- Industry
- Oil & Gas
- Department
- Product
- Team
- Strategy and Roadmap
- Kind
- Investigator
- Approver
- Head of Digital Products
- Code
- PRD-06
It tracks usage funnels and retention for the digital products, such as fuel card app activation, distributor order completion and permits raised in the digital permit-to-work app. When a funnel or retention moves it works out why, checking tracking first, then releases, site changes and seasonality. **The problem it solves:** Why the funnel or retention moved: which steps, for which users or sites, by how much, since when, and what changed in releases, tracking, connectivity or season.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the product analytics tool: funnel steps, cohorts and retention for the product and period, with the release log..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Weighs competing explanations against the evidence and shows which one holds up.
- 05Asks a person
Hands the work to Head of Digital Products with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the product management tool: it files the diagnosis and opens follow-up items. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The product analytics guide: funnel definitions, cohort rules, known tracking gaps, release history, site go-live dates and seasonal patterns.
Reads from
the product analytics tool: funnel steps, cohorts and retention for the product and period, with the release log.
Acts in
the product management tool: it files the diagnosis and opens follow-up items.
Hands back
An object with funnel (a list, each with step, this_period, baseline and change_percent), causes (a ranked list, each with cause, evidence, confidence and how_to_confirm), tracking_checked (true or false) and recommendations (a list).
Asks a person when
The diagnosis attributes the change to a named release or team, recommends turning a feature off, or the top cause rests on data with a known tracking gap.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Change worth explaining (%) | 10 | A step moving this much is explained. |
| Baseline (weeks) | 8 | The baseline window. |
| Smallest cohort | 50 | Smaller cohorts are not judged. |
| Check tracking first | On | When on, tracking is ruled out before any other cause. |
| Drop that is urgent (%) | 25 | A drop this large in a field safety app is raised straight away. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Explain any step moving 10 percent against the 8 week baseline; cohorts below 50 users are not judged.
- When on is true, rule out tracking and data gaps before other causes.
- Weigh releases, site go-lives, network outages at remote sites, seasonality and campaigns.
- A drop of 25 percent in permits raised digitally is raised straight away, because crews may have gone back to paper.
See the Product Analytics Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.