Calm systems for high-stakes decisions
The three most important doors on this site.
For leadership teams, operators, and organizations trying to move past vague AI enthusiasm into real understanding and usable workflow change.
Repository world-state orientation: deterministic brokered context, bounded widening, and hybrid retrieval validation exercised across real repos.
Explore MímirThe working architecture: memory substrate, repository self-model, routing harnesses, capability-forging lanes, and cross-project governance.
Browse ProjectsSenior Systems & Applied AI Engineer building memory substrates, repository self-modeling systems, orchestration runtimes, and trust-calibrated evaluation surfaces. I come from healthcare, operations, and hands-on systems building, so the standard is still practical usefulness under real constraints.
Core capabilities: durable memory systems, bounded routing/orchestration, evaluation harness design, and founder-grade implementation discipline.
Most teams think they are hiring someone to build AI systems.
What they usually discover, later and more expensively than they wanted, is that the model was never the whole problem. The hard part is getting the system around it to behave in the real world: defining the right task, knowing whether memory is helping or just making the prompt heavier, making tool use reliable instead of theatrical, and designing evaluation that predicts real outcomes instead of reassuring numbers.
That is the layer I have been working on. I am less interested in whether a model can do something once than whether a system can do it repeatedly, legibly, and with failure modes you can actually live with.
How I think about AI systemsThese are not disconnected demos. They are connected system layers: memory substrate, topology/orientation, routing control, capability proving, and ecosystem governance.
Model-agnostic memory substrate with card, evidence, and policy-state primitives plus deterministic rehydration for agent runtimes.
Repository self-model and world-state orientation layer with deterministic brokered rehydration and cross-repo validation across real engineering repos.
Cross-project atlas that defines ownership boundaries, capability contracts, terminology, and overlap-risk closure across the ecosystem.
Assistant orchestration proving ground where routed lanes, memory providers, and failure handling are exercised under runtime constraints.
Client-facing local-first companion runtime centered on identity continuity, persona control, and avatar-aware interaction.
Bounded capability-forging service focused on trust-calibrated wrapper lanes, verifier-backed review bundles, and promotion gating.
Profile-aware specialist-routing harness for multi-lane inference experiments with explicit degraded modes and measurable control profiles.
The graph below shows the architecture thread from runtime proving to durable memory, repository world-state orientation, and cross-project boundary control.
Assistant orchestration proving ground where routed lanes, memory providers, and failure handling are exercised under runtime constraints.
Client and identity surface
Client-facing local-first companion runtime centered on identity continuity, persona control, and avatar-aware interaction.
Routing and lane instrumentation
Profile-aware specialist routing with constrained research lanes and non-authoritative shadow characterization.
Profile-aware specialist-routing harness for multi-lane inference experiments with explicit degraded modes and measurable control profiles.
Experimentation waves
Audio-first deterministic submarine simulation designed for fast iteration, replay traces, and headless testing.
Automated playtesting
Automated playtesting system built specifically to exercise SubSim through deterministic simulation runs.
Local-first autonomous media pipeline that converts news signals into scripted, rendered, and packaged short-form broadcasts.
Coding arena platform for challenge publishing, controlled execution, and repeatable submission scoring.
Commission work (applied competencies)
Commissioned applied competency project for secure accounting ingestion, OCR review, and export workflows.
Inventory/vision exploration
Inventory and intent platform spanning Android client workflows, enterprise APIs, and optional vision evaluation services.
Commissioned applied competency project for modular trading research and policy-driven execution planning.
Commissioned applied competency project for deterministic strategy evaluation and replayable market decisions.
Started as embedded memory experiments inside FRIDAY/Lex.
Model-agnostic memory substrate with card, evidence, and policy-state primitives plus deterministic rehydration for agent runtimes.
Now a standalone memory substrate for cards, evidence, policy-state, and deterministic rehydration.
Repository orientation branch
Extends memory work into repository world-state orientation, brokered context, and bounded cross-repo export.
Repository self-model and world-state orientation layer with deterministic brokered rehydration and cross-repo validation across real engineering repos.
Ecosystem atlas and boundary governance
Cross-project atlas that defines ownership boundaries, capability contracts, terminology, and overlap-risk closure across the ecosystem.
Bounded capability proving lanes
Wrapper lane graduated; adjacent-lane transfer proving remains intentionally narrow and safety-gated.
Bounded capability-forging service focused on trust-calibrated wrapper lanes, verifier-backed review bundles, and promotion gating.
Next-generation assistant runtime unifying agency, Muninn memory, and identity continuity.
The full index includes core architecture systems, adjacent experiments, and commissioned competency work.
Cross-project atlas that defines ownership boundaries, capability contracts, terminology, and overlap-risk closure across the ecosystem.
Assistant orchestration proving ground where routed lanes, memory providers, and failure handling are exercised under runtime constraints.
Next-generation assistant runtime unifying agency, Muninn memory, and identity continuity.
Client-facing local-first companion runtime centered on identity continuity, persona control, and avatar-aware interaction.
Repository self-model and world-state orientation system that brokers bounded rehydration for coding agents across evolving codebases.
Model-agnostic memory substrate with card, evidence, and policy-state primitives plus deterministic rehydration for agent runtimes.
Inventory and intent platform spanning Android client workflows, enterprise APIs, and optional vision evaluation services.
Commissioned applied competency project for modular trading research and policy-driven execution planning.
Profile-aware specialist-routing harness for multi-lane inference experiments with explicit degraded modes and measurable control profiles.
Coding arena platform for challenge publishing, controlled execution, and repeatable submission scoring.
Commissioned applied competency project for deterministic strategy evaluation and replayable market decisions.
Local-first autonomous media pipeline that converts news signals into scripted, rendered, and packaged short-form broadcasts.
Automated playtesting system built specifically to exercise SubSim through deterministic simulation runs.
Bounded capability-forging service focused on trust-calibrated wrapper lanes, verifier-backed review bundles, and promotion gating.
Audio-first deterministic submarine simulation designed for fast iteration, replay traces, and headless testing.
Commissioned applied competency project for secure accounting ingestion, OCR review, and export workflows.
Whether you want help designing a trustworthy AI system layer, pressure-testing an architecture direction, or exploring Mímir as a foundational component, I am open to serious conversations.