Engineering consultancy
AI evals and coding agents for engineering teams
Cloudsail is an engineering consultancy for CTOs and engineering leaders with a product and team already in place. We build and maintain eval suites so AI releases are decided on evidence, and we help engineers use coding agents on real repositories with review, tests and cost under control.
A baseline first, then every change tested on your own data before it ships.
Our team has built software and production AI for
Where we focus
Choose AI evals if you ship AI features and need evidence before each release. Choose agentic coding if you want coding agents to do measured, reviewable work in your repositories. Both start with a scoped project and can continue as ongoing work.
All servicesAI Evals Engineering
For teams shipping an LLM feature, RAG system or agent. A scoped initial build delivers versioned datasets, deterministic checks, calibrated model judges, CI regression checks and a first release report. Ongoing maintenance is agreed separately: a named engineer adds cases from production failures, rechecks judges and reports on each release candidate at a cadence agreed with you.
AI agent evalsRAG evaluationRAG developmentMCP server development
Agentic Coding
For teams with an established codebase that want coding agents to take on more work. A workshop on your repositories leads to a scoped pilot with stop conditions, measured as cost per accepted change, including review, rework, retries, CI and provider spend. Ongoing support then extends agents to further task types, with approvals and fallbacks in place and your engineers keeping release authority.
Agentic coding
From assisted coding to bounded autonomous workflows
Autonomy expands one task type at a time. Your team starts with assisted coding, moves to supervised agent tasks and hands narrow, well-tested work to background agents only when pilot results support it. Each step has approvals, fallbacks and stop conditions agreed in advance, and decisions rest on measured cost per accepted change. Your engineers keep review and release authority throughout.
Works with
LLM cost optimisation
Spend by team and task, then budgets, defaults and routing.
Harness engineering
Context, checks and review rules that make agents reliable.
Coding agent adoption
One shared setup and training on real tickets.
Evaluations on your repositories
Replays of merged changes before you switch tools or models.
Testing
Tested on your own data before it ships
Coding agents
Replays of changes your team has already merged.
Process agents
Past cases with known outcomes.
Custom models
Cases the model was never trained on.
Clients
What clients say
“They were embedded in our team, which was really effective.”
“We are impressed with their engineers' high-quality work.”
“Their responsiveness, friendliness, and successful project delivery were top-notch!”
Team
The people behind the work
Mickey GrafFounder and CEO- 01
Your environment, your rules
Every data flow is agreed with you before work starts.
- 02
A data processing agreement in every contract
With the documentation your data protection team needs.
- 03
Teams and tasks, never individuals
Works council requirements are handled before anything goes live.
- 04
Everything we build stays yours
Code, test sets and runbooks, written for your team to run.
From the founder
Models get cheaper every quarter. Running them well doesn't
New models arrive every few months. Whether they pay off depends on the work around them: context, checks, routing and measurement. That is the work we do.
Mickey GrafFounder and CEO
Ask AI for a summary of Cloudsail
Pick a topic and open it in your assistant.
Summarise what Cloudsail (cloudsail.com) does, which services it offers and how a first project with them runs.
FAQ
Common questions
Which services does Cloudsail focus on?
Two. AI Evals Engineering builds and maintains the eval suite for your LLM product, RAG system or agent, so release decisions rest on regression checks and reports rather than spot-checks. Agentic Coding helps your engineers move from AI-assisted coding to agents that complete bounded tasks in your repositories, measured by cost per accepted change. Each starts with a scoped project and can continue as ongoing work with a named engineer. Related work such as harness engineering, cost optimization and training supports these two services.
Where do we start?
Where AI already costs money or where work still moves by hand. We measure that first, and the first project answers one clear question.
What does a first project look like?
One process, team or model, with the measures agreed before we start. We take a baseline, make changes one at a time, test each against it, and hand over the setup with training.
Are you consultants or engineers?
Engineers. The people who scope your project build it with your team and hand it over.
Will this work with our existing codebase and systems?
Yes. We work in the repositories, tools and processes you already have, without a rewrite or a new platform.
We already pay for Copilot, Cursor or Claude Code. Why has nothing changed?
Licences help individuals. Results come from the setup around them: the context agents see, the checks before merge, budgets and routing, and training on real tickets. That is the part we set up.
Do your agents decide on their own?
Only within limits you set. Each agent starts by preparing work for a person to decide, and takes on more only after you have reviewed its results with us.
Which models and tools do you use?
Whichever suit the task: commercial models such as Claude, GPT or Gemini, open-weight models on your own hardware, and the coding agents your teams already have.
Can everything run on our servers?
Yes, for agents, test sets and open-weight models. Commercial models run only through data flows you have approved.
Who handles data protection and the works council?
We handle your works council's requirements before anything goes live, and prepare the documentation your data protection team needs.
What does it cost?
It depends on the scope and the size of your teams. You get a written proposal after the first call, and the first conversation is free.
What if a change doesn't pay off?
Then we leave it out. You keep the test set and the measurements either way.
The AI is bought. Now make it pay off
Bring one piece of work. 30 minutes with an engineer, no access to your systems needed.
Look for the draft in your email program
Send it from there, and an engineer replies in person with times for a 30-minute call. If no draft has opened, write to us at miki@cloudsail.com.