Skip to main content
skilder

Your teams already use AI. Take it to the next level.

From individual habits to a shared AI workforce: skilder turns the way your teams already use AI into clear roles built on your processes, working alongside your people, monitored and governed.

skilder

Pick an AI interface to start.

Supported by

The problem

Your people adopted AI faster than your organisation.

Everyone has their own prompts

Know-how lives in people’s heads and chat histories. When someone leaves, it leaves too.

Zero visibility on ROI

You can’t tell who uses what, for which task, or what it actually brings in.

Shadow AI

Personal accounts, internal documents pasted into chats: your data moves outside any framework.

AI roles

AI roles, built on your processes.

A role is one of your company’s jobs translated for AI: its procedures, document templates and tools. Build it once, the whole team uses it.

  1. Capture Your best practices become reusable skills, versioned and documented.
  2. Share Publish a role to a team in one click. Everyone calls it from the assistant they already use.
  3. Improve Real usage shows what works. You refine it, everyone benefits.

Example roles

  • Sales
  • Legal
  • HR
  • Ops
  • Marketing
  • Support
skilder mascot at work at its desk

Insights

See what gets used. Measure what it pays back.

Every use of a role is tracked. You finally know where AI saves time, and what that time is worth.

Dashboard · this month

Illustrative data

Role Uses Time saved Value
Sales assistant 412 96 h EUR 8,600
Legal counsel 287 74 h EUR 6,700
Human resources 184 41 h EUR 3,400
Marketing assistant 98 19 h EUR 1,500

Governance

Scale without losing control.

Going from a few users to the whole company takes a framework. skilder builds it in from day one.

Permissions

Everyone reaches the roles and tools they need. Nothing more.

Versioning

Every skill has a history. You know what changed, and you can roll back.

Auditability

Every use is traced, from request to tool call. Ready for your audits.

Sovereignty

Hosted in Switzerland by Infomaniak, or installed on-premise in your own environment.

Get started

Keep your tools. Plug in skilder.

skilder is agnostic. Your teams keep the AI assistant they know, and skilder connects to it through MCP, the open standard.

  1. Connect your model

    Pick your company’s AI assistant, or a model hosted in Switzerland.

  2. Build your first roles

    We start from two or three priority processes, with your teams.

  3. Deploy and measure

    Roles go live, usage comes back, ROI becomes visible.

Works with your AI stack

And with your ecosystem

Customers

Already rolling out their AI roles with skilder.

OrllatiIDRHEquallMemowaysFutura21ADOPT-AI

Expert session

Let’s move your AI adoption forward, together.

30 minutes with an expert, free, no strings attached.

Tell us what you need

You leave with

  • A map of how your teams use AI today
  • Two or three priority roles to build
  • An estimate of the time you can win back

FAQ

The questions we get most.

Another question? Ask it on the call, a founder will answer.

Ask an expert

  • What is skilder?

    Most organisations have bought Claude, ChatGPT or Copilot licences and watched adoption stall, because every employee has to re-explain their job to the AI each time. skilder fixes that. It is a registry and control plane that turns your know-how into governed roles, one per seat on the org chart, assembled from Agent Skills and scoped MCP tools. Employees keep the AI client they already have; the role arrives inside it. skilder adds no new tool to open.

  • What exactly is a role, and how is it different from a Claude Skill?

    A Claude Skill is a single SKILL.md file: instructions, optional scripts, reference content. It describes one capability and is portable across any agent that reads the standard. A role is the work one seat actually does: it bundles several skills with the MCP tools that seat may reach, its context and its permissions, and serves them on demand to any MCP-compatible agent. The skill is the capability; the role is how that capability runs in your company, versioned, access-controlled and traced.

  • Do roles work out of the box?

    No, and that is by design. skilder ships blueprints for 60+ functions, from finance to legal to support, and each one is configured to your playbooks, systems and vocabulary before it goes live. Configuring a role from a blueprint takes a few clicks in a visual interface, not code. Engineers are only needed when you want to expose a custom internal system as an MCP server.

  • Is our business data safe with skilder?

    A role is the permission boundary: it reaches only the connectors granted to it centrally, those grants are revocable, and they never widen at runtime. Access is governed by SSO and role-based access control, with tenant isolation between workspaces. Every task is logged and attributed to the person who sent it; skilder keeps that execution trace, and you can export or delete it. Hosting is sovereign in Switzerland or the EU, with on-premise available, and LLM providers run under zero-data-retention terms, so your data never trains a public model.

  • How much does skilder cost?

    There is a free plan with usage included, so a builder can configure and run a first role before talking to anyone. Paid plans scale with usage, meaning executions, connected tools and governed users, and add enterprise SSO, advanced audit and dedicated support. skilder does not charge per seat, and authoring roles is always free: you pay for what your organisation actually runs.

  • What is skilder Factory?

    skilder Factory is the fast lane. The skilder team works beside yours for two weeks: your first roles configured, SSO and permissions set, everything tested on real work, then the keys handed over. Two ways to work together: delegate the build, or have your own champions backed while they ship. The self-serve path stays free and is enough to configure a first role. Durations, scope and prices are on the Factory page.

The blog

Our latest thinking.

Field notes on Agent Skills, MCP and governed AI: what holds up in real deployments, and what quietly breaks.

Read the blog