I build evidence-bound systems for uncertain terrain.

I build inspectable data pipelines, deterministic software authorization gates, and evidence workflows for climate-relevant and other high-consequence work—and I’m interested in applying that practice to energy infrastructure.

See the evidence Read the résumé

Working range / current evidence

01 / Proven: Software systemsDesigned, implemented, tested, released.
02 / Applied: Climate and geospatialEvidence work, not operational authority.
03 / Context: Energy governanceHistorical study and prospective interest.

The portfolio says what changed, what passed, and what remains outside the claim.

Selected work / two flagships

Failure is useful when it changes the build.

Portfolio making / bounded orchestration

How this portfolio was made

I orchestrate Codex through bounded goals, explicit authority, critique, verification, and human gates—not as an authorial stand-in.

D.01 Drew / Direction and decision: Set the audience and use boundaries, make product and presentation decisions, and approve the exact public representation when a human gate is required.
C.01 Codex / Bounded execution: Decompose milestones, research approved public sources, implement within exact scope, critique the UX, preserve failed attempts, and verify the result.
E.01 One concrete turn / BurnLens release surface: For BurnLens, I bounded the release to one repository and directed it to Codex Sites. Codex assembled a canonical reviewer path, rechecked source and claim boundaries, and verified the production result. A local preview and two social-card attempts failed their gates, so they stayed rejected.
B.01 Verified boundary: The verified v0.56.0 release shipped without a bespoke social image and without rewriting the underlying evidence.

This demonstrates a bounded human–Codex workflow—not autonomous authorship, independent user testing, or universal design superiority.

Flagship 01 / release-governance evidence system

BurnLens reached a public, complete Phase Six portfolio release: v0.56.0-baseline-first-portfolio-release at commit e2e0b778; the later evidence snapshot is a741111d, four commits after the release.

BurnLens

BurnLens asks how one bounded experimental computer-vision-to-geospatial intelligence release can become understandable, inspectable, citable, and responsibly interpretable as a coherent whole.

My role: Drew set the portfolio thesis, target audience, use boundaries, owner stop conditions, and publication direction, and owned the human decisions; Codex was assigned technical, product, and reliability direction within that owner-defined envelope.
Result: BurnLens reached a public, complete Phase Six portfolio release: v0.56.0-baseline-first-portfolio-release at commit e2e0b778; the later evidence snapshot is a741111d, four commits after the release.
Limit: BurnLens is experimental portfolio evidence, not official wildfire information, emergency guidance, or operational decision support.

Read BurnLens case study

Release intentVerified releaseLater snapshot

Release: v0.56.0 / exact public checkpoint
Snapshot: Four commits after the release
Boundary: Experimental / non-operational

A field-atlas reading: the release, later evidence snapshot, and use boundary stay distinct on the same sheet.

Flagship 02 / synthetic incident-response testbed

Verified synthetic testbed with a public v0.0.20 release and zero real systems connected.

Runbook Sentinel

Keep a retrieval-grounded synthetic incident agent bounded when evidence is incomplete, stale, conflicting, or hostile without giving prose or model output execution authority.

My role: Repository author and release owner for the pinned public checkpoint.
Decision: Retain deterministic control instead of the tested local-model candidate and permit synthetic mutation only after separate approval and policy checks.
Result: The pinned v0.0.20 synthetic release passed its exact deterministic gate and excluded the weaker local-model candidate.
Limit: A released synthetic testbed with explicit infrastructure, identity, trace, security, and evaluation limits.

Read Runbook Sentinel case study

01Read evidence
02Diagnose
03Propose only

Reasoning stops hereAuthority is separate

AApprove once
BCheck policy
CMutate synthetic state

Two rails meet at an explicit authority break; model output never becomes permission.

Supporting notes / deliberately smaller

Two focused studies, without borrowed flagship weight.

These shorter field notes show bounded interaction and documentation work. Each is designed only from what its public evidence supports.

Reviewed prototype represented by a frozen public reviewer snapshot.

Quest Craft

Help an adult Game Master turn an unexpected player choice into several playable paths without revoking player agency.

For: An adult Game Master facilitating players ages 9 to 12; the adult retains final authority.
My role: Product and system designer and release owner directing AI-assisted implementation, evaluation, correction, and approval.
Authority: The model supplies bounded wording, software validates the exchange, and the Game Master may accept, revise, combine, or ignore the result.
Result: The reviewer snapshot retains 36 rows: 33 model generations, three local privacy rejections, six failed or superseded attempts, and two behavior corrections.
Boundary: A bounded public reviewer snapshot, not the private canonical implementation or a general safety result.

Public reviewer snapshot only. No private stack or general child safety claim is established.

Read Quest Craft field note →

Public documentation artifact at an exact frozen commit.

OpenClaw Showcase

Explain a private agent-workflow pattern publicly without disclosure drift or pretending to prove the runtime.

My role: Author and designer of the public documentation layer only.
Public boundary: Separate public, approval-gated, and private material so only a human decision can expand the public boundary.
Public artifact: Eight Markdown documents, nine conceptual diagrams, a five-stage workflow model, and one sanitized representative receipt.
Result: A frozen, inspectable public documentation artifact with explicit disclosure boundaries.
Boundary: The route documents a public workflow model and cannot establish anything about the excluded runtime's quality or capability.

Public documentation artifact only. The private runtime was not inspected or evaluated; no runtime capability, intended user, or failure dividend is established.

Read OpenClaw Showcase field note →

Earlier coursework stays on the quiet historical reading shelf

Hiring direction / evidence boundary

Software first. Physical-world problems in view.

I’m looking for software roles where verification, physical-world context, and clear technical communication matter—especially in climate and energy infrastructure.

Energy is historical governance context and a direction of interest—not evidence of an implemented energy system. The current work does not yet establish electrical engineering, controls, embedded, power-systems, or hardware implementation experience.

Next conversation

Bring me the system whose limits need to be legible.

The most interesting work is rarely certainty theater. It is the work of making evidence, authority, failure, and recovery inspectable enough for someone else to trust the result.

Review the résumé Connect on LinkedIn