DeepC Optimize runs as an optimisation protocol in Experiments. It proposes each next round of batches from everything you have measured, inside a design screened against regulatory precedent. You make and test the batches at the bench.
From a formulation report to a signed record of every round, each step as it appears in DeepC.
01
Under a formulation report, the Next step bar offers Optimise a candidate. DeepC asks which candidate when the report does not settle it, then writes an optimisation protocol with its own record number and page.
02
The protocol sets 2 to 6 factors, each with the range it may move in and its regulatory precedent for the route and dosage form, and the objectives with the tests that measure them. It is reviewed and approved with electronic signatures before a batch is made.
03
The design batches are made and tested first. Each round, DeepC proposes the next batches from everything measured so far. A proposal becomes a batch when you accept it, with its quantities rounded to your balance, and its results are entered by hand, from an instrument export or from a photo of the notebook page, each confirmed before it is saved.
04
Each objective is drawn batch by batch against its aim, with the best result so far, and each batch sits beside the settings it was made at. When you name the optimum, the rounds end and DeepC drafts the report.
05
The protocol, each batch record and the report are signed with electronic signatures (21 CFR Part 11 technical controls), and every change is kept with who made it and why. Protocols are listed in Experiments and in the Library.
The protocol shown is an illustrative example.
DeepC proposes the formulation limits, checked against regulatory precedent, and searches only inside them. In a retrospective on real tablet formulations, all of its proposals stayed inside the limits, against under half from an optimiser that searched without them.
Retrospective on the design space of 106 real film-coated tablet formulations, 20 runs of 25 proposals each. Both optimisers share the design space, the starting points and the seeds; only DeepC’s searches inside the limits for lubricant, glidant and disintegrant ratios and core weight.
From a first call to a pilot on your own programme.
A call with a formulation lead, who is in touch within a business day.
On your own programme, scoped with your team.
The AI model providers behind DeepC retain none of your content and train nothing on it.
Prefer email? info@deepceutix.com