Claude agents and cloud platforms, built inside your team.

Services

• Forward deployed engineering

  We join your team and take Claude agents from a first trial to production.

  • Agent workflows built on Claude Code and the Claude Agent SDK, with MCP servers connected to your tools.
  • Harnesses that keep agents in bounds: scoped permissions, hooks that block destructive commands, a token budget for every run, and write access only through pull requests.
  • Production deployment as short-lived Kubernetes Jobs, with least-privilege credentials, secrets kept out of prompts and logs, and human approval before anything changes production.
  • Monitoring with Langfuse tracing, an audit log of every agent action, and alerts on cost and failures.
  • Documentation and a handover, so your team runs it after we leave.

• Platform engineering

  We build and run the platform your developers ship on, from inside your team.

  • Kubernetes on EKS and AKS, and HashiCorp Nomad, Consul and Vault.
  • Infrastructure as code with Terraform and Helm, and GitOps with ArgoCD.
  • CI/CD on GitLab CI, GitHub Actions or Azure DevOps, with the slow and flaky steps fixed.
  • Monitoring and alerting with Prometheus, Grafana and Alertmanager.
  • Lower cloud cost across development, test and production environments.

• Site reliability engineering

  We migrate and operate your systems, with agents doing the routine work.

  • Migration from on-premises to AWS with reusable Terraform modules, a cost estimate per component, and Well-Architected documentation.
  • Cluster patching, security updates, and dependency updates through Renovate on GitHub or GitLab.
  • Incident response, with agents that investigate an alert and draft a root-cause report for the on-call engineer.
  • A monthly retainer, so you pay per month and not per token.

Selected work

We don't publish client names.

• Two AI-first products, from zero

  Cloud infrastructure built from scratch for AI video surveillance in office buildings, and for an aviation SaaS.

• An on-premises to AWS migration framework

  Reusable Terraform modules, CI pipelines, custom tooling, per-component cost estimates and Well-Architected documentation, for a software company becoming an AWS partner.

• Multi-agent DevOps tooling

  Agents built on the Claude Agent SDK that run as ephemeral Kubernetes Jobs. They open pull requests and draft manifests, with no write access to production.

• Lower infrastructure cost

  Reduced cloud spend across development, test, acceptance and production environments, and across the CI/CD fleet.

How we work

• Embedded

  We join your standups, tools and on-call rotation, part time or full time. Billed monthly.

• Fixed-scope project

  A written scope and a fixed price before work starts. Suits migrations and platform builds.

• Monthly retainer

  Ongoing operations after a project ends: patching, updates and on-call, billed monthly.

What happens after you get in touch

1. A 30-minute call

   You describe the problem. We tell you whether we are the right fit.

2. A written proposal

   Scope, timeline and price, in writing, before any work starts.

3. Delivery

   Work happens in your repositories, as pull requests your team reviews.

4. Handover

   Documentation and a walkthrough, so your team can run it without us.