Urban Connect’s agentic diagnostic agent works a network fault out for itself, pulling the logs, querying the routers and upstream providers, then writing the call-centre ticket, so support is proactive instead of a manual scramble.
Agentic Diagnostics
FDX - Apex (GPU)
Methodology
Practice
Urban Connect runs a lot of high-speed dedicated connections, business and consumer, and when something on the network goes wrong the first response was almost entirely manual. The infrastructure would report an issue, and a call-centre agent then had to chase it down by hand: working out what had actually failed, which components were involved, and which customers were affected. It was slow, reactive and ate a lot of agent time, and customers often felt the problem before Urban Connect had a clear picture of it.
We built Urban Connect an agentic diagnostic agent that does the legwork itself. It picks up the relevant log files proactively the moment an issue surfaces, then queries the other infrastructure in the path, routers and the like, to see how the fault is propagating. It also checks the status of the upstream providers, so it can tell an Urban Connect problem apart from one further up the chain, and builds a complete picture of what has gone wrong and exactly which clients are affected. It then creates a human-facing ticket, or adds to an existing one, with all of that diagnostic detail already attached, so the agent who picks it up starts with the answer rather than a blank page. The agent runs on a privately hosted open model, Gemma and Qwen on our Apex (GPU) private inference infrastructure with high-speed NVLink between the cards, so the network logs and customer data never leave Urban Connect’s own environment.
Resolutions take far less time now that the diagnostic work is done before a human is even involved. Support has shifted from reactive to proactive, with issues picked up and worked out as they happen rather than after a customer calls in, and the tickets that reach the call centre arrive complete instead of empty. The result is quicker fixes and happier customers.
Similar work in Technology & Innovation
First Technology
A cloud chat assistant, Harvey, that lets legal and paralegal staff check contract terms, dates and notice periods in seconds instead of digging through documents.
Practice
Modernise Apps with Azure AI
First Technology
We gave First Technology staff local AI chat and agentic desktop agents running on our private NVIDIA GPU cluster, so the data and token generation stay local, the bill is in local currency, and responses come back fast.
Practice
Private AI Inference
Vector Gaming
Vector Gaming needed serious GPU horsepower to train a custom 350-million-parameter model for smarter game NPCs. We put our private GPU cluster behind their Vulkan-based distributed trainer and cut a two-month run down to a fraction of that.
Practice
Distributed Model Training
Get in touch
Send us the gist of what you are trying to do. The right person from First Digital will be in touch within a working day.
