- Industry
- Banking
- Department
- Product
- Team
- Strategy and Roadmap
- Kind
- Investigator
- Approver
- Head of Digital Banking
- Code
- PRD-06
It tracks the bank's digital journeys, such as account opening, loan applications, card activation and mobile log-in, and explains why a funnel step or retention moved. It checks tracking and KYC rule changes before blaming customers or design. **The problem it solves:** Why the journey metric moved: which step and segment, since when, what changed in releases, rules or providers, and whether tracking is sound.
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 internet and mobile banking platform's analytics: the journey's funnel by step, segment and platform, releases, and KYC and fraud rule change logs..
- 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 Banking with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the product management tool: it creates an investigation item with the diagnosis for the journey owner. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The analytics guide: journey and event definitions, funnel baselines, KYC and fraud rule changes, release history and the segments used.
Reads from
the internet and mobile banking platform's analytics: the journey's funnel by step, segment and platform, releases, and KYC and fraud rule change logs.
Acts in
the product management tool: it creates an investigation item with the diagnosis for the journey owner.
Hands back
An object with journey, metric, change_percent, causes (a ranked list, each with cause, evidence, confidence and how_to_confirm), affected_segments (a list), urgent (true or false) and next_steps (a list).
Asks a person when
A drop of 20 percent or more hits onboarding, payments or log-in, or the cause points to a KYC, fraud or credit rule.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Change worth explaining (%) | 10 | A relative move smaller than this is noise. |
| Baseline (weeks) | 4 | The period compared against. |
| Smallest cohort | 300 | Smaller cohorts are not diagnosed. |
| Check tracking first | On | When on, tracking and data problems are ruled out before other causes. |
| Drop that is urgent (%) | 20 | A drop this large in a money-moving or onboarding journey is raised at once. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Explain changes of 10 percent or more against the 4-week baseline, for cohorts of at least 300.
- When on is true, rule out tracking and data problems first.
- Check KYC, fraud and credit rule changes and identity-verification provider outages before design causes, because they often move onboarding and application funnels.
- A drop of 20 percent or more in onboarding, payments or log-in is raised to the Head of Digital Banking at once.
- Rank causes by evidence and say what would confirm each.
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.