§ 3 — What we build
Eight practices.
Built for the way pharma actually works.
Keep scrolling →
Applied AI for Life Sciences / Est. 2026
We build AI that is
fluent in it.
Custom, pharma-tuned models and agents for the commercial, medical and market access teams who can't afford a confident wrong answer.
General-purpose AI has never derived a line of therapy, read a payer policy, or sat through an MLR review. So it guesses. In pharma, a confident guess ends up as a number in somebody's board deck.
Fig. 1
§ 2 — Core AI
Supervised fine-tuning with LoRA and QLoRA on open-weights models, trained on your therapy areas.
DPO and reward modelling against expert feedback, so the model answers the way your analysts would.
Frontier-model quality compressed into a small, private model that is fast and cheap to run.
Persona-driven conversations and rare-case generation where real labels are scarce or sensitive.
Hybrid search that checks permissions on every query and cites every passage it returns.
Multi-agent orchestration with typed tool calls, MCP servers and deterministic decision steps.
Vision-language extraction that turns labels, policies and PDFs into strict, validated JSON.
Governed analytics over Snowflake and Databricks, with a golden question set and per-step scoring.
Expert gold sets, LLM-as-judge and regression suites that run on every change.
Confidence scores you can route on, so uncertain answers go to a human reviewer.
PHI redaction, claim checks, refusal policies and a full audit trail.
Serving, monitoring, drift detection and cost control, all inside your cloud.
Fig. 2 — Inside a fine-tuning run
EGFR+ mNSCLC patient on osimertinib. Progression at month 14, then carboplatin + pemetrexed starts 70 days later. Which line is the new regimen?
This appears to be a continuation of first-line therapy. Chemotherapy is often added to targeted therapy, so the patient is likely still on first-line treatment, though this may vary…
{ "line": 2,
"trigger": "regimen change after progression",
"rule": "client_v4.2 · gap 63d",
"confidence": 0.94,
"evidence": ["PD m14", "carbo+pem d70"] }
Illustrative benchmark. All figures are invented for this example.
§ 3 — What we build
Keep scrolling →
Fine-tuning
Small, private models trained on therapy-area semantics, your brand vocabulary and your commercial definitions. They're cheaper, faster and more consistent than a frontier API, and they run where your data already lives.
Real-world data
Line-of-therapy derivation, cohort building, persistence and switching on claims and EHR data. Each patient-level decision traces back to its evidence, and every definition carries a version number.
Market access
Agents read payer policies, formularies and prior-authorisation criteria and turn them into structured records you can compare across plans. When a policy changes, the record updates and you get an alert.
Omnichannel
Segmentation, propensity and next-best-action that field teams actually trust, because each recommendation comes with a plain-language reason. Includes a rep copilot for pre-call planning and call summaries.
Medical · Legal · Regulatory
Pre-screens promotional material against approved claims, label language and references, and flags fair-balance gaps before the committee sees the piece. The result is fewer review cycles, and the reviewers stay in charge.
Safety
Finds adverse events in call notes, patient-support programmes and social listening. Supports case-intake triage, deduplication and MedDRA coding, with a human signing off every case.
Analytics
Ask your commercial warehouse a question in plain English. Answers are tiered by confidence, checked nightly against a golden question set and linked to the exact SQL behind each figure.
Insight
Agents code primary-research transcripts against your codebook, mine MSL insights and track competitor trials, launches and label changes. Your team gets a short, cited brief every Monday.
Fig. 3 — A real question, end to end
That means showing its working, citing the definition it used, and telling you what you can't yet put in front of a client.
What was second-line share for our brand in EGFR+ metastatic NSCLC last quarter? Can I show it to the client?
Cohort first: 1,847 patients qualify. 304 are excluded because the setting can't be determined from their records.
↳ shows the denominatorUnder definition client_v4.2 (63-day gap, maintenance doesn't start a new line), second-line share is 23.4% (CI 21.5–25.3).
↳ names the definitionThe vendor figure of 27.7% isn't a conflict. It's fully explained by a 90-day gap (+2.9 pts) and counting maintenance as a new line (+1.4 pts).
↳ reconciles, doesn't argueBefore it goes to the client: 214 patients have an ambiguous line boundary and are queued for steward review. The worst-case swing is 1.9 pts.
↳ surfaces the caveatIllustrative. All figures are invented for this example.
§ 4 — Across the value chain
§ 5 — Method
A prompt is a
We build the second one.
Your experts define the task. We build the gold set and the evaluation harness before writing any model code.
week 1–2De-identified claims, documents and transcripts, plus synthetic data wherever real labels are scarce.
week 2–4Supervised fine-tuning followed by preference alignment, on open models you own outright.
week 4–7Per-step accuracy, calibrated confidence, LLM-judge plus expert review, and a regression run on every change.
week 6–8Deployed privately in your cloud. Every analyst correction becomes training signal for the next version.
ongoingAI use cases mapped across the pharma value chain
to a first measured pilot on your own data
of our models can run inside your own cloud
client records ever used to train a shared model
§ 6 — Ways to engage
We map your use cases, score them on value, feasibility and data readiness, and leave you with a ranked roadmap.
One use case on your own data, with a gold set and an accuracy number your stakeholders can sign off on.
A production system with monitoring and governance, handed to your team with full code ownership.
We run, retrain and govern your models, and help you build an internal AI centre of excellence.
§ 7 — Contact