Service
Monitoring, upgrades & ongoing support
After handover, you can run the deployment yourselves using our documentation, or engage us for ongoing support. Support is optional and priced separately from the implementation fee.
What you get
- Visibility of health, latency, errors and GPU utilisation
- A planned path for model upgrades and security patches
- A named contact who knows your deployment
Typical scope
- Monitoring dashboards and alerting
- Model and serving-stack upgrades, tested before rollout
- Security patching of the components we deployed
- Periodic capacity and cost reviews
Technical detail
- → Metrics via Prometheus / Grafana or your existing observability tools
- → Staged rollouts with rollback plans for model changes
Scope and pricing are agreed per engagement. Implementation is a fixed, one-time fee; infrastructure is paid directly to your provider; ongoing support is optional and priced separately.
Ready to talk through your requirements?
Tell us the use case, where it should run and how many people will use it. We will take it from there.