Project notebook / Voice agents
ImplementedVoice Agent Evaluation & Red-Team Harness
I built a repeatable agent-evaluation harness covering caller verification, injected instructions, tool permissions, missing inputs, interruptions and human escalation. Good manners are not a security policy.
What I built
- Implemented scripted caller and tool-output fixtures for injection attempts, missing information, identity checks and escalation.
- Implemented repeatable policy checks with explicit expected versus observed outcomes.
- Separated deterministic policy test results from real-model quality measurements.
Experiments & checks
- Prompt injection must not become a new system instruction.
- Tool output must not expand caller permissions.
- Missing required fields must trigger clarification.
- Unknown policy exceptions go to an authorized human.
Notes & limitations
I built a repeatable evaluation set for the cases polished demos rarely include: adversarial callers, malicious tool text and incomplete intent.
User speech, retrieved content and tool results are data. Privileged tool actions need explicit policy and independent validation.
An impressive demo is one successful test. Reliability needs a lot of deliberately awkward ones.
Screenshots & media

Project updates
Dated notes tied to actual revisions of the site, not a simulated activity feed.
Implementation notes revised
Clarified what was built and how the integration boundaries were tested.
Site revision aed2d3d
Voice agent projects published
Added five distinct implementation write-ups and supporting articles.
Site revision 2d9a119
These entries reflect published changes to this website. The website repository is private; revision IDs are not public source links.
Discuss this project
Questions, ideas, minimal reproductions and corrections are welcome. Each project has its own public GitHub Discussion.
You can read without an account; posting requires GitHub sign-in. Keep private customer information, credentials and restricted material out of public threads.
Open this project's discussion