Case studies
Enterprise AI, taken into production.
In-depth accounts of systems we built with our clients: the problem, the approach, and the results that held up in production. The full list of projects is on a separate page.
FGS Global
Strategic communications · Agent evaluation and monitoring
One quality standard for an enterprise AI agent network.
FGS Global's consultants use Fergus, an AI agent network, across the firm's practice areas. There was no way to tell whether a change made Fergus better or worse, or what it cost. We set the development lifecycle and built the evaluation and release layer, with evals built around the issues users raised.
Read the case study →
Sourcera
Procurement · Indirect spend · Supplier intelligence
An AI engine that finds savings in indirect spend and drafts the tender.
Finding savings in indirect spend usually takes procurement analysts weeks of manual work. Sourcera, a procurement intelligence platform, automates it. We built its AI engine: it profiles suppliers, finds savings opportunities in spend data, flags contract constraints, and drafts the tender documents (RFx: requests for proposal or quotation), directly in the customer's sourcing platform. Each stage has its own evaluation, so results stay stable across customers and releases.
Read the case study →