Qfact's users were doing by hand what a machine could read for them. We led the QIntelligence initiative end to end and delivered a system that analyses the documents they upload and turns them into precise project suggestions.
Natural language does not cooperate. The system had to interpret documents written by many different people, in many different shapes, and still produce suggestions specific enough for a user to act on.
It also had to be more than a demo. Several model families and services had to work together as one coherent service inside an existing microservices platform.
The system significantly reduced administrative workload for platform users and improved the accuracy of the project recommendations they act on.
A microservices platform for complex analysis workflows, built and led from 2018 to 2024. We introduced measurable sprint velocity where there was none and removed whole classes of recurring bugs.
The indexing and full text search foundation underneath QIntelligence, built on Python and Elasticsearch and designed to outlive the requirements it started with.
A performance focused redesign of analysis functionality, with configurable reporting that took 25 or more frequently requested use cases off the development backlog entirely.
Tell us what you are building and where it hurts. We will tell you straight whether we are the right partner for it.
Book a 15 minute introduction