# Ben Downey

> Co-founder and engineer. Building and measuring AI agent systems. A structured interview on AI evaluation, engineering and evidence. Every answer leads with the answer, then the evidence and its limits.

Answer ids (q01, sme04, e02, r4) are stable and identical across the page, the JSON and the markdown. Skills carry self-ratings on a 0 to 4 scale, each with its evidence. Every answer says what I decided and what I checked.

## Interview
- [Interview, markdown](https://www.bendowney.com/interview.md): every answer with its detail, limits and what I decided
- [Interview, JSON](https://www.bendowney.com/interview.json): the same content as structured data, including rated skills
- [JSON Schema](https://www.bendowney.com/interview.schema.json): field definitions for the JSON
- [Interview page](https://www.bendowney.com/interview/): the version for people

## Code
- [DXdev on GitHub](https://github.com/dxdev-inc)
- [agent-scorecard](https://github.com/dxdev-inc/agent-scorecard)
- [agent-guardrails](https://github.com/dxdev-inc/agent-guardrails)
- [agent-memory](https://github.com/dxdev-inc/agent-memory)

## Optional
- [Verify, do not assume](https://dxdev.com/blog/agent-verification-before-claiming-success/)
- [All green does not mean all tested](https://dxdev.com/everyday-ai/all-green-doesnt-mean-all-tested/)
- [Verify the AI reviewer's checkable claims](https://dxdev.com/blog/verify-the-ai-reviewers-checkable-claims/)
- [A rubric verifier for autonomous workers](https://dxdev.com/blog/rubric-verifier-autonomous-workers/)
- [The Hotfix That Lied](https://dxdev.com/blog/jira-staging-live-never-merged-to-master/)
- [Home page](https://www.bendowney.com/)