Blake Medulan / builder & writer

I build AI systems that prove what they claim.

A credential broker whose operator can't read the secrets. Compliance evidence that exists before the auditor asks for it. An evaluation that checks whether the French answer is as good as the English one. Each one comes with a way for you to check it yourself.

See the work Read thebdot

check it yourself VERIFIED

# vault.melx.buzz: Sepulchre
$ bash tools/verify-policy.sh
==> operator-scoped token reading inbound  DENIED
# osfi.melx.buzz: osfi-gate
$ osfi-gate verify ./evidence
==> signed evidence bundle                 OK
# open-articles: every number, reproduced
$ make reproduce && make test
==> no credentials, no provider calls      PASS
█

01 — Live work

Shipped in public, each one checkable.

Each screenshot scrolls through its page. Click one to open the live site.

01Security · Credential broker

Sepulchre

“Don't trust us. Verify us.”

A credential broker for the secrets that pass between people. The operator who runs it can't read what flows through it: an explicit Vault deny policy blocks access no matter what other permissions exist. A script you can run yourself checks that promise against the live system.

Zero-knowledge operator access
Hash-chained signed audit trail
BYOK per-tenant encryption
Human approval for AI agent readers

vault.melx.buzz

Sepulchre homepage: Don't trust us. Verify us.

02RegTech · Compliance as code

osfi-gate

“The audit evidence is written before anyone asks for it.”

For Canadian banks, insurers and credit unions. osfi-gate runs in the build pipeline on every change. It maps scanner findings to controls anchored in OSFI guidance, applies the policy the risk team keeps in Git, and files a signed record of every decision. Anyone can verify those records offline.

OSFI B-13 · B-10 · E-21 · E-23
24 controls from Semgrep, Trivy, Gitleaks, Checkov
E-23 bridge to ServiceNow model inventory
Offline bundle verification

osfi.melx.buzz

osfi-gate homepage: Risk signs off before the merge button works.

03AI evaluation · Open source

French Drift

“Is the French answer as good as the English one?”

A bilingual quality harness. It runs the same corpus, questions and metrics through an AI content pipeline in English and in Canadian French, then reports the gap between the two. It also tracks Canadian-specific failures: Quebec forms replaced by France equivalents, and valid Canadian French "corrected" into something else.

218 checks across 6 suites
10 dimensions of service parity
Offline zero dependencies
Bilingual site & report

french-drift.melx.buzz Live report Code

french-drift.melx.buzz

French Drift homepage: Is the French answer as good as the English one?

/report

04Architecture · Interactive diagrams

Architecture Collection

“A collection of architectures.”

Interactive architecture and concept diagrams across the Score Anything Loyalty platform, independent open-source projects and reference studies. The thread running through them is AI architecture: hosted multi-agent systems, on-box constrained decoding, computer vision, and how to choose between them based on the constraints that bind.

AI through-line RAG, agents, guardrails, MLOps
Score Anything loyalty, ledger, SOC 2
Open source Sepulchre, OSSS, ISO 20022
Reference studies Azure Databricks, AWS

Open the collection Code

bdot-real.github.io/archsamples

Architecture Collection homepage listing AI architecture diagrams

02 — Also building

3 Halves Labs. Own your fan economy.

Sports · Music · Agencies

SCORE Platform

The Score Anything Loyalty platform I build at 3 Halves Labs.

SCORE is an open, modular fan engagement, loyalty and AI platform for sports clubs, music artists, venues and agencies. It brings fan engagement, marketing and operations together so organizations own their fan data, replace point solutions, and open new revenue streams.

Loyalty programs & rewards
Fan engagement across channels
AI predictors & insights
100% data ownership

3halves-labs.com

Fan economy · Public beta

ALEX

Trade athletes like stocks.

The Athlete Loyalty Exchange runs itself and is governed by AI agents. Fans buy and sell athlete coins with loyalty points, and prices move in real time with demand and performance. There are no drafts, salary caps or season-long commitments. It runs on loyalty points only, so it stays a closed, non-cash ecosystem.

7 leagues MLS, EPL, NBA, NFL, NHL, MLB, F1
Real-time market pricing
Loyalty points non-cash, closed ecosystem
Self-running governed by AI agents

athlete-exchange.app

ALEX market dashboard with portfolio, top gainers and market mood

ALEX trade card for Jan Oblak showing price chart

Biomechanics · Computer vision

MotionScore

Research-grade motion analysis from ordinary video.

A markerless biomechanics platform. It estimates pose from video, lifts it to 3D, and compares an athlete's movement with elite reference models from any camera angle, using joint-angle features, Procrustes alignment and dynamic time warping. Newton-Euler inverse dynamics and a 9-state Kalman filter with IMU fusion estimate forces without a lab. Motion capture labs cost $100k–500k; this needs a camera.

4.2–7.8° joint-angle RMSE vs. marker capture
±8–15% kinetics vs. force plates, with IMU
View-invariant comparison to elite models
7+ sports running to rugby lineouts

3halves-labs.com

MotionScore · lineout throw analysis

MotionScore analysis of a rugby lineout throw with skeleton overlay and a score of 84 out of 100

03 — Open source

Standards and tools, in the open.

Flagship · Open standardv2.0

Open Sports Scheduling Standard OSSS

A neutral, open standard for describing sports schedules, constraints and optimization goals, for traditional sports, esports and competitive events.

Sports scheduling is fragmented because every vendor describes the problem in its own way. OSSS standardizes the description of the problem and leaves the solution to whoever solves it, so scheduling rules stay portable and schedules can be audited and explained.

50+ constraint types

35objective metrics

16validated examples

60tests passing

View on GitHub Spec CC-BY-4.0 · Code Apache-2.0

// examples/amateur-league/osss-instance.json (excerpt)
{
  "id": "amateur-league-2025",
  "fixtures": [
    { "id": "round1-match1", "participants": ["AFC-1", "AFC-2"], "durationMinutes": 90 }
  ],
  "constraints": [
    { "id": "min_rest_72h", "type": "hard", "rule": "min_rest_time",
      "selector": { "entityType": "team" }, "params": { "min_hours": 72 } },
    { "id": "max_travel_500km", "type": "soft", "rule": "max_travel_distance",
      "params": { "max_km": 500 }, "penalty": { "model": "linear", "weight": 0.7 } }
  ],
  "objectives": [
    { "metric": "total_travel_distance", "aggregation": "sum", "weight": 0.7 }
  ]
}

TypeScriptWIP · v0.1.0 Nov 2026

fastify-mcp-guard

Authorization for MCP tool calls. For each call it allows, denies or holds for human approval, using per-argument Cedar policies and an audit trail.

TypeScript

mcp-iso20022

A governed MCP server for ISO 20022 payment operations. AI agents can initiate and validate payments, and every action goes through an audit layer first.