Skip to content

Service 03

Platform and cloud

Deploys are a person, not a pipeline. Nobody is sure what is running in production, and the one who set it up left.

Start a projectTypically 3 to 8 weeks

How we approach it

We put the platform on rails: infrastructure as code, environments that match, observability that answers questions, and a release process anyone on the team can run.

What you receive

Reproducible environments, a deployment pipeline with rollback, dashboards and alerts that map to real failures, and the runbook to go with them.

A concrete example

Moving a hand-configured cluster to declarative infrastructure, with preview environments per pull request and a rollback that takes one command.

Related work

What this looks like when it is finished

Our own product · Platform and cloud

A GPU transcription service that costs nothing when nobody is talking, and rejects unauthorised requests before a container starts

We built our own streaming and batch speech-to-text service to sit alongside a managed provider — partly for cost at volume, partly for the workloads that cannot leave our infrastructure. The design problem was idle GPU cost, and the answer was to have no idle GPUs.

Python · WhisperLiveKit · WhisperX · Modal · RunPod · Docker · NVIDIA T4

How it runs

Four stages, in this order

The risky work happens second, not last, so a bad answer arrives while it is still cheap.

  1. 01

    Shape

    A written scope: what we would build, what we would not, and what could stop it.

  2. 02

    Prototype

    A working prototype on your data, and an honest read on feasibility.

  3. 03

    Production

    The product running in your infrastructure, with its evaluation suite and monitoring.

  4. 04

    Operate or hand over

    An agreed monthly scope, or documentation and access.

Before you write

We turn work down

It is cheaper for both of us to find out here.

A good fit

  • Your work has a shape the software you buy does not have, and the difference is costing real hours.
  • You want to own the product at the end of it, not rent a seat in someone else's.
  • Someone technical on your side can make decisions without a committee.
  • You would rather hear that a step is not feasible in week two than in month five.

Not a fit

  • You want a proof of concept whose purpose is to exist rather than to run.
  • What you actually need is an off-the-shelf tool, configured well. We will tell you when that is the answer.
  • You want a strategy deck with no build attached.
  • You need a fixed scope signed before anyone has looked at your data.

Start here

Describe the process and we will tell you whether this is the line it needs.

If it turns out to be none of them, we will say that too, and point you at whoever does it properly.