<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>skilder · Blog EN</title><description>skilder articles in English.</description><link>https://www.skilder.ai/</link><language>en-US</language><item><title>AI agent glossary: role, skill, MCP server and the terms around them</title><link>https://www.skilder.ai/en/blog/ai-agent-glossary/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/ai-agent-glossary/</guid><description>Plain definitions of the terms that come up when a company governs AI agents: role, blueprint, skill, SKILL.md, MCP, MCP server, connector, registry, context lake, execution trace and more.</description><pubDate>Sun, 15 Nov 2026 00:00:00 GMT</pubDate><category>product</category><category>glossary</category><category>roles</category><category>skills</category><category>mcp</category><category>ai-agents</category><category>governance</category></item><item><title>AI maturity: 12 readiness questions before you scale AI</title><link>https://www.skilder.ai/en/blog/ai-maturity-readiness-questions/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/ai-maturity-readiness-questions/</guid><description>Most AI maturity models score the whole company. These 12 readiness questions, asked workflow by workflow, show what is ready to scale, who owns it and how to measure it.</description><pubDate>Thu, 12 Nov 2026 00:00:00 GMT</pubDate><category>governance</category><category>governance</category><category>ai-maturity</category><category>roles</category><category>shadow-ai</category><category>ai-roi</category></item><item><title>How to connect internal business systems to Claude and ChatGPT securely</title><link>https://www.skilder.ai/en/blog/connect-internal-systems-ai-securely/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/connect-internal-systems-ai-securely/</guid><description>A technical guide to connecting a CRM, email, file storage or ERP to Claude and ChatGPT through MCP, with per-user OAuth, least-privilege scopes, audit logs and a tested revocation path.</description><pubDate>Thu, 12 Nov 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>mcp-gateway</category><category>governance</category><category>ai-security</category><category>tool-use</category></item><item><title>MCP gateway vs skills platform vs Copilot Studio: which one to start with</title><link>https://www.skilder.ai/en/blog/mcp-gateway-vs-skills-platform/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/mcp-gateway-vs-skills-platform/</guid><description>An MCP gateway governs tool access, Copilot Studio builds Microsoft 365 agents, and what buyers call a skills platform is really agent roles. What each one does, and which one to start with.</description><pubDate>Wed, 11 Nov 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>skills</category><category>mcp-gateway</category><category>roles</category><category>governance</category></item><item><title>AI governance framework: a practical template for European companies</title><link>https://www.skilder.ai/en/blog/ai-governance-framework-template/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/ai-governance-framework-template/</guid><description>A practical AI governance framework template for European companies: a one-page frame, a register with one row per AI capability, six steps to fill it in, and how it maps to the AI Act.</description><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate><category>governance</category><category>governance</category><category>ai-governance</category><category>roles</category><category>shadow-ai</category><category>ai-act</category></item><item><title>AI policy for employees: a usage policy template people follow</title><link>https://www.skilder.ai/en/blog/ai-policy-for-employees/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/ai-policy-for-employees/</guid><description>What an AI policy for employees should contain, a usage policy template you can adapt, and how to roll it out so employees use the approved tools instead of their own accounts.</description><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate><category>governance</category><category>governance</category><category>shadow-ai</category><category>ai-governance</category><category>roles</category></item><item><title>How to turn an SOP into an AI skill employees can run in Claude, ChatGPT or Copilot</title><link>https://www.skilder.ai/en/blog/sop-to-ai-skill/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/sop-to-ai-skill/</guid><description>A step-by-step guide to rewriting a standard operating procedure as an AI skill: a SKILL.md template, a worked example, MCP tools, tests, versions and an owning team.</description><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate><category>product</category><category>skills</category><category>mcp</category><category>roles</category><category>claude</category><category>copilot</category></item><item><title>Runlayer and Composio alternatives for distributing MCP tools internally</title><link>https://www.skilder.ai/en/blog/runlayer-composio-alternatives/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/runlayer-composio-alternatives/</guid><description>Runlayer and Composio govern or supply MCP tools for engineers. Six alternatives compared on end users, per-user auth, governance and hosting, with a shortlist by team and a method to reach business users.</description><pubDate>Sun, 08 Nov 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>mcp-gateway</category><category>governance</category><category>roles</category><category>tool-use</category></item><item><title>AI audit trail: the execution logs EU compliance teams ask for</title><link>https://www.skilder.ai/en/blog/ai-audit-trail-execution-logs/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/ai-audit-trail-execution-logs/</guid><description>What an AI audit trail must show an EU compliance reviewer: the fields skilder records for every run, a sample exported record, and how to use it in an incident and in a quarterly review.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate><category>governance</category><category>governance</category><category>ai-agents</category><category>roles</category><category>mcp</category><category>ai-security</category></item><item><title>MCP registry vs MCP gateway: what each one does, and why you need both</title><link>https://www.skilder.ai/en/blog/mcp-registry-vs-mcp-gateway/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/mcp-registry-vs-mcp-gateway/</guid><description>An MCP registry decides which MCP servers exist and are approved. An MCP gateway enforces policy on every call. What each one does, where it sits in the request path, and what neither of them solves.</description><pubDate>Sun, 01 Nov 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>mcp-registry</category><category>mcp-gateway</category><category>architecture</category><category>governance</category><category>security</category></item><item><title>skilder wins Venture Kick Stage 2: CHF 40,000</title><link>https://www.skilder.ai/en/blog/skilder-wins-venture-kick-stage-2/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skilder-wins-venture-kick-stage-2/</guid><description>skilder has won Stage 2 of Venture Kick and receives CHF 40,000 to help companies deploy AI capabilities securely, inside the tools their teams already use.</description><pubDate>Mon, 26 Oct 2026 00:00:00 GMT</pubDate><category>product</category><category>news</category><category>funding</category><category>skilder</category><category>venture-kick</category><category>switzerland</category></item><item><title>Shadow AI statistics 2026: the numbers, with their sources</title><link>https://www.skilder.ai/en/blog/shadow-ai-statistics-2026/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/shadow-ai-statistics-2026/</guid><description>Shadow AI statistics for 2026, each with its primary source and date: how many employees use unapproved AI, what data goes in, the governance gap and what shadow AI costs in breaches.</description><pubDate>Thu, 08 Oct 2026 00:00:00 GMT</pubDate><category>governance</category><category>shadow-ai</category><category>statistics</category><category>governance</category><category>ai-security</category><category>research</category></item><item><title>Agent plugins vs. skilder roles: what each one packages, and where it runs</title><link>https://www.skilder.ai/en/blog/agent-plugins-vs-skilder-roles/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/agent-plugins-vs-skilder-roles/</guid><description>Agent plugins bundle skills, MCP servers and hooks into one install for one client. A skilder role serves skills and scoped tools to any MCP agent from a governed workspace. How they differ, and when to use which.</description><pubDate>Mon, 05 Oct 2026 00:00:00 GMT</pubDate><category>engineering</category><category>agent-plugins</category><category>claude-code</category><category>codex</category><category>skills</category><category>mcp</category><category>governance</category></item><item><title>Progressive skill discovery as access control: what the skilder paper measures</title><link>https://www.skilder.ai/en/blog/progressive-skill-discovery-paper/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/progressive-skill-discovery-paper/</guid><description>A 30-page white paper tests whether serving skills through one MCP server can enforce what an agent may do. 13 scenarios, six models, three tool interfaces, and the limits the authors report.</description><pubDate>Thu, 01 Oct 2026 00:00:00 GMT</pubDate><category>governance</category><category>mcp</category><category>roles</category><category>research</category><category>access-control</category><category>context</category></item><item><title>LiteLLM vs agentgateway vs skilder: three layers, not three rivals</title><link>https://www.skilder.ai/en/blog/litellm-vs-agentgateway-vs-skilder/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/litellm-vs-agentgateway-vs-skilder/</guid><description>LiteLLM fronts the models, agentgateway fronts the tools and agents, skilder defines the roles an agent performs. What each one governs, where it sits in the request path, and which one to deploy first.</description><pubDate>Wed, 30 Sep 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>mcp-gateway</category><category>governance</category><category>tool-use</category><category>skills</category></item><item><title>skilder selected for Tech4Trust season 8</title><link>https://www.skilder.ai/en/blog/skilder-tech4trust-season-8/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skilder-tech4trust-season-8/</guid><description>skilder joins the eighth season of Tech4Trust, Trust Valley&apos;s accelerator for digital trust: nine months to help AI agents move from pilot to production.</description><pubDate>Wed, 30 Sep 2026 00:00:00 GMT</pubDate><category>governance</category><category>news</category><category>skilder</category><category>tech4trust</category><category>switzerland</category><category>governance</category></item><item><title>Least privilege for AI agents: the role is the permission boundary</title><link>https://www.skilder.ai/en/blog/least-privilege-ai-agents/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/least-privilege-ai-agents/</guid><description>Agents inherit whatever their tools can reach. Least privilege for AI agents means scoping tools per role, not per user, and treating every tool description as untrusted input.</description><pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate><category>engineering</category><category>governance</category><category>mcp</category><category>ai-agents</category><category>tool-use</category><category>roles</category></item><item><title>What is an MCP server? The MCP protocol explained simply</title><link>https://www.skilder.ai/en/blog/mcp-server/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/mcp-server/</guid><description>An MCP server exposes tools, data and prompts to an AI agent through the Model Context Protocol. Definition, how the MCP protocol works, examples and the governance questions to settle in the enterprise.</description><pubDate>Mon, 28 Sep 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>mcp-server</category><category>mcp-protocol</category><category>ai-agents</category><category>governance</category></item><item><title>Sovereign AI in Switzerland: hosting, the FADP and vendor independence</title><link>https://www.skilder.ai/en/blog/sovereign-ai-switzerland/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/sovereign-ai-switzerland/</guid><description>What AI sovereignty means in Switzerland: where the data sits, which law applies, which model runs, who stays in control. The FADP framework and the questions to ask an AI provider.</description><pubDate>Sun, 27 Sep 2026 00:00:00 GMT</pubDate><category>governance</category><category>sovereign-ai</category><category>ai-sovereignty</category><category>switzerland</category><category>fadp</category><category>hosting</category></item><item><title>Enterprise AI governance: a practical framework for leaders</title><link>https://www.skilder.ai/en/blog/enterprise-ai-governance/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/enterprise-ai-governance/</guid><description>Enterprise AI governance is more than a usage policy. Registry, named owners, role-based permissions, traceability, lifecycle: the practical framework, the FADP, the AI Act and a ten-question checklist.</description><pubDate>Sat, 26 Sep 2026 00:00:00 GMT</pubDate><category>governance</category><category>ai-governance</category><category>governance</category><category>ai-act</category><category>fadp</category><category>shadow-ai</category></item><item><title>Shadow MCP: the ungoverned MCP servers your employees already connected</title><link>https://www.skilder.ai/en/blog/shadow-mcp/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/shadow-mcp/</guid><description>Shadow MCP is shadow AI with hands: MCP servers employees connect to their AI clients outside any review. What it is, why it is riskier, and how to govern it without blocking.</description><pubDate>Fri, 25 Sep 2026 00:00:00 GMT</pubDate><category>governance</category><category>shadow ai</category><category>mcp</category><category>governance</category><category>security</category></item><item><title>You can&apos;t manage what you can&apos;t measure: the problem of valuing agent skills</title><link>https://www.skilder.ai/en/blog/measuring-agent-skills-value/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/measuring-agent-skills-value/</guid><description>Everyone is building agent skills, but almost no one can say which ones are worth keeping. Why skill value resists measurement, and what an honest answer looks like.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate><category>product</category><category>skills</category><category>ai-agents</category><category>observability</category><category>ai-roi</category></item><item><title>Skilder receives Venture Kick Stage 1 grant</title><link>https://www.skilder.ai/en/blog/skilder-receives-venture-kick-stage-1-grant/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skilder-receives-venture-kick-stage-1-grant/</guid><description>Skilder has been selected by the Venture Kick jury and awarded a CHF 10&apos;000 Stage 1 grant.</description><pubDate>Mon, 14 Sep 2026 00:00:00 GMT</pubDate><category>governance</category><category>news</category><category>funding</category><category>skilder</category><category>venture-kick</category><category>switzerland</category></item><item><title>Context as a First-Class Primitive: Why Your Agent&apos;s Capabilities Shouldn&apos;t Be Baked In</title><link>https://www.skilder.ai/en/blog/context-as-a-first-class-primitive-why-your-agents-capabilities-shouldnt-be-baked-in/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/context-as-a-first-class-primitive-why-your-agents-capabilities-shouldnt-be-baked-in/</guid><description>There&apos;s a quiet architectural decision buried in most AI agents, and it shapes everything downstream: where does the agent&apos;s capability actually live?</description><pubDate>Wed, 26 Aug 2026 00:00:00 GMT</pubDate><category>governance</category><category>context</category><category>skills</category><category>architecture</category><category>connectors</category></item><item><title>SKILL.md, the King of Shadow AI</title><link>https://www.skilder.ai/en/blog/skill-md-the-king-of-shadow-ai/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skill-md-the-king-of-shadow-ai/</guid><description>Why Agent Skills, as currently architected, are becoming the single biggest accelerator of Shadow AI in the enterprise. And what to do about it.</description><pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate><category>governance</category><category>shadow-ai</category><category>skills</category><category>governance</category><category>mcp</category><category>ai-agents</category></item><item><title>Skilder awarded a CHF 20,000 Digital Grant by the FIT</title><link>https://www.skilder.ai/en/blog/skilder-awarded-a-chf-20-000-digital-grant-by-the-fit/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skilder-awarded-a-chf-20-000-digital-grant-by-the-fit/</guid><description>Skilder has been awarded a CHF 20,000 Digital Grant by the Foundation for Innovation and Technology (FIT), the Vaud-based foundation that supports early-stage innovative companies in the canton.</description><pubDate>Tue, 23 Jun 2026 00:00:00 GMT</pubDate><category>product</category><category>news</category><category>funding</category><category>skilder</category><category>fit</category><category>switzerland</category></item><item><title>What is shadow AI?</title><link>https://www.skilder.ai/en/blog/what-is-shadow-ai/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/what-is-shadow-ai/</guid><description>Shadow AI is the unmanaged use of generative AI tools by employees. Definition, real-world risks, and how to respond without killing productivity.</description><pubDate>Wed, 20 May 2026 00:00:00 GMT</pubDate><category>governance</category><category>shadow-ai</category><category>governance</category><category>gdpr</category></item><item><title>Knowledge vs. Know-How: The Distinction Quietly Killing Your AI Agents</title><link>https://www.skilder.ai/en/blog/knowledge-vs-know-how/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/knowledge-vs-know-how/</guid><description>95% of enterprise AI pilots fail not because models are weak, but because they&apos;re loaded with knowledge and asked to deliver know-how. Why these are different categories.</description><pubDate>Fri, 15 May 2026 00:00:00 GMT</pubDate><category>governance</category><category>know-how</category><category>knowledge</category><category>roles</category><category>ai-agents</category></item><item><title>From Context Bloat to Context Load</title><link>https://www.skilder.ai/en/blog/context-bloat-to-context-load/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/context-bloat-to-context-load/</guid><description>Why enterprise AI gets heavier as it gets more capable, and how a capability graph lets you assemble context as a runtime payload instead of a static config file.</description><pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate><category>engineering</category><category>context</category><category>performance</category><category>ai-agents</category><category>architecture</category><category>tool-use</category></item><item><title>The Context Lake: Why Your Data Lake Isn&apos;t Enough for AI Agents</title><link>https://www.skilder.ai/en/blog/context-lake/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/context-lake/</guid><description>A new layer is taking shape in the agentic enterprise stack: the context lake. Business context, tool permissions, and governance need their own home.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate><category>governance</category><category>context-lake</category><category>ai-agents</category><category>governance</category><category>enterprise</category></item><item><title>Beyond &quot;MCP vs Skills&quot;: Composing for Scalable Agent Architecture</title><link>https://www.skilder.ai/en/blog/mcp-vs-skills-composing/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/mcp-vs-skills-composing/</guid><description>MCP solves the N×M connectivity problem. Skills solve context saturation. The real opportunity isn&apos;t picking one. It&apos;s composing skills over MCP, organized by business context.</description><pubDate>Thu, 05 Feb 2026 00:00:00 GMT</pubDate><category>engineering</category><category>mcp</category><category>skills</category><category>architecture</category><category>ai-agents</category><category>tool-use</category></item><item><title>Beyond Single .md Files: How Skill Graphs Scale AI Context</title><link>https://www.skilder.ai/en/blog/skill-graphs-scale-ai-context/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skill-graphs-scale-ai-context/</guid><description>Single skill files hit a complexity ceiling fast. Skill graphs turn domain expertise into a navigable network so agents can traverse business logic instead of guessing.</description><pubDate>Sat, 31 Jan 2026 00:00:00 GMT</pubDate><category>engineering</category><category>skill-graph</category><category>context</category><category>knowledge</category><category>ai-agents</category></item><item><title>Agent Skills vs. Workflow Platforms: Which One Should You Actually Use?</title><link>https://www.skilder.ai/en/blog/agent-skills-vs-workflow-platforms/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/agent-skills-vs-workflow-platforms/</guid><description>Workflow platforms vs. AI agent: it depends on how messy your reality is. A framework for choosing between deterministic workflows and adaptive agent skills, plus the hybrid that wins.</description><pubDate>Thu, 29 Jan 2026 00:00:00 GMT</pubDate><category>product</category><category>skills</category><category>workflow</category><category>automation</category><category>ai-agents</category></item><item><title>RAG vs Agent Skills: The Key Difference Everyone Should Know</title><link>https://www.skilder.ai/en/blog/rag-vs-agent-skills/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/rag-vs-agent-skills/</guid><description>RAG retrieves content. Skills package competencies. Why conflating them limits how companies think about AI agents, and a framework for choosing between them.</description><pubDate>Wed, 21 Jan 2026 00:00:00 GMT</pubDate><category>engineering</category><category>rag</category><category>skills</category><category>ai-agents</category><category>architecture</category></item><item><title>Retrieval Is the New Intelligence</title><link>https://www.skilder.ai/en/blog/retrieval-is-the-new-intelligence/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/retrieval-is-the-new-intelligence/</guid><description>As agents gain access to more tools, the bottleneck shifts from reasoning to retrieval. Why picking the right tool is the next frontier in AI agent design.</description><pubDate>Mon, 19 Jan 2026 00:00:00 GMT</pubDate><category>engineering</category><category>retrieval</category><category>ai-agents</category><category>skills</category><category>tool-use</category></item><item><title>Skills: The Secret Weapon for Smarter AI Agents</title><link>https://www.skilder.ai/en/blog/skills-secret-weapon-smarter-ai-agents/</link><guid isPermaLink="true">https://www.skilder.ai/en/blog/skills-secret-weapon-smarter-ai-agents/</guid><description>Agent Skills are modular instruction sets that extend AI capabilities for specific tasks. Anatomy of a SKILL.md, activation flow, and how to build your first one.</description><pubDate>Sun, 11 Jan 2026 00:00:00 GMT</pubDate><category>product</category><category>skills</category><category>ai-agents</category><category>claude</category></item></channel></rss>