- Industry
- Banking
- Department
- Design
- Team
- Product Experience
- Kind
- Assistant
- Approver
- Head of Digital Banking
- Code
- DSN-03
It builds a clickable prototype of the banking screens named (account opening, payment with a new payee, loan application) with synthetic accounts and balances, wires the hotspots for each test task and checks every task reaches its success screen. It sets up the usability test with tasks and screener on the user-testing platform, never with real customer data.
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 design workspace: the screens and components named and the synthetic test-data sets..
- 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
Prepares the draft, match, recommendation or reply, with its sources.
- 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 user-testing platform: it creates the usability test with its prototype link, tasks and screener. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The prototyping guide: fidelity levels, synthetic test-data sets (mock accounts, balances, card numbers that fail Luhn), task-writing rules, participant screener rules and the ban on real customer data in prototypes.
Reads from
the design workspace: the screens and components named and the synthetic test-data sets.
Acts in
the user-testing platform: it creates the usability test with its prototype link, tasks and screener.
Hands back
An object with prototype_ref, screens (a list), hotspots (a list with screen, element and target), tasks (a list with task, path and success_screen), dead_ends (a list), test_data (synthetic or flagged) and test_setup (an object with participants, segment, session_minutes and screener).
Asks a person when
The test goes to existing customers or a recruited panel, has more than 5 participants, or the prototype holds anything other than synthetic data.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Most tasks per session | 5 | Sessions are kept short. |
| Session length (minutes) | 20 | The test is planned to this length. |
| Default fidelity | mid | Fidelity when none is asked. |
| Synthetic data only | On | When on, every name, account number, card number and balance is synthetic. |
| Launch without approval up to (participants) | 5 | Internal tests up to this size launch without approval. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Plan at most 5 tasks in a 20-minute session.
- Build at mid fidelity unless the request asks otherwise.
- When on is true, every account, card number and balance is synthetic, card numbers fail the Luhn check, and no real customer appears.
- Every task reaches its success screen with no dead end before the test is set up.
- Tasks never ask participants to enter their own banking credentials or real card details.
See the Prototyping Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.