An automation written for your process, paired with the right technical profile: AI engineer, developer. The business logic is modelled before it is coded. The code is produced with Claude Code, reviewed line by line, then delivered containerised into your infrastructure: repository, image and documentation are yours. Designed for organisations whose technical team can deploy and maintain an application.
A developed application lives well when someone on your side hosts it, monitors it and updates it. Three capabilities are enough; all are standard operations work, none requires AI expertise.
Someone on your side can run a Docker container, on an internal server or in your cloud, and expose it to its users.
Apply an update, read the logs, react to an alert, manage secrets and API keys. Standard operations work.
Open the repository, find a rule in the model, adjust a prompt or switch models without rebuilding the application.
Each stage is committed separately. The technical scoping stands on its own, and it sometimes points to a simpler level: that is a useful outcome.
Feasibility, target architecture, maintenance load, estimated running cost, and the question asked plainly: which level best answers the need?
The process as it is actually run, gathered from the people who run it, then formalised into diagrams that serve as the specification.
Written with Claude Code under human review, a test set on your real cases, fall-back strategy, containerisation.
Go-live in your environment with your technical team at the controls, operations documentation, then support on request.
Six stages, in this order. The first two make the rest work: an automation lasts when the process was understood before it was coded.
Custom development is the largest investment of the three levels. Chosen well, it is also the most transformative — and this stage is there to make sure before any development starts.
The real process lives in the heads of the people who run it: the exceptions, the implicit trade-offs, the tacit rules. The interviews capture them, and that is what makes an automation hold up in the real world.
The interviews become diagrams. The business validates what it recognises, the technical side validates what it can build. The model then plays three roles: scope contract, development specification, and documentation that outlives the team.
Claude Code writes much of the code from the validated model. An engineer drives, reviews and arbitrates. The gain: speed on what is mechanical, and human time concentrated on what matters.
A live application differs from a prototype in one respect: it knows what to do when a model answers off-target, when an API goes down, when a document arrives in an unexpected format. Here every case has a defined behaviour.
The application is delivered containerised and deploys into your infrastructure, with your technical team at the controls. Your data stays within your perimeter: only the model calls leave, and you know which ones.
No dependency on a subscription, a platform or a supplier. If you decide to carry on alone, everything is there.
History, prompts, configuration and test set. Hosted on your side.
Docker and compose file, redeployable identically with one command.
The process formalised and validated: the reference for any future change.
Install, monitor, diagnose, update, roll back.
Every failure mode, its expected behaviour, who is alerted.
A transfer session, then support on request, at your pace.
Built for you, delivered to you: the tool is entirely yours, and your team knows how to keep it alive.
High volume, many rules, several systems to orchestrate, execution without intervention. Below those criteria, a no-code agent usually answers the need.
Hundreds of orders a week, arriving as PDFs, emails or spreadsheets: extraction, checks against the reference data, injection into the ERP, human hold on any discrepancy.
Several thousand leases reviewed against your analysis rules, with structured output per asset and a link back to the source clause.
Assembling documents to a mandated format, completeness and consistency checks, traceability of every decision made along the chain.
Every incoming request analysed, categorised, enriched with customer context from the CRM, then routed to the right team with a draft reply.
Invoices, delivery notes and scanned customer files: document type identification, field extraction, matching against the order, filing in the right folder.
A system that reads your sources every morning — press, sector publications, regulatory texts — cross-checks them against your watch topics and delivers a sourced summary to the right people.
A scoping call: the target process, your systems, your technical team, the level that fits best.
Three lines is enough: reply within 24 h.