Samuel McDonnell

Projects

Every project here carries either a measured result or a written reason there isn't one. Nothing is listed without one or the other.

7 projects · 0 with a measured result

2026–present

Professional · RWA

RWA MCP Server

A production MCP server splitting typed, audited tool access into separate customer and authoring surfaces.

Measured internally at RWA — not mine to publish No measurement

  • Python
  • Model Context Protocol
  • FastMCP
9 components
  1. Tool registry Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  2. Customer / authoring split Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  3. Typed schema validation Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  4. Per-tool scoping Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  5. Fail-closed access gate Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  6. Metadata-first query gate Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  7. Guarded query execution Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  8. Demo sites as a proving ground Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  9. Call audit log Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE

2025–present

Professional · RWA

RWA Customer Portal

A Next.js portal giving customers self-serve dashboards over their own data, with a staff console behind it.

Measured internally at RWA — not mine to publish No measurement

  • Next.js
  • React
  • TypeScript
  • Tailwind CSS
  • Drizzle ORM
  • Auth.js
  • Tableau Embedding API
8 components
  1. Tenant-scoped dashboards Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  2. Tableau embed layer Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  3. Staff console Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  4. Session and revocation Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  5. Tenant and module catalog Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  6. Notifications Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  7. GDPR tooling Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  8. Rate limiting Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE

2025–present

Personal

Glas Intelligence

Multi-agent simulation that turns uploaded documents into stakeholder agents and runs policy scenarios.

No accuracy number yet — and that is the honest answer No measurement

  • Python
  • Flask
  • Celery
  • Redis
  • Zep Cloud
  • OASIS (camel-ai)
  • Vue 3
  • Supabase
  • Docker
  • Nginx
8 components
  1. Document ingestion Evidence: CODE
  2. Persona synthesis Evidence: CODE
  3. Simulation runner Evidence: CODE
  4. Quantitative analysis Evidence: CODE
  5. Monte Carlo engine Evidence: CODE
  6. Calibration guardrails Evidence: CODE
  7. Report agent Evidence: CODE
  8. Forecast scoring Evidence: CODE

2026–present

Professional · RWA

RWA Chatbot

A FastAPI reasoning agent answering domain queries from validated per-tenant data snapshots, not live queries.

Measured internally at RWA — not mine to publish No measurement

  • Python
  • FastAPI
  • Anthropic API
  • LangChain
8 components
  1. Reasoning agent loop Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  2. Snapshot-backed data layer Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  3. Snapshot validation Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  4. Multi-tenant sector configuration Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  5. Knowledge store Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  6. Feedback-driven correction Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  7. Eval harness Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE
  8. Observability Evidence: MEASURED INTERNALLY — NOT PUBLISHABLE

2026–present

Personal

Asymmetric Opportunity Screener

A weekly agent that searches arXiv, SSRN and the web and scores what it finds against a fixed rubric.

Private repo, no backtest run — nothing to verify yet No measurement

  • Python
  • Anthropic API
  • Tavily
  • Supabase
  • GitHub Actions
  • Telegram Bot API
12 components
  1. Source search Evidence: UNVERIFIED
  2. Search backend abstraction Evidence: UNVERIFIED
  3. Run budget Evidence: UNVERIFIED
  4. Five-axis rubric Evidence: UNVERIFIED
  5. Promotion thresholds Evidence: UNVERIFIED
  6. Prompt-injection boundary Evidence: UNVERIFIED
  7. Three-stage dedup Evidence: UNVERIFIED
  8. Input snapshots Evidence: UNVERIFIED
  9. Cost metering Evidence: UNVERIFIED
  10. Log sanitisation Evidence: UNVERIFIED
  11. Weekly delivery Evidence: UNVERIFIED
  12. Unit test suite Evidence: UNVERIFIED

2026–present

Personal

X Content Generator

A daily pipeline that researches AI news, drafts candidate posts, and scores them on five axes.

The feedback loop has run for a month and stored nothing No measurement

  • Python
  • Anthropic API
  • Tavily
  • Supabase
  • GitHub Actions
  • Telegram Bot API
12 components
  1. Trend research Evidence: UNVERIFIED
  2. Candidate generation Evidence: UNVERIFIED
  3. Deliberate over-generation Evidence: UNVERIFIED
  4. Prompt-injection boundary Evidence: UNVERIFIED
  5. Five-axis scoring Evidence: UNVERIFIED
  6. Ranking Evidence: UNVERIFIED
  7. Candidate persistence Evidence: UNVERIFIED
  8. Repeat suppression Evidence: UNVERIFIED
  9. Manual engagement logging Evidence: UNVERIFIED
  10. Weighted feedback Evidence: UNVERIFIED
  11. Telegram delivery Evidence: UNVERIFIED
  12. Cost metering Evidence: UNVERIFIED

2026–present

Personal

Personal Intelligence Digest

A daily digest whose queries come from a fixed interest profile, sharpened by an accumulated knowledge base.

No measurement, and the repo is not public yet No measurement

  • Python
  • Anthropic API
  • Telegram Bot API
  • GitHub Actions