Lead AI Product Engineer · Agent Governance · Verifiable Autonomy
Bicameral · MythologIQ Labs · Microsoft Agent Governance Toolkit · AgenTrust
Governance by prompt is not real governance. I build agent systems where authority, provenance, validation, and release decisions are enforced outside the model's own reasoning.
I build products and infrastructure across local-first AI, agent governance, career technology, governed software delivery, and verifiable agent state.
- Production agent systems: governed runtime, MCP, evidence ingestion, authority boundaries, deterministic validation, and release evidence at Bicameral.
- Independent products: local-first user-facing systems spanning Career Ops, product marketability, and voice AI.
- Agent infrastructure: reusable skill knowledge, local orchestration, memory, inference, and governed execution.
- Enterprise systems: a longer-term Qortara product family for governed memory, software delivery, operator visibility, and runtime policy enforcement.
- Open-source governance: listed maintainer on Microsoft's Agent Governance Toolkit and contributor to AgenTrust Agent Manifest.
| Tier | Projects | Status |
|---|---|---|
| Primary side projects | Job Ranger · Viable · This Voice Thing | Active product development |
| Active infrastructure | skillz · COREFORGE | Active; COREFORGE remains under development and its source is private |
| Enterprise direction | Agent Memory · Qortara Logic · Qortara SDLC · Qortara Navigator · Qortara Governance | Enterprise-tier product architecture at varying stages of implementation |
| Foundational lineage | FailSafe · Qor-logic | Earlier systems that established patterns carried forward; Qor-logic is frozen and superseded |
| Area | Contribution | Evidence |
|---|---|---|
| Job Ranger | Built and shipped a local-first Career Ops product for career direction, evidence-backed opportunity assessment, truthful application materials, and deliberate job-search workflows. | Repository · v1.2.0 |
| Viable | Local-first marketability operating system connecting product truth, ICP discovery, market evidence, campaigns, outcomes, and learning. | Repository |
| This Voice Thing | Windows-first local voice-AI workbench with multiple TTS engines, voice cloning/design, narration, transcription, model management, and a local API. | Repository |
| skillz | Passive, provenance-aware skill knowledge resource for agents, with first-party skills and exact-version third-party review evidence. | Repository |
| Agent Memory | Enterprise-directed reference architecture for governed memory, lifecycle, forgetting, provenance, conformance, and runtime evidence. | Repository · ADR-021 |
| Qortara Governance | Deterministic tool-dispatch policy enforcement for agent frameworks, with a public local enforcement layer and a hosted enterprise boundary. | Repository |
| Microsoft Agent Governance Toolkit | Governed accumulated context across delegated multi-agent workflows; contributor trust and MCP verification work. | Maintainers · PR #2800 · PR #2852 |
| AgenTrust · Agent Manifest | Designed the v0.2 incremental memory checkpoint/delta binding protocol for governed persistent state. | Issue #174 · PR #190 |
| Bicameral | Governed acquisition, redaction, provenance, decision evidence, and fail-closed validation in a production agent stack. | PR #269 · PR #287 |
- Uncertainty may propose. Authority constrains. Durable consequences require bounded permission.
- Provenance over phrasing. Where an instruction, memory, artifact, or decision came from matters more than how confidently it is worded.
- Negative paths are part of the contract. Replay, stale state, residual data, partial failure, and unauthorized mutation must have defined behavior.
- Evidence should outlive the agent. Important decisions need inspectable artifacts, not a claim that the model considered them.
Languages: Python · Rust · TypeScript · Go
Agent systems: MCP · orchestration · local inference · RAG · governed memory
Security / trust: policy engines · capability mediation · provenance · redaction · tamper-evident evidence
Platform: GitHub Actions · Docker · PostgreSQL · SQLite · FastAPI · Tauri
MythologIQ Labs, LLC · governed agents · verifiable trails · accountable autonomy