# Shipsteer > We build an AI agent pipeline from ticket to production inside your company in about 4-6 weeks, on a BDD test foundation, and train your team to run it. Based in Poland, working remotely or on site across the EU, in Polish and English. Agents write the code. Your team makes the decisions. We work with agents ourselves: our agents map your repo, tests and CI, draft the first scenarios and build the configuration from proven templates. People handle the conversations, design, decisions and accountability. ## Pages - [English](https://shipsteer.eu/en/): Shipsteer | AI agent delivery pipelines for dev teams (BDD) - [Polski](https://shipsteer.eu/): Shipsteer | Wdrożenie agentów AI w zespole developerskim (BDD) ## How an engagement runs - Step 1: We learn your product, company and workflow (3-5 days). Interviews with the team and decision makers. Our agents map repo, tracker, CI and scenario coverage in a few hours. Outcome: Readiness report with a test assessment, pipeline design, first ticket class. - BDD foundation, if tests are missing (1-3 weeks). Agents describe the existing product behaviour as scenarios and your team approves them. Only then do agents change code. Outcome: Key product paths covered by scenarios and running in CI. - Step 2: We build the AI agent pipeline (2-3 weeks). Context for agents, quality gates, scenario and QA agents, implementation and review agents, a question layer, morning report, integrations. Outcome: First agent tickets in week one of the build, an end-to-end pipeline on the first repo. - Step 3: Continuous delivery (CI/CD) (1-3 weeks). CI on every merge request, preview environments, promotion development → staging → preprod → production, acceptance tests on selected environments, release checks, monitoring, fast rollback. Outcome: Agent work reaches production regularly and safely. - Step 4: We train and hand over (1-2 weeks). Workshops for developers, leads and product owners, pairing on running the pipeline, a runbook. Outcome: Your team runs, tunes and extends the pipeline on its own. - Step 5: We tune and grow the pipeline (ongoing, min. 3 months). Prompts and gates improved from metrics, models matched to roles, more ticket classes and repos, more parallel agents. Outcome: More tickets done without rewrites, lower cost per ticket. Larger engagement (several repos or teams): about 6-8 weeks. Pace depends on access to repo, tracker and CI within the first 2 days and a decision maker who answers questions within one working day. Steps can be bought separately. ## When an agent needs a decision When a requirement is unclear or there are several reasonable solutions, the agent moves the ticket to “Needs clarification” and writes one comment. You answer in a line, without a meeting. Example comment in ticket #142 "Validate VAT ID in form": - Problem: The ticket says “validate the VAT ID”. A number can be checked by format only, or online in the EU VIES registry, which is sometimes unavailable. - Question: Should the order be blocked when VIES does not answer? - Options: A) Format check only: Fast and never blocks, but accepts made-up numbers. B) Format now, VIES in the background: The order goes through, an invalid number flags the invoice for the accountant. C) Block until VIES confirms: Safest, but orders fail whenever VIES is down. - Recommended path: B. The checkout scenario “order completes in under 3 s” would fail with C, and B follows how the payment webhook already retries. Meanwhile I am working on the other scenarios of this ticket. - Answer (product owner): B. And email the accountant when an invoice is flagged. - Agent: Added the scenario “Invalid VAT ID flags the invoice and notifies the accountant”. Resuming. - The agent stops instead of guessing: Unclear requirements, several reasonable solutions or a change in product behaviour mean a question, not an assumption hidden in the code. - One comment, everything needed to decide: The problem in context, one concrete question, two or three options with their consequences and the path the agent recommends, with the reason. - The answer goes straight into the work: The agent turns the decision into a BDD scenario, updates the ticket and resumes. The decision stays in the ticket history, open questions appear in the morning report. ## Where agents work well and where they don't - Works well: Tickets with BDD scenarios or clear criteria. Works poorly: Vague requirements like “make it better”. - Works well: CRUD, API integrations, migrations, tests, docs. Works poorly: Architecture decisions and cross-cutting changes across services. - Works well: Bugfix with a reproduction. Works poorly: Performance, concurrency, security-critical code. - Works well: Screens from an existing design system. Works poorly: Code without functional tests, until we build the BDD foundation. Monthly report: behaviour coverage by BDD scenarios and its growth; share of tickets merged without rewrites; share of tickets with a question and response time; AI cost per merged ticket; lead time from ticket to production and release count; change failure rate and review time. ## Pricing (net, EUR; PLN prices on the Polish page) - Readiness scan: €0. A 30-minute call and a short questionnaire about your repo, tests and CI. Within 2 working days you get a readiness assessment and a recommendation on where to start. - Discovery and design: €2,000. 3 working days, a readiness report with a test assessment and a pipeline design. Credited towards the engagement if you start it within 60 days. - BDD foundation: from €5,000. Scenarios for the key paths, running in CI. Valuable on its own. - Pilot with a success criterion: from €12,000. 3-4 weeks, one ticket class, one repo. We write the success criterion into the contract after step 1. If we miss it, you don’t pay the last instalment. The report covers tickets, stories, bugs, cases from the QA agent, automated checks and human decisions. - Small engagement: about €26-29k, about 4-6 weeks. 5-20 developers, 1-2 teams, 1 main repo, one decision maker. care €3,900/month, AI budget up to €1,200/month included. - Larger engagement: about €52-59k, about 6-8 weeks. 20-80 developers, 3+ teams or several products, several decision makers. care €7,500/month, AI budget up to €2,400/month included. - Training: from €2,100, 1-2 days or 1-3 weeks of pairing. For client teams and companies building a pipeline themselves. open training €690 per person. ## Training - Working with agents as a team (Developers; 2 days, up to 12 people): €5,200. Context for agents, reviewing agent changes, working with quality gates. On your code. - BDD and tickets for agents (POs, analysts, testers, developers; 1 day, up to 12 people): €2,100. Acceptance criteria as Given / When / Then scenarios an agent can do without questions and a machine can verify. - BDD in practice (Product teams; 2 days, up to 12 people): €4,700. A workshop on your code: first scenarios for the most important product paths. - Agentic pipeline lead (Tech leads, EMs; 1 day, up to 8 people): €2,100. Metrics, cost per ticket, who decides and how fast. - Pipeline takeover (1-3 of your people; 1-3 weeks pairing): €5,900. Your people tune, scale and fix the pipeline on their own. - Open training (Individuals; 2 days, groups up to 12): €690 / person. The basics of the model and a chance to meet us. Remote, or on site in the EU. ## FAQ ### We already have Cursor or Claude Code. Why do we need you? A tool is not a process. We build the system around it: context, quality gates, questions, reports, CI/CD and team training. You’d get there by trial and error in a few months; with us it takes a few weeks. ### We have more than 50 developers. Is this for us? Yes. We most often work with companies that have from a few to a few dozen developers, but we are happy to talk to larger ones. In a big organisation we start with one team and one repo, then expand. ### Will agents replace our developers? No. They change their work: less routine, more decisions, review and hard problems. ### We have no functional tests. Does this make sense? Yes, and that is exactly where we start. The BDD foundation comes first: we describe product behaviour as scenarios, and only then do agents change code. That stage alone gives you value, even without further steps. ### Why BDD and not just unit tests? Unit tests check the code; BDD scenarios check that the product does what the business wants. An agent can write correct code that does the wrong thing. A scenario catches it. ### Who is responsible for what goes to production? A human on your side always approves the merge. An agent never pushes code to the main branch on its own and has no access to production. Only the pipeline deploys to production, after a human approves. ### Can training and the engagement be remote? Yes, we run most of the work remotely. For workshops and the engagement kick-off we can come to you, in Poland or elsewhere in the EU. ### Is our code safe? We work under a data processing agreement (DPA). For regulated companies, models run on your own cloud account. ### How much does the AI cost? The budget is included in the package; any overage is billed transparently with an alert at 80%. ### What if we stop working together? The pipeline, configuration and documentation live in your repo, and your team is trained. ### Which models do you use? We match them to the task (Claude, OpenAI models, models on Bedrock or Vertex). We are not tied to one vendor. ## Contact - Email: kontakt@shipsteer.eu - Free readiness scan and calls: https://shipsteer.eu/en/#kontakt