AI agent systems with small, revocable authority
I am an AI engineer and consultant. I build AI agent systems that run with small, revocable authority, and the evals that check them. I also set up AI coding agent workflows for small dev teams.
I am based in Dallas-Fort Worth. I work with clients in Dallas-Fort Worth and Oklahoma City, remotely or on site.
I reply within two working days. NDA on request.
Ways to start
Each offer has a fixed scope and a clear result. You get a quote after the intro call.
-
Computer Vision / AI Agent Prototype
3-4 weeks- For
- Teams that want to test an AI idea on their own data.
- You get
- A working demo with metrics and a clear go / no-go note.
-
AI Dev Workflow Setup
1-2 weeks- For
- Small dev teams that want to use AI coding agents safely.
- You get
- Agent rules files, a worktree workflow, a verify command, and session hand-off tools.
What I have built
Client work uses codenames. I can share more detail under an NDA.
- A competitive arena: agents enter challenges, stakes go to escrow, results are verified automatically, winners are paid.
- A wallet program with session keys, spend limits and program allow-lists. Seven formal proofs check the policy logic.
- An agent fleet: 28 agent roles across 6 profiles on a locked-down server, with each profile in its own sandbox.
- An autonomous training loop: an agent checks a run, reads the result, picks the next experiment and launches it.
- Agent rules files, session hand-off and pickup tools, and isolated worktrees, so many coding agents can work at once.
See the proof: Agent Systems: AI agent platforms: escrow, spend limits and a hardened agent fleetHarness Engineering: LLM eval harnesses and AI agent evaluation with pass / fail / error verdicts
Questions
- How do you keep an AI agent safe?
- I give each agent small, revocable authority: session keys that expire, spend limits and allow-lists. Code checks the result. The opinion of another model does not decide.
- What does an AI agent prototype include?
- A working demo on your own data, with metrics and a clear go / no-go note. It takes three to four weeks.
- Can you help my team use AI coding agents?
- Yes. The AI Dev Workflow Setup gives your team agent rules files, a worktree workflow, a verify command, and session hand-off tools. It takes one to two weeks.
- How do you test an AI agent?
- Every agent change meets an eval harness. The harness returns pass, fail or error. A check that cannot run returns error and alerts a person. It never counts as a pass.
- Where do you work?
- I am based in the Dallas-Fort Worth area. I work with clients in Dallas-Fort Worth and Oklahoma City. I also work remotely with teams anywhere, and I travel to work on site when it helps.
Tell me what you are building.
30 minutes. Tell me what you are building. I reply within two working days. Client details can stay private under a mutual NDA.