Selected work

Proof of judgment under real constraints.

Four stories at different evidence boundaries: professional systems are sanitized, public code is linked, research is labeled, and team recognition stays attributed.

Case studies

From context to failure modes, review boundaries, and outcomes.

Professional system — sanitizedInsurance · Document intelligence · Agentic workflows

From claim packet to auditable action

A governed document workflow that turns mixed claim packets into typed facts, visible exceptions, and reviewer-ready decisions.

Reduced document handling in a measured workstream while keeping every uncertain field and route inspectable.resume-supported · Role, workflow scope, and qualified outcomes are supported by the latest résumé.
Read case study
Synthetic validation eventOperational pattern; details sanitized
{
  "packet_id": "SYN-042",
  "contract": "claim_fact.v3",
  "confidence": 0.78,
  "rule": "service_date_sequence",
  "state": "review_required",
  "trace_id": "tr_8a21"
}
  1. Ingest
  2. Classify
  3. Extract
  4. Validate
  5. Human review
  6. Action
  7. Observe
Professional system — sanitizedHealthcare payer · Local inference · Compliance review

Clearing a 7,000-case review backlog without moving regulated documents off-prem

A local document-review system combining OCR, retrieval, small language models, and a reviewer surface inside the data boundary.

Cleared a 7K-case backlog and reduced review time by about 90% in the measured workflow.resume-supported · Backlog and review-time outcomes are supported by the latest résumé.
Read case study
Synthetic reviewer routeDelivered professional system; details sanitized
review_case:
  source: synthetic-policy-17.pdf
  pages: [4, 5]
  retrieval_score: 0.84
  extraction_state: qualified
  route: reviewer_confirm
  reason: conflicting_effective_dates
  1. Local intake
  2. OCR
  3. Chunk
  4. Retrieve
  5. Generate
  6. Review
  7. Measure
Team award projectHealthcare interoperability · Patient communication · FHIR

Standards-aware patient communication, built as a team

A healthcare interoperability project recognized by the Global HL7 AI Challenge for Transformative Impact in Healthcare.

Team recipient of the 2025 Global HL7 AI Challenge recognition for Let’s Talk Doc.public-source · HL7 confirms Let’s Talk Doc and the Transformative Impact in Healthcare award.
Read case study
Synthetic FHIR communication contractAward project; official award and recipient sources verified
{
  "resourceType": "CommunicationRequest",
  "status": "active",
  "subject": { "reference": "Patient/SYNTHETIC" },
  "payload": [{ "contentString": "Post-visit summary" }],
  "language": "es-US"
}
  1. Clinical context
  2. FHIR contract
  3. Patient-friendly transform
  4. Safety checks
  5. Human touchpoint
Research labRepresentation engineering · Local models · Evaluation tooling

Turning model-behavior research into a reproducible engineering workbench

A public local-first workbench for activation steering, model inspection, API-driven experiments, and repeatable evaluation.

Public code, tests, UI, and documented limitations make the research inspectable rather than promotional.public-source · Source, tests, UI, and documentation are public.
Read case study
Experiment manifestMaintained public repository
experiment: sentiment-axis-04
model: local-transformer
layer: 18
coefficient: 0.65
seed: 42
comparison: baseline_vs_steered
status: reproducible
  1. Load model
  2. Capture activations
  3. Construct vector
  4. Apply hook
  5. Evaluate
  6. Compare