Expertise
AI agents, automation and business tools.
From cloud services and APIs to sovereign deployment, I connect your use cases, your data and your tools. Audit, delivery or training: we choose the format that fits your starting point.
Engagement formats
Three ways to move forward.
Clarify a decision, build a tool or support your team. Where you start depends on what you need today.
Audit & scoping
Know what to build, with which data and for what use.
- Your situation
- You have a task to improve, several technical options or an AI project whose feasibility has yet to be established.
- Possible deliverables
- A map of the process and its constraints
- Reasoned options, with or without AI
- A prioritized scope and success criteria
- The first step
- Describe a concrete task, its users and what is blocking today. An anonymized example can then be used for scoping.
Design & deployment
Move from a defined need to a usable, verified system.
- Your situation
- You want to connect your tools, automate a flow or create a business application. The interface, the data and day-to-day operation need to work together.
- Possible deliverables
- Documented architecture and integrations
- A tool tested on representative situations
- Go-live and hand-over documentation
- The first step
- Describe the expected use, your existing tools and the access constraints. Together we define a first scope to build and evaluate.
Training & support
Help your teams choose, use and evolve their tools.
- Your situation
- Your team wants to understand how AI can be used, get to grips with a tool or have a technical perspective on its choices.
- Possible deliverables
- Workshops tailored to roles and uses
- Hands-on exercises and materials
- Recommendations and a shared roadmap
- The first step
- Tell me who is involved, how they work today and the decisions or tasks on which they need to become more autonomous.
I have led AI training and awareness sessions in public administration, for staff and managers. References available when we talk.
The scope, deliverables and terms are defined together before the engagement.
Technical domains
Choose the architecture that fits the use.
AI agents & API integrations
Design an agent that can consult your tools, prepare an action and carry it out within a defined scope. From cloud services to sovereign deployment, with explicit access and verifiable results.
The right starting point if your need involves actions across several tools.
Document automation
Turn transcription, extraction or summarization tasks into a coherent workflow, with checks and a review step suited to your documents.
The right starting point if a document task ties up your teams.
AI assistant for your documents
An assistant that answers from your internal documents, cites the passages it used and says when the information is missing. A controlled alternative to using consumer tools on sensitive data.
The right starting point if your teams spend a long time looking for information that already exists in your documents.
Custom business applications
Design and build an internal application fitted to your processes: a workflow designed with its users, connections to your existing tools, access rights and traceability. With AI where it adds value, without it otherwise.
The right starting point if a spreadsheet, ill-fitting software or repeated data entry is slowing down an important process.
Sovereign AI
Scope the use cases, data flows and dependencies before choosing an architecture. For organizations that want to adopt AI while keeping control of their own systems.
The right starting point if you need to decide on use cases and architecture.
On-premise LLMs
Design a local AI pipeline, evaluate it on your use cases and integrate it with your tools. For teams with a hosting constraint or a need to work offline.
The right starting point if your hosting constraint is already clear.
AI training for teams
Workshops that help your teams use generative AI in their actual work: choosing the uses that help, checking the results, protecting data and knowing when not to use it.
The right starting point if your teams already use AI without shared guidelines, or are hesitant to start.
The skills that tie it all together.
Document search & RAG
A defined corpus, sources you can consult and answers evaluated against your own questions.
Business tools & interfaces
Workflows designed with their users, integrated with your existing applications and access controls.
Security & operations
Explicit permissions, checks and documentation so the system can be taken over and evolved.
Method
A clear project, at every stage.
Technical choices follow the need. Deliverables make each decision concrete.
Understand
A shared scope
Design
Choices, explained
Build
A proven tool
Hand over
A next phase under control
Next step
A need still to be defined?
Describe your context, the tool involved and what you would like to improve. We can then define the first useful step.