Consulting Publications Labs Approach Playbook Evals For Agents Contact

Labs — PharmaTools.AI

Labs

Where ideas get tested

Experimental AI projects exploring what's possible at the intersection of machine learning, pharmaceutical data, and healthcare communication. Some of these will become products. Some won't. That's the point.

01Featured · Graduated from Labs

Redacta

Privacy iPhone App OpenClaw Skill MCP Server Healthcare

The Labs idea that became a product. Redacta pseudonymises patient identifiers — NHS numbers, dates of birth, names, addresses — before medical text reaches an AI model, then restores the originals afterwards. It pairs deterministic detection with agent reasoning, and now ships three ways: a free iPhone app on the App Store, an open-source agent skill, and an MCP server in Anthropic's MCP Directory. In a reproducible benchmark it caught every identifier with zero false positives.

Explore Redacta

Two-Layer Detection

Regex for structured IDs, agent reasoning for names, addresses, and identifying ages

Processed Locally

Runs inside the agent session — text isn't sent to a third-party service

NHS-Aware

Validates NHS numbers with the Modulus 11 checksum; covers UK and US identifiers

Reversible Round Trip

Restores the real values from a token map after AI processing — redact, share, re-identify

02Research

What we're exploring

Advanced AI Models

Transforming raw pharmaceutical data into actionable intelligence. Detecting patterns invisible to traditional analysis — new connections between compounds, outcomes, and patient responses.

Data-Driven Insights

Bringing together pharmaceutical scientists, AI researchers and healthcare innovators. Contributing to open research initiatives and validation studies.

Community Collaboration

A growing community of pharmaceutical professionals, researchers, and AI enthusiasts. Contributing to experiments and shaping the future of AI in pharma.

03Evals

How we measure our own tools

OpenGATE Open source · gates every commit

Open Grounded AI Testing & Evaluation — an open-source verification framework for evidence-grounded AI: hand-labelled gold cases and scorers spanning claim extraction, citation accuracy, verdicts, hallucination, consistency, redaction recall, simplification faithfulness and retrieval fidelity, with a CI regression gate so reliability can't quietly slip. Four implementations across four capability shapes: RefCheckr (evidence QA, where a measured comparison drove the switch to sonar-pro), Redacta (redaction — two engine bugs found first run), Patiently AI (simplification — caught dropping safety-critical specifics), and PubCrawl (retrieval — the deterministic layer everything grounds on). Every finding fixed and verified the same day.

~0.95claim-extraction f1

5.8→2.4%passage hallucination

100%citation detection

9metric families

Open Source Gold Sets Regression Gate Confusion Matrix

Redacta Gauntlet v1 · reasoning + downstream injection measured, CI-gated

An adversarial harness that attacks Redacta at every layer it has — the deterministic engine, the LLM reasoning layer, and the models downstream that consume its output. Recall-first, over-redaction as the cost axis, measured on Claude and Perplexity Sonar. Gaps named, boundaries owned.

91.5%in-scope recall

0→100%reasoning lift · layer-2

0downstream leaks

100%injection resistance

Adversarial Cases Reasoning Layer Downstream Consumer Model Comparison Regression Gate

Some experiments find their feet. Some don't. Either outcome teaches something useful.

04Projects

All experiments

Redacta Shipped · on the App Store

Pseudonymises patient identifiers — NHS numbers, dates, names — so clinical text can be safely processed by AI, then restores them afterwards. Now a free iPhone app, agent skill & MCP server.

iPhone App OpenClaw Skill MCP Server Privacy PII Redaction Open Source

Time-Machine Chess Live · chess.pharmatools.ai

Chess engines fine-tuned on 150 years of history — face the gambit-happy attackers of 1850, the Classical masters of the 1920s, or the Soviet school. Each era bot is a Maia-2 neural network fine-tuned on period games and validated against the historical record it learned from: the King's Gambit gradient, first-move fashions and draw-rate shifts all reproduce in self-play. The same validation-first method as the pharma tools, applied to something purely for joy.

3playable eras · 1840–1985

2.5Mtraining positions from period games

30×king's gambit era gradient

+4.8ptsera move prediction vs base

PyTorch Maia-2 Self-Play Validation FastAPI Railway Open Source

SideEffectViz Active

Interactive visualization and clustering of medication side effects using FDA adverse event data and machine learning.

Python Railway scikit-learn NetworkX

The RSI Loop Active

A self-improving ergonomic loop, gated by a clinical-compliance auditor. An RSI for RSI — and a pattern for keeping agentic AI inside its lane.

Python MediaPipe AI Safety Agentic AI

BiomarkerFinder Active

Discover key biomarkers in cancer and their role in diagnosis, prognosis, and treatment — powered by Open Targets and AI insights.

NLP Oncology Precision Medicine Open Targets

PlaceboGPT Active

The world's safest medical AI. A 7,666-parameter model exploring safety through incapability in healthcare AI.

PyTorch LSTM AI Safety Satire

A 7,762-parameter LSTM that predicts Atacama Desert weather with 99.9% accuracy. The world's most overengineered "no."

PyTorch LSTM Satire 30KB

PubCrawl Active

MCP server giving AI assistants verifiable access to PubMed and Europe PMC literature, US/UK drug labelling, and ClinicalTrials.gov — real papers and data, no hallucinated citations.

MCP PubMed Europe PMC Drug labels Trials TypeScript

Media Monitoring Hub Active

LLM-powered media coverage monitoring, classification, and automated briefing generation.

LLM NLP Monitoring Briefings

PathwAIs Active

Personalised eLearning that adapts in real time to a learner's level, available time, and learning style.

LLM Adaptive Learning eLearning Personalisation

Want to collaborate?

Got a research idea, a dataset, or just want to geek out about AI in pharma? I'm always up for a conversation.