A pharma data platform’s AI agent was working. We rebuilt it anyway.
A live AI system on a pharmaceutical market access platform was rebuilt on its own knowledge foundation, and single answers became a working dialogue with the data.
- Client
- Pharma data platform
- Industry
- Life Sciences
- Asked by
- Engineering leadership
- How it shipped
- Side by side with the live system, staged, no cutover
- Built with
- A ReAct agent on the existing domain views and metadata
- Published
- 3 November 2026
Results at a glance
What the rebuild changed, on the same data.
<1
minute for complex, multi-part questions, answered as a conversation.
Production use300+
columns of regulatory, HTA and reimbursement data, asked about in conversation.
Data coverage7
domain views carried over unchanged from the first build. Only the engine was renewed.
Architecture0
cutovers. The live system kept serving users until the new agent had proven itself.
Rollout01 · What changed
The first engagement ended with the platform answering questions across 300+ columns of regulatory, HTA and reimbursement data, in every jurisdiction in the dataset, with regular use at 55% of platform users. The agent took a self-contained question and returned a grounded answer.
Then users started asking differently. A landscape question led to a narrowing, the narrowing to the evidence behind one decision, and that to the assessment document explaining it. The first generation answered questions. Users had begun to hold conversations.
Meanwhile, agentic AI, systems that reason in steps and correct their own course, became viable in production. The system was working and nothing forced a change. We proposed modernizing anyway, and engineering leadership chose to do it from strength.
“Modernizing from strength is cheaper than modernizing from failure, and the only way to never need the latter.”
One conversation, three turns
Before, each step was a separate investigation: filter, export, cross-reference, open documents.
- Turn 1LandscapeThe HTA landscape for an indication in France, and the current first-line options.
- Turn 2SubsetNarrowed to the decisions with the stronger benefit ratings, on exactly those results.
- Turn 3EvidenceWhich clinical trials supported the most recent of those, and what kind of studies they were.
- Behind itThe documentThe assessment document that explains the decision, linked back to the platform.
02 · What we delivered
Same foundation, a new engine.
The metadata layer and the domain views carried over unchanged. On top of them we built a new reasoning agent.
03 · How it ran
Evidence first, no cutover.
We developed the new agent against the same knowledge foundation and ran it side by side with the live system: same questions, same data, answers compared directly. It went through an adversarial testing campaign, then rolled out through the company’s environments in stages while the existing system kept serving users.
The running system stayed up until its successor had proven itself against it. No big-bang cutover, no disruption to users.
Run, with Compound: keeping a live system current so it keeps gaining value.
Side by side · before the rollout
Same questions, same dataThe readout: the new agent against the live system.
The running system stayed up until its successor had proven itself against it. No big-bang cutover, no disruption to users.
Measured side by side on the same 100 questions and 30+ conversation flows.04 · Results
Complex, multi-part questions come back in under a minute, as a conversation.
Questions that used to break into filters, exports and spreadsheets are answered conversationally, in one pass, in under a minute.
Follow-up chains work on exactly the results shown: landscape, subset, evidence, document, in one conversation.
The full regulatory, HTA and reimbursement dataset, including the evidence behind each decision, can be asked about in conversation.
The hardest questions, multi-condition, cross-source and drill-down, no longer go to in-house experts and data engineers.
The knowledge layer from the first engagement carried over unchanged. The engine on top was renewed at a fraction of the original effort.
05 · What they learned
The first build made the data answerable. The modernization made it conversational.
The same knowledge foundation carried both.
If this sounds like your company