The Agentic Engineering Company

AI agents in everyday work, with every task measured for cost and quality

We build AI agents and models with your teams, for software development and for the processes behind your business. They run on infrastructure you control. Each change is tested on work you have already done, and we keep it only when it is cheaper and at least as good. When we are done, your team owns it and can run it without us.

Talk to an engineer Find your starting point

What we work on

Coding agents

We set up coding agents that know your repositories and stay within budget, and test each change on code you have already merged.

LLM cost optimisation Harness engineering Coding agent adoption Evaluations on your repositories

Help with Claude Code, Codex, Cursor or Copilot

AI agents and process automation

Agents take on the routine part of complex cases, such as claims, invoices or service requests, and pass anything uncertain to a person.

A test set built from your past casesSign-off wherever a decision mattersA cost in euros for every handled case

How a first project runs

Custom model training

For one well-defined, high-volume task, we train a small open-weight model on your data that costs far less to run than a large general model.

Training data from cases with known outcomesA test against your current model before any switchServing and retraining in your environment

When training is worth it

AI engineering and architecture

We add AI to the products you sell and build the serving, retrieval and connections to your systems that it relies on.

Assistants and voice interfacesRetrieval and MCP serversModel serving, GPUs and cloud setup

What we build into products

You can start with any of them.

Our team has built software and production AI for

Find your starting point

Each situation links to the service where the work begins.

Agent costs grow every month, and no one can say which team or task is behind themSpend attributed by team and task, then defaults, budgets and routingLLM cost optimisation Agents open more pull requests than review can keep up withChecks that run before review, and review routed by riskHarness engineering Some teams rely on agents every day, others barely use themTraining on real tickets and one shared setup for every teamCoding agent adoption Cases still move between inboxes, PDFs and systems by handOne process mapped and measured, then an agent for its routine stepsAI agents and process automation The pilot looked good, but no one will trust it with real cases yetA test set of past cases, sign-off steps and a cost per caseAI agents and process automation One task runs hundreds of thousands of times a month on an expensive modelA small open-weight model trained for that task and tested against the current oneCustom model training Data and models must not leave infrastructure you controlServing, retrieval and agents in your own cloud account or on your own serversAI engineering and architecture Your roadmap holds more AI work than your team can take onOur engineers in your teams, part-time or placed for longerHow we work

What changes for you

The cost of each task, in euros

You see what an accepted change, a handled case or a model request costs, by team and task, with the acceptance or error rate beside each figure.

Decisions backed by your own data

Every option is tested on your past work first, and you get a clear recommendation, including when to stop.

A setup your team owns

Configuration, test sets and runbooks stay with you, written so your team can run them without us.

How we test each change

Each kind of work is tested differently, always on your own data.

Coding agents

We replay changes your team has already merged, against tests the agent cannot see.

Process agents

We run past cases with known outcomes and compare the agent's answer with the real one.

Custom models

We compare the new model with your current one on cases it was not trained on.

Coding agents: cost per finished task

Before and after a change to the setup

Bug fixes

€3.10 to €2.30

Refactors

€4.20 to €3.30

Tests

€1.90 to €1.30

Reviews

€1.10 to €0.85

€62000 to €49000 a month

Rework 11% to 10%

Example with synthetic data.

Working with us

A first project with one clear question

A single process, team or model, with the measures agreed before we begin.

Built together with your people

Our engineers work in your teams on real tasks, and your colleagues learn the setup while it is being built.

Yours to run

You get the code, test sets and runbooks, and we step back once your team is comfortable running them.

You can bring us in for a defined project, have our engineers join your teams part-time or for longer placements, or book training on your own work. Training runs remotely or on site in Germany and Poland, in English, German or Polish.

How an engagement runs

The people behind the work

Three founders run Cloudsail, and the engineers who scope your project also build it with your team and hand it over.

Meet the team

Mickey GrafFounder and CEO
Johann DeckCo-founder and CTO
Maximilian LehmannCo-founder and COO

“I am incredibly grateful to Mickey and the team for their work here. They listened deeply, delivered with great expertise and I trust them implicitly. Stellar work.”

Justin Buckthorp, Founder and CEO, 360 Health & Performance

How we handle data

Work happens in your environment, and every data flow is agreed with you first.

No model or tool vendor pays us, so our advice follows what works on your data.

Each contract includes a data processing agreement.

Reports cover teams and tasks. We never report on individual employees.

We handle your works council's requirements before anything goes live, and prepare the documentation your data protection team needs.

Recent writing

All posts

The latest posts, each with the date it was last checked against the vendors' own documentation.

AI SDLCHow coding agents change each phase of the software development lifecycle, who owns each handoff, and how to measure and govern the change.Spec-driven developmentHow to write specs coding agents can follow, take one change from spec to merge, and choose between Spec Kit, OpenSpec, BMad, GSD and Kiro.AI code reviewHow to set up AI code review and keep a person accountable for every merge when coding agents write more of your pull requests.Coding agent securityPractical security and governance for coding agents: prompt injection, secrets, permissions, sandboxing, unattended runs and ownership.pstack workflowsWhat the pstack plugin for Cursor contains, how its playbooks and model roles work, and how a team adopts it under its own controls.Autonomous software factoryWhat it takes for coding agents to carry scoped work from issue to merge, which work fits, and where people stay in control.

Common questions

Is the first conversation free?

Yes, there is no charge.

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.

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.

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.

How do you report results?

By team, task and model, with cost and quality side by side.

What if a change doesn't pay off?

Then we leave it out. You keep the test set and the measurements either way.

Talk 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.