Question 1

Who will I actually talk to?

Accepted Answer

The pharmacometrician who does the modeling. The same person scopes the project, writes the analysis plan, makes the modeling decisions and signs the report. If the question needs clinical, statistical or regulatory input, you are introduced to that specialist by name before they start.

Question 2

Is this a CRO with better marketing?

Accepted Answer

No, and the difference is in the incentives. A CRO sells time, so more hours are good business. We sell a defined piece of evidence at a fixed price, so finishing it well and on time is good business. In practice, the senior scientist who scopes your project is the one who does the modeling, and nobody is learning pharmacometrics on your program.

Question 3

When is the right time to involve you?

Accepted Answer

Earlier than most teams do. The best moment is usually before a study is locked, when the design can still change so it produces data a model can use. The second best is as soon as a readout lands. You don't need a modeling strategy to get in touch, only the question. If modeling is the wrong tool for it, we will tell you on the call.

Question 4

Can you work with our CRO?

Accepted Answer

Yes. Many clients keep their CRO for operations and data management. We take SDTM, ADaM or raw data with specifications, and the guaranteed date starts when the agreed data arrive. How the handoff works.

Question 5

How do pricing and milestone payments work?

Accepted Answer

You get a fixed price after the scoping call, paid in two parts: when you approve the analysis plan, and when we deliver the report and assessment table. Prices are quoted per project, not published.

Question 6

What if the analysis turns out to be harder than expected?

Accepted Answer

That risk is ours. It is the point of a fixed price. If a model resists convergence, or the covariate structure is messier than the data first suggested, we absorb the extra work. What we will not do is quietly narrow the question to fit the budget. If the honest answer changes, you hear it while there is still time to act.

Question 7

What do you guarantee, and what not?

Accepted Answer

We guarantee the delivery date, with a credit if we are late, the documentation standard, and our support through agency questions on our analyses. We never guarantee regulatory acceptance. That depends on the whole dossier and the agency's judgement, not on the model alone.

Question 8

Is this ICH M15-ready?

Accepted Answer

Yes, in the way the guideline describes: a documented assessment for each question of interest, an analysis plan approved before modeling starts, documented code verification, and code and data delivered for review. M15 is a framework, not a guarantee of acceptance. Our M15 guide.

Question 9

Our data are sparse, or messy. Is that a problem?

Accepted Answer

Usually not one that stops the work, though it changes what can be concluded. Sparse sampling still supports a population model; that is part of why the method exists. What matters more is that dosing and sampling times are reliable. Where they are not, we tell you what can and cannot be concluded. Data assembly takes a large share of any real timeline, and we plan for it honestly.

Question 10

Can you support a regulatory submission?

Accepted Answer

Yes: final reports, CDISC datasets, eCTD placement, Module 2.7.2 and labelling text, briefing documents and responses to agency questions. The submission package.

Question 11

Which software do you use?

Accepted Answer

NONMEM, PsN, nlmixr2, PKNCA and PK-Sim, chosen by the question and by what your submission and your team will need later. Where we have the choice, we favour open tools so you can reopen your own work without a licence, or without us. Versions and environment.

Question 12

Where do the agents stop and the scientist start?

Accepted Answer

Our agents are custom-built and run locally on our own servers. They prepare datasets, draft code and report text, run diagnostics and re-run analyses to check them. They never produce results: every estimate and simulation comes from established software running code you can re-execute. Model structure, covariates, what the diagnostics mean and what goes in front of a regulator are decided by a person who signs their name to it.

Question 13

How is confidentiality handled?

Accepted Answer

We sign NDAs as a matter of course, and will sign yours before seeing anything non-public. Client results are never published or mentioned without written permission.

Question 14

Do we own the model, the code and the data?

Accepted Answer

Yes, all of it: analysis datasets, code, model files, run logs and reports. Everything is generated from code, so it can be re-run, audited and extended by you or anyone you choose.

Questions sponsors ask

Still have a question?