Urgent work starves strategy. We give teams AI agents they can trust.
Led by Andy Woolterton — two decades in enterprise architecture and AI strategy. Building governed agent systems for insurance and professional services.
Proof in the real world
After-Image · Creative venture
Built a luxury photography brand from zero using NullProof's own framework. Multi-Clock Work handled strategy, governance, and back-office operations — freeing the founder to focus on client-facing creative work. Live, taking commissions.
Proves: governed creative operations at commercial scale.
Visit After-Image →Portfolio Exposure Radar · Insurance
Continuous intelligence for emerging risk. 13 source workflows monitoring regulatory, litigation, scientific, and market signals. Cross-referenced against client portfolios with automated scoring and agent-driven escalation.
Proves: insurance-grade signal monitoring under governance.
See the signal architecture →NullProof Studio · Internal pilot
Built the operating system that runs this studio. One human, governed AI agents, ninety days from zero to production. Live, taking commissions.
Proves: the studio runs on its own platform.
See the operating model →What we build
Governed agent systems
AI agents that operate under explicit trust boundaries. Durable event queues, belief graphs, hallucination detection, three-stage validation with supervisor arbitration. The governance isn't bolted on — it's the architecture.
See the operating model →Insurance & risk infrastructure
Signal monitoring across regulatory, litigation, scientific, and market sources. Claims processing with FNOL routing. Portfolio exposure scoring. Built for brokers and underwriters who need to know what changed overnight.
See the signal architecture →Open-source tooling
en-quire: an MCP server for governed markdown and YAML editing. Section-level addressing, RBAC, git-native approval workflows, full-text search. Works in any language. On npm and Docker Hub.
GitHub → nullproof-studio/en-quireFrameworks you can study. Engagements you can commission. A platform you can run.
Platform
AI orchestration without vendor chaos.
MCP-native client that keeps Notion, Claude, OpenAI, and local models in one continuous state — swap providers without losing the thread.
Preview →Field Notes
Governance protocols for teams managing competing priorities.
Multi-Clock Work, Bandit Scoring, strategic outcomes mapping, and AI delegation guardrails — documented as runnable field guides.
Start reading →Practice
Embedded systems design for your team.
4–12 week architecture sprints: prioritisation models, AI governance protocols and context workflows tailored to how your organisation actually works.
See engagement types →From the Codex · Field Notes
Field notes from building agent systems in production. Not theory — operational decisions, trade-offs, and what we learned.
Important work ages in the background while urgent noise fills every hour. To stop this, organisations must move beyond static frameworks—the 'pillars'—and adopt a kinetic operating system that governs how work is filtered, orchestrated, and dispatched across a hybrid workforce of humans and autonomous agents.
Published agentic AI stack architectures — five-layer, seven-layer, and nine-layer frameworks in common circulation, alongside Microsoft's own agentic AI roadmap reviewed as of April 2026 — cover compute, models, orchestration, tooling, and observability. None include trust as a named layer. Agents can hold wallets, execute payments, and submit documents - they just can't prove who they are. This paper examines why the identity layer is missing from agent runtimes, how existing standards (W3C DIDs, Verifiable Credentials) can fill the gap, and why the window to build it openly is now.
Every governance framework in use today embeds trust assumptions calibrated on decades of human behaviour. Agents break those assumptions. This paper argues that trust management - the explicit identification, assessment, and governance of trust signals - needs to become a discipline in its own right, with registers, scoring, thresholds, and continuous monitoring, paralleling how organisations already manage risk.
Agents that manage documentation need more than file access — they need structure, governance, and the ability to edit precisely without reading everything. en-quire gives them that: section-level editing, searchable document structure, and git-native approval workflows, all without imposing a schema on your markdown.
Studio
Founder, Designer, and Chief Architect. Two decades in enterprise architecture, AI strategy, and creative systems design. Creator of the Multi-Clock Work framework for managing creative operations across time horizons.
Human accountability. Governed agents. Proof in every deliverable.