Labels at scale,in the hot path.
Particula-Classify assigns intent, sentiment, and categories against a taxonomy you lock in advance, at 12 ms median and 10K+ requests per second on a single node. Small enough to sit in the request path, self-hosted so the traffic never leaves.
One job, done to spec.
Here is the spec.
Everything below is work the model handles on its own, with no wrapper, no retry loop, and no second call out to a larger model when it gets stuck.
Your taxonomy, locked
Labels come from the label set you define, never free text. No drift, no novel categories appearing in production.
10K+ requests per second
Sustained on a single node, with batching handled by the runtime. Built for ticket queues, chat routing, and event streams.
Confidence you can route on
Scores are calibrated, so a 0.97 means 0.97. Send low-confidence items to a human queue with a one-line rule.
Retrains on your labels
A few hundred corrected examples usually move the needle. The included tuning job runs overnight on the same GPU.
Context, latency, hardware,
and what it takes to run.
The numbers a capacity plan actually needs. Sizing gets reviewed against your traffic before the pilot, and the figures go into the agreement in writing.
From first call to production
without a rewrite.
Three steps, and you keep the weights at the end of them. Nothing about the rollout depends on us staying in the loop afterwards.
- 01
Discovery call
30 minutes, no slides. Your task, your data shape, and the security constraints around it. If this model is the wrong fit, we say so on the call.
- 02
Pilot install
Containerized deployment to staging in your VPC or on-prem, on the same stack as Lumen and Notetaker. The eval harness runs on your data and the numbers go into the pilot agreement.
- 03
Production rollout
Runbook handoff, operator training, and 90 days on call. After that it is yours to operate, no vendor dependency.
Five others share
this runtime.
They run on the same serving stack, the same deployment path, and one API, so licensing a second model adds no operational surface.
“Bring a hundred real examples from your pipeline. We run the model on them live, the harness scores the output in front of you, and you decide with numbers instead of a sales deck.”
Sebastian Mondragon, Founder of Particula Tech