Tendril — AI Lessons for Real Life

Tendril

The weekly Stripe one-pager

Export a Stripe Sigma query (or CSV) covering the last 90 days

Feed it to Claude with your product's pricing tiers as context

Ask for: MRR movement, top 5 at-risk accounts, failed-charge patterns

Flag dispute rate — over 0.75% and Stripe starts paying attention

Pipe the weekly summary into Slack every Monday 8am

The real win is catching failed charges early. A 4% involuntary churn rate is normal; a 12% one means your dunning emails are broken and you're bleeding cash silently.

-- Stripe Sigma: at-risk customers (last 30d) SELECT c.email, c.id AS customer_id, COUNT(ch.id) AS failed_charges, SUM(ch.amount)/100.0 AS failed_usd, MAX(ch.created) AS last_failure FROM charges ch JOIN customers c ON c.id = ch.customer WHERE ch.status = 'failed' AND ch.created >= CURRENT_DATE - INTERVAL '30 days' GROUP BY c.email, c.id HAVING COUNT(ch.id) >= 2 ORDER BY failed_usd DESC LIMIT 20;

Good is when you know your MRR, net churn, and top 3 at-risk accounts by heart every Monday — and your recovered-charge revenue pays for your AI bill.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-biz2-stripe-dashboard-ai-adults

What is the main idea of "Reading Your Stripe Dashboard With AI"?

Use Claude and Digits to turn noisy Stripe data into a weekly one-pager you'll actually read.
Use AI as the final authority for the whole decision
Avoid checking the answer once it sounds polished
Focus only on speed instead of judgment

Which concept is most central to "Reading Your Stripe Dashboard With AI"?

Stripe Sigma
financial analytics
cohort analysis
dunning

Which use of AI fits this topic best?

Let the AI decide what matters without your review
Use the answer before checking whether it fits the situation
Export a Stripe Sigma query (or CSV) covering the last 90 days
Treat the AI output as automatically correct

What should a careful learner remember about "Don't share raw Stripe exports with random LLMs"?

Customer emails and charge IDs are PII. Use Claude with a zero-retention workspace or redact emails first.
Skip the context so the tool can guess faster
Treat the output as private even after sharing it online
Use the answer without checking the source

You want to use AI after this lesson. What is the safest next step?

Act immediately because the AI answer is written clearly
Use AI as a workflow assistant, with human review for decisions that carry risk.
Hide uncertainty so the final answer looks cleaner
Use private or sensitive details before checking permission

How should AI output about financial analytics be treated?

As proof that no other source is needed
As a replacement for context, consent, or expert review
As a draft or helper output that still needs human judgment and verification
As something that becomes correct when it sounds confident

Name one way to verify an AI answer about financial analytics.

Which action would help you apply "Reading Your Stripe Dashboard With AI" responsibly?

Use the tool to avoid thinking through the tradeoff
Keep going even if the output conflicts with a trusted source
Treat the AI output as automatically correct
Feed it to Claude with your product's pricing tiers as context

The weekly Stripe one-pager

Export a Stripe Sigma query (or CSV) covering the last 90 days

Feed it to Claude with your product's pricing tiers as context

Ask for: MRR movement, top 5 at-risk accounts, failed-charge patterns

Flag dispute rate — over 0.75% and Stripe starts paying attention

Pipe the weekly summary into Slack every Monday 8am

The real win is catching failed charges early. A 4% involuntary churn rate is normal; a 12% one means your dunning emails are broken and you're bleeding cash silently.

Good is when you know your MRR, net churn, and top 3 at-risk accounts by heart every Monday — and your recovered-charge revenue pays for your AI bill.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-biz2-stripe-dashboard-ai-adults

What is the main idea of "Reading Your Stripe Dashboard With AI"?

Use Claude and Digits to turn noisy Stripe data into a weekly one-pager you'll actually read.
Use AI as the final authority for the whole decision
Avoid checking the answer once it sounds polished
Focus only on speed instead of judgment

Which concept is most central to "Reading Your Stripe Dashboard With AI"?

Stripe Sigma
financial analytics
cohort analysis
dunning

Which use of AI fits this topic best?

Let the AI decide what matters without your review
Use the answer before checking whether it fits the situation
Export a Stripe Sigma query (or CSV) covering the last 90 days
Treat the AI output as automatically correct

What should a careful learner remember about "Don't share raw Stripe exports with random LLMs"?

Customer emails and charge IDs are PII. Use Claude with a zero-retention workspace or redact emails first.
Skip the context so the tool can guess faster
Treat the output as private even after sharing it online
Use the answer without checking the source

You want to use AI after this lesson. What is the safest next step?

Act immediately because the AI answer is written clearly
Use AI as a workflow assistant, with human review for decisions that carry risk.
Hide uncertainty so the final answer looks cleaner
Use private or sensitive details before checking permission

How should AI output about financial analytics be treated?

As proof that no other source is needed
As a replacement for context, consent, or expert review
As a draft or helper output that still needs human judgment and verification
As something that becomes correct when it sounds confident

Name one way to verify an AI answer about financial analytics.

Which action would help you apply "Reading Your Stripe Dashboard With AI" responsibly?

Use the tool to avoid thinking through the tradeoff
Keep going even if the output conflicts with a trusted source
Treat the AI output as automatically correct
Feed it to Claude with your product's pricing tiers as context