Marketing Engineering with AI · Coming soon
Stop spending Monday morning building the weekly report for the CEO
For marketers and analysts who turn numbers into a weekly update for leadership by hand. You build a one-page dashboard of the few measures leadership acts on, with a definition for each, and an agent that drafts the weekly update on what changed and why — checked so every number it writes matches the data.
The course: The five-minute executive dashboard and a weekly narrative agent
$25 $49 early-bird price
This course is being built now. Join the early-access list to reserve the early-bird price and shape what it covers.
Joining the list is free. You only pay if you buy at launch, at the $25 early-bird price.
If this sounds like your week
- Monday morning goes to logging into GA4, the ad platforms and the store and copying numbers into a slide.
- The dashboard gains charts every quarter, and leadership still asks you what happened.
- Two people bring two revenue numbers, and the meeting goes to deciding which one is right.
- You would let AI draft the update, but one wrong number in front of the CEO costs more than the hours it saves.
What you do now, and where it stops working
Today you export, paste and write the summary yourself, or paste the numbers into a chatbot and check every figure it writes by hand. The first costs a morning each week. The second saves the writing and adds a new risk: a confident sentence with a number that is not in your data.
What changes after the course
- Leadership reads one page with a handful of measures, each against the prior period.
- Every measure has a written definition and source, so a number means one thing to everyone.
- Each week an agent drafts what changed and the likely reasons, and you edit instead of write.
- Before the update goes out, a check flags any number or claim in the draft that does not match the data.
How it works: Cut, define, draft, verify
- 1Cut: choose the measures leadership makes decisions on and drop the rest from the page.
- 2Define: write a definition and a source for each measure, so the revenue argument ends before the meeting.
- 3Draft: the narrative agent reads the week’s data and writes what changed and why into your update template.
- 4Verify: every number and claim in the draft is checked against the data, and anything that does not match is flagged for you before you send.
What you get
- Dashboard template with measure definitions
- Narrative agent prompt and code
- Weekly update template
- Claim-checking checklist
- Video walkthrough of the dashboard and agent
This is for you if
- You assemble the weekly marketing update for a founder, CEO or leadership team.
- You have a dashboard, but leadership asks you instead of opening it.
- You want AI to draft the update and need a way to trust the numbers it writes.
Skip it if
- You need a data warehouse or BI platform rollout. This course is one page and one agent.
- You want the update sent with no person reading it. The course keeps you on the final check.
Before you join
- Will the AI make up numbers?
- It can. Language models write plausible figures that are not in the data. That is why the agent only drafts, and a claim check compares every number it writes against the dashboard data and flags mismatches. You still read and send the final update.
- Our data is scattered across tools. Do I need a warehouse first?
- No. The page needs a handful of measures, and the course shows which sources each one comes from. If you later want a modelled warehouse behind it, the dbt course on this site covers that build.
- Do I need to code?
- The dashboard, definitions and update templates need no code. The narrative agent comes as a prompt plus code; running it means following the setup steps and editing a configuration script.
- Do I need to share my company’s data?
- No. You practise on public data: Google’s GA4 sample from its merchandise store and the public Olist e-commerce dataset. Pointing the page and the agent at your own sources comes last, on your own systems.
- The course is not out yet. What am I signing up for?
- An early-access list. You get updates as modules are built, and at launch you can buy at the $25 early-bird price instead of the $49 list price, or not buy at all.
Rather have it built for you? Describe the project and the same work can be done for your team.