A global specialty chemicals and advanced materials group
Engineers building internal GPTs and agents for enterprise teams, grounded in the client's own data sources rather than public ones.
A materials science organisation deciding that generative AI needed an internal strategy, not a vendor contract. The question was how to put GPTs and agents in the hands of their own teams on their own data, without exposing that data to the public internet.
Engineers embedded into the client's AI and platform teams, building internal agents function by function. Each one working from the data that function actually uses, not generic public data.
Compliance
Regulatory submissions
R&D
Formulation + process data
Procurement
Supplier + spec history
Commercial
Operations + sales data
The search layer tuned to each set of documents, because what works on a legal filing doesn't work on a batch record. A labelled test set behind every agent, so a bad change is caught before deploy, not after. The usual enterprise safety checks: no cross-contamination between teams, no sensitive data leaking into model logs. Every action logged, because an enterprise using AI internally will eventually have to explain to legal or audit what the agent did and why.
Change management alongside the engineering. Training the function teams, collecting feedback, iterating the agents. The engineering is a fraction of the work; adoption is the rest.
A small to medium standing team embedded in the client's AI and platform groups.
GPTs and agents in regular use across functions, grounded in the organisation's own data, with the evaluation and audit scaffolding to run them responsibly over time.
Capabilities used
Tell us about it. We'll tell you honestly whether we're the right team to help ship it.