6 results found
Where AI Should Run: Chat Apps, Local LLMs, MCP, APIs, CLIs, and AgentOS
A visual guide to understanding where AI should run, including local LLMs, chat apps, coding agents, MCP, APIs, CLIs, AgentOS, and BYO LLM architectures. Learn how context, tools, permissions, and governance shape the right AI workflow.
Responsibilities of Skills, MCP, CLIs, and APIs
Clarifies responsibilities across Skills, MCP servers, CLIs, and APIs for AI dev workflows—keeping auth, permissions, and audit boundaries clean.
Migrate Contentful to Contentstack in 10 minutes. Content and Code.
Launch an AI-guided tool to migrate from Contentful to Contentstack, moving content and rewriting app code via deterministic CLI steps.
AI will not live in one place, but trust has to
This article discusses the tension between rapidly expanding enterprise AI capabilities and the need for strong governance, introducing a two-layer architecture: off-platform AI for experimental reach and on-platform AI for trusted, governed execution. It explains how combining both layers allows organizations to benefit from flexible, distributed AI while maintaining oversight, brand integrity, and risk management.
Agents are users now and this website is ready
AI assistants are now part of every developer's workflow. This post covers why we built developers.contentstack.com to serve both humans and agents, and how to connect any MCP-capable client to start building on top of it in minutes.
Codex built a skill with custom CLI for itself. Is MCP even a thing anymore?
This article explores how Codex, given a management token, API key, and precise schema documentation, imported content flawlessly and even built a custom CLI and skill to repeat the process, raising questions about the future relevance of MCP in content operations.