Your business on autopilot.
We design and build agentic systems — plugins, skills, specialised agents, MCP connectors, guardrails — installed directly inside the Claude (Anthropic) or OpenAI environment you already pay for. No heavy infrastructure, no extra SaaS: tools wired into your data and systems that prepare and execute while you keep the decision.
Book a meeting →Who it's for.
SMBs and SMEs already using Claude or ChatGPT — or ready to — that want far more than a chatbot: agents wired into their data, tools and processes, whatever the trade. Clients leaving a workshop with a roadmap; organisations that refuse generic SaaS lock-in and want to keep control of their code and data. Based in Lausanne, we travel to Paris and across Switzerland for scoping and steering committees; development happens remotely.
Four phases, sequential.
Each phase produces a testable deliverable. A formal go/no-go decision between phases. No vague promises: a clear scope, a firm budget, and your right to stop at any point.
Forward Deployed
We draw on the Forward Deployed Engineering model invented by Palantir and now deployed by OpenAI and Anthropic at their enterprise clients: a senior engineer embedded with the client, who discovers the problem on the ground, prototypes within days, ships working code, and stays to ensure adoption. We adapt it for European SMEs and mid-market companies, without single-vendor lock-in, at a scale that fits.
What we build.
Business plugins & skills
Packaged competencies for Claude Code, Cowork or ChatGPT: your procedures, your document templates, your tone, activated in one command.
Specialised agents
Agents dedicated to one function (prospecting, invoicing, content, operations…) that prepare the work and submit it for your validation.
MCP connectors
The bridge between your AI and your systems: CRM, ERP, Airtable, email, LinkedIn. Your agents read and act on your real data.
Guardrails & hooks
Irreversible actions blocked, an action journal, mandatory human validation before any external send. Autopilot, without the cold sweats.
Routines & automations
Morning briefs, weekly reviews, scheduled follow-ups: tasks that run on their own and report back.
The Sales IQ Cockpit.
The agentic system we use to run Sales IQ every day, directly inside Claude: six plugins covering prospecting, clients, content and operations. It's exactly what we build for our clients — applied to our own business.
You decide; Claude prepares, executes and reports.
Transverse protections: external sends and irreversible actions blocked, action journal.
Qualify, approach, prep calls, track the pipeline.
Meeting notes, onboarding, invoicing preparation.
LinkedIn posts, editorial calendar, content recycling.
Morning brief, weekly review, GO/NO-GO decisions.
Target-driven prospecting funnel: targeting, email + LinkedIn sequences orchestrated in Airtable.
Sales is our trade, so that's where we started. But the mechanics are the same for any function: finance, HR, production, support. Your business, your agents.
What we build on.
- Claude Code · Cowork · Claude.ai
- ChatGPT · OpenAI
- Your existing subscription
- Plugins & skills
- Agents & subagents
- Hooks & guardrails
- MCP (Model Context Protocol)
- CRM · ERP · Airtable
- Email · LinkedIn
- Autopilot
- Explicit human validation
- Action journal
How we work.
Fixed-fee per project
No open T&M. Firm quote with precise schedule from scoping onwards.
Full IP ownership
You own the code, the data, the fine-tuned models. No lock-in.
Systematic handover
Documentation, training, code transmission. Your team can take over.
Paid, committing scoping
Initial scoping is billed and produces a firm quote. You then decide whether to continue.
Why no catalogue pricing.
Every agentic system is unique: scope, integrations, autonomy level, guardrails, user base size. Quoting a price before understanding the project would be either misleading or unfavourable to the client. The initial scoping phase (paid) produces a firm, binding quote along with a tailored timeline estimate. And because the systems install into the Claude or OpenAI subscription you already pay for, there is no infrastructure to fund and no extra licence: you pay for the development, not rent.
What sets us apart.
- 1We run our own company with our own agents: the Sales IQ Cockpit is our daily proof, not a demo.
- 2Systematic skills transfer, built into the project. No residual dependency.
- 3Fixed-fee per project, not T&M. You know what you pay before signing.
- 4Real B2B expertise: our AI workshops keep us close to leadership challenges.
A process ready for autopilot?
30 minutes to understand your technical context and verify whether we're the right partner for your project.
Book a meeting →