Personal Portfolio

Mike Reese

I like inventing things. I'm building agentic systems and the experiments that show whether they work.

mike.reese1212@gmail.comGitHubLinkedInRésumé (JSON)

About

Founded 2 companies, innovated in the heavy equipment industry with a physics-based universal compatibility matching engine based on a graph structure, and currently trying to find the Rosetta Stone for the context layer of LLMs that unlocks purely declarative prompting for long-running tasks in an evolving system. Big proponent of thinking from first principles, removing friction, questioning the status quo, and reducing complex systems down to quantifiable, pure-signal experiments. AKA - just cut the Gordian Knot. So, I'm really enjoying the evolving paradigm and rapid pace at the frontier of AI :-)

Current work

Telos2026 A context and application layer for declarative, long-running agentic work

Selected work

Agentic
  • Software factories
  • Gas City on AWS2026 Forked and hosted the Gas City multi-agent runtime on AWS: one EKS cluster per environment, autoscaled with Karpenter, running about 12 agent crews, one per business domain, communicating via EventBridge. Custom agent packs and role definitions, rewrote Gas City, Dolt and Beads integrations to be Kubernetes-native. AWSContainersPythonGraph dataSkills
  • Loop Harness2026 Ideator → Author → Generator → Evaluator → Judge automated loops over 465 work units folded about 20 repos into monorepos. DAG dependency graph, Observability dashboard, Full telemetry coverage with 'Miner' agents triggered on merges to identify design pattern opportunities, operational complexity improvements, and removal candidates (bloat reduction). Account pool with automated swapping and session resume when limits were hit. PythonHooksSkillsEvals
  • Telos2026 Current Focus. An application layer and context management system for agentic work to facilitate declarative, long-running tasks in an evolving system (which is every system). Purpose is to reduce Drift / Bloat / Sprawl / Regressions over long-running tasks by creating a measure for epistemic understanding with agents. Stateful Knowledgebase to derive the current 'Truth', Self-extending ontology, context / action / effect checks, telemetry on measurable system objectives and agent sessions / turns / tool use for a given declarative prompt. Three prototypes to date. Experiment harness exists solely to facilitate design decisions for this idea. ContainersRustPythonGraph dataFrontendMCPHooksEvals
  • Experiment harness2026 Isolated runtime experiments on agentic techniques. Goal is pure-signal hypothesis testing, prioritizing rapid iteration and validation with toy model repos. Uses Scientific Method - causal claims, control/test arms, measurable outcomes, separate validation environment combining quantitative and qualitative measurements, multiple runs to reduce variance. ContainersPythonSkillsEvals
  • Compatibility engine2024–2026 Invented a universal, physics-based compatibility engine for heavy machinery and attachments. Used inference to project machine and attachment specifications into hardware component-level subgraphs & used set theory to generate the Cartesian product of viable component combinations. Modeled attachment fit for heavy equipment as the intersection of three physical property relationships between linked hardware components: connect, power and lift. 25M-node, 100M-edge graph. AWSPythonGraph data
  • Storefront fitment filter2025 Let Attachments King shoppers filter every product by their machine, beyond what Shopify's collection pages allow, using a Bloom filter per product carried through to checkout. Online-store sales rose 99% in the first month. Frontend
Deterministic

Experiments

G001

Do algebraic design docs improve coding agents' quality, token use, or time against no supplied docs and prose docs?

Hypothesis: Describing a codebase algebraically instead of semantically reduces inference via proofs which reuse repeated reasoning.

  1. E009-E010Generation · fresh codebase · 1 imperative stageOne-stage build: algebraic docs missed the preset quality marginOne build stage, two builder models. Algebraic docs scored below no docs with one model and above with the other, both times by less than the rule's threshold.
  2. E015-E017Generation · fresh codebase · 5 imperative stagesFive-stage builds: algebraic docs missed the quality margin and used more tokensTwo runs, two builder models. The algebraic arm never beat no docs by the rule's threshold and used the most build tokens in both runs.
  3. E018-E025Generation · fresh codebase · 5 imperative stages · z3-checked algebraFive-stage z3 builds: quality margin unmet; tokens fell in both runsTwo repeat runs. The algebra arm proved its design with z3 before coding. Its score stayed close to no docs, and it used fewer build tokens in both runs.
  4. E020-E026Generation · fresh codebase · 7 declarative stages · z3-checked algebraSeven declarative stages: quality margin unmet; tokens rose in three runsThree repeat runs with declarative prompts. The z3-checked algebra arm scored level with or below no docs and used more build tokens in every run.
  5. E022-E023Retrieval · 400k-line codebase · 5 questions · z3-checked algebraDesign docs missed quality and efficiency targets in retrievalTwo builder models answered five questions each. Neither design form met the retrospective +0.1 correctness target and saved tokens and time in both runs.
  6. E024Generation · 400k-line codebase · 5 imperative stages · z3-checked algebraExisting-codebase changes: z3 algebra missed the quality margin and used more tokensThree repeat runs extending an application its design records already describe. No doc form beat no docs by the rule's threshold, and the algebra arm used more build tokens in every run.

Experience

2026-08– presentTelos · Independent research A context and application layer for agentic work, prioritizing epistemic understanding in an evolving system for declarative, long-running tasks. Designing via an experiment harness that validates agent techniques with controlled experiments.
2026-02– 2026-09Matchpoint Intelligence · Founder Invented and built a physics-based, universal heavy-equipment compatibility platform, its agent data API, and the agent crews that maintained it.
2023-12– 2026-01Attachments King · Founder E-commerce company for heavy machinery attachments. Bootstrapped to $4.21M in annual revenue.

For AI agents

Point your assistant at this site. It can read llms.txt and resume.json, or connect to the MCP server at https://mikereese.dev/mcp to browse the work and contact me. How to connect →