- Industry
- Insure AI
- Department
- Engineering
- Team
- Application Engineering
- Kind
- Decision-maker
- Approver
- Engineering Lead
- Code
- ENG-10
It finds and ranks technical debt in the insurance platforms by cost, such as legacy product rules duplicated across policy systems, hard-coded tax rates or a brittle renewal batch, and proposes refactors that pay back. It weighs debt that slows rate changes or product launches highest.
How it works
7 steps, and a person signs off before step 7.
- 01Looks it up
Finds the record the request is about in the code repository: change history, complexity and incident links by component..
- 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.
- 04Forecasts, when it decides
Projects what each option will cost or return before it recommends one.
- 05Works it through
Prepares the draft, match, recommendation or reply, with its sources.
- 06Asks a person
Hands the work to Engineering Lead with its reasoning before anything goes out.
- 07Acts
Once approved, it acts in the code repository: it creates the refactor items in the backlog. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The debt register, hotspots, the cost of incidents and delays per component and the refactor guidelines.
Reads from
the code repository: change history, complexity and incident links by component.
Acts in
the code repository: it creates the refactor items in the backlog.
Hands back
A ranked list of debt items, each with item, component, cost_estimate, refactor, effort, payback_sprints and risk.
Asks a person when
A refactor touches rating or claims payment logic, or exceeds the capacity.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Capacity for debt (%) | 20 | Share of each sprint. |
| Hotspot window (days) | 180 | Change history looked at. |
| Complexity limit | 15 | Above this a function is a hotspot. |
| Largest refactor (lines) | 1500 | Bigger ones are split. |
| Payback within (sprints) | 6 | Refactors must pay back this fast. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Spend at most 20 percent of capacity on debt.
- Rank by cost over 180 days, with debt that slows rate changes, product launches or regulatory changes first.
- Propose only refactors that pay back within 6 sprints and stay under 1500 lines.
- Flag functions over complexity 15 in rating and claims code.
- Never refactor rating logic without the rating test pack passing before and after.
See the Technical Debt Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.