What if I don't have PostHog — can Tycoon Agent use something else for activity?

Yes. Tycoon Agent works with Mixpanel, Amplitude, GA4 events, or even just Stripe (login = active). With Stripe-only she can do payment retention (still on a paid plan w8 vs paid w1) which is the sharpest business signal anyway.

How does Tycoon Agent define 'retained' for week-N?

Default: any session in week N counts as retained. You can override to a specific event (used core feature X, sent message, completed task) — that's typically the more honest number. Tycoon Agent will show both side-by-side if you want.

What does 'leak hypothesis' actually look like?

Example: "Cohort week of March 4 has w4 retention of 31% vs trailing 8-wk avg of 47%. 68% of that cohort came from a Twitter post about feature X. Retention drops sharpest at day 9 — that's when feature X's free tier limit hits. Likely cause: misleading expectations from the Twitter copy. Action: rewrite the Twitter post or extend trial."

Can I run this on a specific subset — only paid users, only enterprise, only one feature?

Yes. Tell Tycoon Agent the filter ("only Pro plan", "only users from organic search", "only users who hit feature X in week 1") and she re-runs the cohort against that segment. You can have multiple recurring versions side by side.

Ask Tycoon Agent: Run a weekly cohort retention analysis

You'd think this needs a data analyst and a Mode dashboard — Tycoon Agent ships a fresh cohort table to your Lark every Monday at 9am.

The short answer

Tycoon Agent runs a weekly cohort retention analysis by pulling signups from Stripe and behavioral events from PostHog, then bucketing users by signup week and tracking week-1, week-2, week-4, week-8, and week-12 retention. Every Monday she ships a Lark message with the full cohort triangle, week-over-week deltas highlighted, and the one cohort that's leaking worst with a hypothesis on why — usually traced to a specific traffic source or a product change that shipped during their signup week. You stop wondering whether retention is actually improving. You see the curve, you see which acquisition channels produce sticky users, and you get a concrete "this week, fix X" call-out rooted in real numbers. No SQL. No data hire. No more pretending the screenshot from 3 months ago still represents your product.

How Tycoon Agent actually does it

Pull signups + activity
Stripe customer.created events for the cohort definition. PostHog session events for the activity definition (default: any session = retained, configurable to feature use).
StripePostHog
Build the cohort triangle
Group by signup week. Compute week-1, w2, w4, w8, w12 retention as % of cohort still active. Compute WoW deltas vs the prior cohort.
Cross-reference with traffic source + ship log
Tag each cohort with dominant acquisition channel (GA4 source) and any product changes that shipped that week (Vercel deploy log + Linear).
GA4VercelLinear
Find the leak
Identify the cohort with the worst retention vs the 8-week trailing average. Generate hypothesis: which channel? which product change? which onboarding step?
Write the brief
Lark message Monday 9am with the cohort triangle (rendered table), the worst cohort highlighted, the hypothesis, and one concrete action for this week.
Lark

What it looks like in chat

YouSet up a weekly cohort retention analysis. I want to see it every Monday.

Tycoon AgentLocked in. First report runs Monday 9am ET. Setup: **Cohort definition:** signups from Stripe, weekly buckets. **Retention definition:** any PostHog session in the week. (Want stricter? I can use "used core feature X" instead — tell me which event.) **Triangle columns:** w1 / w2 / w4 / w8 / w12 retention %. **Cross-refs:** GA4 channel attribution per cohort, Vercel deploys + Linear shipped tasks tagged to each week. **Output:** Lark message with the rendered triangle, WoW deltas color-coded, the worst cohort flagged with a leak hypothesis, and 1 action. First run will include 12 weeks of backfill so you see the trend immediately. Want me to also email a CSV every Monday for your records?

What you get back

A Lark message every Monday 9am with the full cohort retention triangle, WoW deltas highlighted, the worst-performing cohort called out with a hypothesis, and one concrete action for this week.

Cadence: Weekly Monday 9am, plus on-demand reruns when you ask.

Run a weekly cohort retention analysis automatically