutor → onboarding → additional supply → bookings only if matching parent demand exists

Paid acquisition / reinvestment Spend → new booking parent → repeat lessons → commission → acquisition budget → more spend ```

Organic/reputation: our primary compounding mechanism, but uneven and constrained. Organic supplies 52% of new booking parents, versus paid’s 39% and referrals’ 9%. These parents have 48% six-month retention and $260 net LTV. Completed lessons generate reviews, which can improve subsequent discovery and conversion without buying every next customer.

Profiles with at least three reviews capture 81% of organic profile sessions; unreviewed profiles capture only 4%. This supports the mechanism, but does not establish that reviews alone cause the traffic difference.

The warning signs are substantial:

• Organic profile sessions rose 40%, but booking parents rose only 20%.
• Search CTR fell from 6.1% to 5.0%, an 18% relative decline.
• 61% of recently created profiles had no booking within 60 days—and therefore no reviews.

This is a reinforcing loop concentrated in established profiles, not proof that adding more profiles compounds demand.

Parent referrals: contributing, not yet demonstrably self-sustaining. Each active parent generates:

`0.31 invites/month × 14% conversion = 0.0434 new booking parents/month`

That is 4.34 new booking parents per 100 active parents per month. Even six fully active months produce only 0.26 referred booking parents per parent. We lack lifetime active-month data to calculate a full reproduction rate.

Referral customers are valuable: 51% six-month retention and $275 net LTV, with a $20 credit per successful referral. But the credit alone is not the fully loaded, incremental CAC.

Tutor referrals: contributing supply, with decaying demand yield. They produced 44% of new tutors, incentivized by $50 per onboarded tutor. Tutor count grew 62%, while bookings per active tutor fell 25%, from 9.1 to 6.8.

Multiplying those figures suggests monthly bookings increased roughly 21%—from 129,000 to 156,000—while supply expanded three times as quickly. Onboarding more tutors is not equivalent to growing the marketplace. We cannot establish that tutor referrals are self-compounding; their booking yield is deteriorating.

Paid: contributing customers, with decaying marginal economics. Paid delivers 39% of new booking parents, but only 22% remain booking after six months, and their net LTV is $120. Each $40 lesson yields $7.20 commission, before other costs. Reinvestment is possible only if acquisition leaves enough economic surplus; spend itself is not a compounding advantage.

2. Why tripling paid is not the current answer

The quoted 2.2 LTV:CAC divides blended LTV, $210, by paid CAC, $95. It combines different customer populations.

Paid’s actual ratios are:

• Annual average: $120 / $95 = 1.26
• Latest quarter: $120 / $109 = 1.10

That leaves only $25, then $11, of lifetime surplus per acquired parent on the supplied net-LTV basis.

The marginal picture is worse:

• $60,000/month at $82 CAC bought approximately 732 parents.
• $90,000/month at $109 CAC bought approximately 826 parents.
• The extra $30,000 bought only 94 additional parents: approximately $319 per additional parent.

This before/after comparison is not a controlled incrementality estimate, but it is a strong warning against extrapolating average CAC.

Even if CAC stayed at $109, $270,000/month would acquire approximately 2,477 parents/month. Relative to current spend, that adds roughly 9,900 gross parents over six months, before churn—not the 13,000 net increase required to reach 50,000. Organic and referrals could close part of that gap, but the pack lacks monthly cohort flows needed to forecast it honestly.

Decision: Freeze paid at no more than $90,000/month during a four-week incrementality audit; reduce spend where marginal economics fail. Release additional budget in steps of at most 25%, not a single tripling. Require incremental CAC of $80 or less—a proposed 1.5× paid LTV:CAC hurdle—and no deterioration in cohort quality. Stop any expansion that fails that hurdle. These are management thresholds, not observed performance.

3. Three squads for two quarters

Squad 1 — Recover organic booking demand

Test: Diagnose the CTR decline, then test search-facing changes we control—titles, snippets, profile information and relevant landing experiences—using matched keyword/profile holdouts. Prioritize proven tutors with available capacity. Do not assume we can reverse external search-results changes.

Threshold: Within 8–10 weeks, achieve at least 10% lift in organic first-booking conversion per eligible search impression, with CTR trending toward 5.8% or better, and no deterioration in cancellations or early repeat booking versus control.

Stop condition: Stop variants that improve clicks without incremental bookings. If two adequately powered iterations fail, redirect from presentation fixes to intent and landing-page mismatch.

Quarter two: Scale winning changes; continue measuring completed lessons and cohort retention, not sessions alone.

Squad 2 — Activate supply where demand exists

Test: Pause broad tutor-referral expansion. In underserved subject/time/location segments, test availability guidance and matching that help new tutors earn their first paid, completed lesson. Randomize at market-cluster level to detect displacement from existing tutors.

Threshold: Reduce the 60-day no-booking rate from 61% to 50% or lower, while increasing total completed bookings in treated markets by at least 5%. Require non-negative incremental contribution after intervention costs.

Stop condition: Stop if new-tutor activation merely redistributes existing bookings or worsens cancellations and lesson quality.

Quarter two: Expand only in demonstrated demand gaps. Request honest reviews after completed lessons; never reward reviews or require positive feedback.

Squad 3 — Grow retained demand through parent referrals

Test: Keep the $20 referral credit unchanged. Test referral prompts after successful lessons and repeat bookings against randomized holdouts. Own the paid incrementality audit as the common acquisition-measurement workstream.

Threshold: Raise invitations from 0.31 to at least 0.45 per active parent/month, maintain 14% conversion, and demonstrate at least 25% lift in incremental referred booking parents, with fully loaded incremental CAC below $80 and early repeat booking no worse than control.

Stop condition: Stop prompts that cause annoyance, reduce repeat booking, or merely relabel parents who would have arrived organically. Do not scale on invitations alone.

Quarter two: Scale proven referral treatments; validate six-month retention as cohorts mature.

The offsite should approve these experiments and gates—not an unsupported acquisition forecast. Our objective is 50,000 booking parents, not 50,000 acquired accounts or an ever-larger tutor directory.