Services
AI systems on your infrastructure: built, run and tested
We build AI assistants and agents on your servers or in your cloud, run the platform underneath and test both before go-live. For engineering teams we also roll out coding agents.
How the work runs
01Start
Scoping or an acceptance test
One or two use cases with a measurable goal and a hardware sizing, or an acceptance test of an AI system you already have.
02Build
Your AI system and its platform
The assistant or agent on your servers or in your cloud, and the gateway and model serving underneath, with acceptance criteria in the contract.
RAG developmentAI agents and process automationLLM platform and MLOps
03Run
Operations and regression tests
Model and infrastructure updates, tests after every change and a monthly quality report, by your team or by us.
A baseline first, then every change tested on your own data before it ships.
Where the work begins
Infrastructure
Your own servers or your own cloud account, and the platform that runs models for every team.
On-premise AI
AI on offers, contracts and customer files, with the data staying in your company: own servers or own cloud account, tested before go-live.
Azure OpenAI and Bedrock
GPT and Claude on company data, under the cloud contracts you already have: Azure OpenAI and Amazon Bedrock in your own account, with EU processing and one gateway.
AI platform for all teams
One approved route to AI for every team, with budgets, logs and a free choice of model, run on your servers or in your cloud.
LiteLLM gateway
Budgets and access rules for every team's AI use, through a LiteLLM gateway that is hardened, connected to your identity provider and kept up to date.
vLLM on Kubernetes
Open-weight models on your own GPUs, so data stays in house and costs follow capacity you plan, sized from measured load.
Data and agents
Company data connected so that assistants and agents can work on it.
Data integration for AI
Answers from file shares, SharePoint, ERP and tickets in seconds, for assistants and agents, with permissions carried through and tested.
Knowledge assistants (RAG)
Staff find answers in internal documents in seconds, with sources cited, permissions kept and tests on your own questions.
AI agents and process automation
Agents that take on the routine steps of complex cases and pass decisions to people, with a cost per handled case.
AI chatbots
Customers and staff answered faster from your data, with approved actions and a handover to people when it matters.
System access for agents (MCP)
AI agents that look up and update data in your systems, with narrow permissions, human approval for changes and tests.
Custom model training
A small open-weight model trained for one task and compared with your current model on cost and accuracy.
Testing and quality
Tests before go-live and after every change, and a free review of the AI you already use.
AI system testing
Before go-live, acceptance tests on your own cases tell you how often your chatbot, assistant or agent is right, in terms your QA team already uses.
AI evals engineering
Evals built from your own traces show whether each change made your AI product better or worse, with a release gate that stays in your repository.
AI agent evals
Find out how often an agent gets the job done before it acts in your systems, by checking outcomes, tool calls and how reliably runs repeat.
RAG evaluation
An assistant that answers from your documents, tested on retrieval and on answers in each language your users write in, so you know how often it is right and cites the right source.
Free AI usage review
One page for management on where your AI money goes, whether it pays off and what to change, from exports you choose to share. Free, no system access.
Coding agents
For engineering teams. A single project can draw on more than one of these.
Cost review for one team
A first step with one team: where the coding agent spend goes, what we change together, and the cost per merged change before and after.
LLM cost optimisation
Agent spend broken down by team and task, then lowered through defaults, budgets and routing your platform team can run.
Coding agent adoption
Agents taken from a few pilot teams to the rest of engineering, with training and one shared setup.
Harness engineering
The setup that tells an agent how to build, test and change your code, kept in version control.
Evaluations on your repositories
Tools, models or settings tested side by side on changes you have already merged, before you commit to one.
Coding agent tools
No vendor pays us. We recommend the tools that work on your code and tell you when one doesn't suit your teams.
Claude Code consulting and rollout
Claude Code fitted to your codebase, permissions and review process, starting with one pilot team.
Claude Code training
Workshops where your engineers practise Claude Code on their own repositories and backlog tasks.
OpenAI Codex consulting
Repositories, sandbox rules and access prepared for Codex, with training on the CLI, IDE extension and cloud agent.
Cursor consulting and team training
One agreed set of project rules, tool access and review practice for everyone who uses Cursor.
GitHub Copilot implementation
Copilot and its cloud agent configured to follow the policies and review steps you already run.
Other services
Advice, automation and engineers for your team, with the same fixed prices and written acceptance criteria.
AI engineering and architecture
Assistants, voice interfaces and agents in the products you sell, with the serving and retrieval underneath.
AI automation
Routine work taken off your teams: processes automated step by step with rules, workflow tools, models and agents, approved by people and measured per case.
AI strategy and rollout
AI strategy and rollout that starts with one running, measured system on your own processes and builds the roadmap around its figures.
AI engineers for your team
Extra AI engineering capacity when your team lacks AI skills: experienced engineers who build with you and leave the know-how.
Enterprise AI
One approved AI platform for the whole company: an internal assistant instead of shadow AI, approved models, data that stays in-house and spend per team.
From the blog
AI pilot success criteria
What an AI pilot has to show before the next stage is funded, and how to write acceptance criteria before anyone chooses a tool.
Coding agent pilot design
How to compare coding agents on the same work, with random task assignment, a replay of merged changes and a decision rule agreed in advance.
Outcome versus trace evaluation
Why an agent run can finish without errors and still handle the case wrongly, and how to check business outcomes separately from traces.
RAG document permissions
How access rules travel from source systems into a retrieval index, where they get lost, and which negative tests show that a user cannot retrieve what they may not open.
Fine-tuned model evaluation
How to show that a fine-tuned model should replace the current one: acceptance criteria written in advance, a fair held-out comparison, and cost and latency in the same table.
MCP tool design
Why an MCP server should usually offer a few tools shaped around business actions instead of mirroring every API endpoint, with a worked example and a tool contract.
Questions
Are you an AI agency or an AI consulting firm?
An engineering company. The people who advise you are the engineers who build, test and hand over the work in your systems, so recommendations are checked on your own data before you commit to them. We don't resell tools, and no model or tool vendor pays us.
Where does an AI transformation start?
With one piece of work and a baseline: what it costs today and how good the result is, measured on your own data. We then pick the service that changes that number, and expand only after the first change has been measured.
Do you work with mid-sized companies?
Yes. Our work fits companies of any size that run their own software and have an engineering or IT team. Training runs remotely or on site in Germany and Poland, in English, German or Polish.
Something else in mind?
We also take on build systems, test suites, delivery pipelines and engineering work with no agents involved.
Talk to an engineerHow a project runs
Before any work starts, we agree the scope, access and data flows with you. Our engineers then work inside your team, part-time or on a longer placement, and everything we build stays with you, including configuration, runbooks and measurements.
How we workTalk to an engineer
Bring one piece of work you would like to improve. The call takes 30 minutes and needs no access to your systems or your data.
Booking runs on Google Calendar.

Mickey Graf
Founder and CEO of Cloudsail
Prefer to write first? Leave your email and a few lines. Mickey reads every message himself and replies by email with times for a call.
Look for the draft in your email program
Send it from there, and Mickey replies in person with times for a 30-minute call. If no draft has opened, write to us at miki@cloudsail.com.