- Industry
- Insure AI
- Department
- Design
- Team
- Product Experience
- Kind
- Assistant
- Approver
- Head of Distribution
- Code
- DSN-03
It builds clickable prototypes of insurance journeys for testing, such as a new home quote, photo-led FNOL or a broker renewal screen, with realistic but synthetic policy and claim data. It writes the test tasks and never uses real policyholder or claimant records in a prototype.
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 agent and broker portal: the current screens and components for the journey..
- 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 Distribution with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the agent and broker portal: it publishes the prototype link and test plan to the research page. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The prototype kit, synthetic test personas (policyholders, claimants, brokers), task templates and the data rules for research.
Reads from
the agent and broker portal: the current screens and components for the journey.
Acts in
the agent and broker portal: it publishes the prototype link and test plan to the research page.
Hands back
An object with journey, screens (a list), personas (a list), tasks (a list, each with task, hypothesis and success_criteria), fidelity and data_notes.
Asks a person when
The prototype would use real customer data, or will be tested with real policyholders or brokers outside the company.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Most tasks per session | 5 | Sessions stay focused. |
| Session length (minutes) | 45 | Tasks fit this time. |
| Default fidelity | medium | When not asked. |
| Synthetic data only | On | When on, prototypes never contain real policy, claim or health data. |
| Show realistic prices | Off | When off, prices are marked as examples so testers do not anchor on them. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- When on is true, use synthetic personas only; never real policies, claims or health data.
- Build at medium fidelity unless asked otherwise.
- Write at most 5 tasks that fit 45 minutes, each tied to a hypothesis.
- When off is false, mark every premium as an example.
- Include decline and referral paths, not only the happy path.
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.