documentation
30 articles about documentation in AI news
3 Documentation MCP Servers to Install Now: GitMCP, Microsoft Learn, and Grounded Docs
Stop tab-hopping for docs. These three MCP servers give Claude Code direct access to GitHub repos, Microsoft Learn, and version-specific documentation.
Andrew Ng's Context Hub Solves AI's Documentation Dilemma for Coding Agents
Andrew Ng's team at DeepLearning.AI has launched Context Hub, an open-source tool that provides coding agents with real-time API documentation access. This addresses a critical bottleneck in agentic AI workflows where outdated documentation causes failures.
AI Coding Agents Get Smarter: How Documentation Files Cut Costs by 28%
New research reveals that adding AGENTS.md documentation files to repositories can reduce AI coding agent runtime by 28.64% and token usage by 16.58%. The files act as guardrails against inefficient processing rather than universal accelerators.
The Agent.md Paradox: Why Documentation Can Hurt AI Coding Performance
New research reveals that while human-written documentation provides modest benefits (+4%) for AI coding agents, LLM-generated documentation actually harms performance (-2%). Both approaches significantly increase inference costs by over 20%, creating a surprising efficiency trade-off.
Install This Claude Code Skill to Remove AI Tells from Your Documentation
The Humanizer skill rewrites Claude-generated text to sound more natural by removing common AI patterns, making your docs and comments more authentic.
Databricks: Best MCP Server for Enterprise Docs Is a Custom Build
Databricks recommends custom MCP servers for enterprise docs. No off-the-shelf solution exists for searchable access to proprietary documentation.
OpenAI Clarifies: text-embedding-3-small Not Deprecated
OpenAI's Head of Developer Experience clarified that a documentation error incorrectly marked the text-embedding-3-small embedding model as deprecated. The model remains fully available and supported for developers.
Ethan Mollick Critiques OpenAI's Mythos Story as Flawed LLM Writing
AI researcher Ethan Mollick dissects a narrative example from OpenAI's Mythos safety documentation, pointing out logical inconsistencies and stylistic tropes characteristic of LLM-generated writing.
How Claude Code Reverse-Engineered an FPGA Bitstream: A Template for Hardware Hacking
Learn the exact Claude Code workflow used to map an Altera Cyclone IV FPGA's bitstream format—from fuzzing scripts to documentation generation.
ForeverSolar Uses Claude Agent SDK to Automate Solar Permitting, Cutting Approval Times
Solar installation company ForeverSolar is using Anthropic's Claude Agent SDK to automate permitting documentation, a major bottleneck in solar deployment. This represents a concrete enterprise application of agentic AI beyond software development.
How to Auto-Approve Safe WebFetches While Blocking Suspicious URLs with Hooks
Use Claude Code's PreToolUse hooks to automatically allow clean documentation URLs while forcing manual review for any URL containing query parameters, eliminating repetitive prompts without sacrificing security.
Open-Sourced 'Skill Pack' Claims to Give AI Agents Full Professional Coder Capabilities
An anonymous developer has open-sourced a plug-and-play 'skill pack' that purportedly equips any AI agent with the full capabilities of a professional software engineer. The release, shared via social media, lacks technical documentation or benchmarks.
How a Developer Used Claude Code to Reverse-Engineer a Bricked Smart Clock from Bare Metal
A developer used Claude Code as a co-pilot to reverse-engineer a dead LaMetric Time clock, creating a full USB-boot recovery system with no documentation.
Stripe's MCP Server: The One Feature That Makes It Worth Installing for Developers
Stripe's official MCP server includes live documentation search—letting Claude Code answer Stripe API questions without tab-switching during development.
BitGo's New MCP Server: Query Crypto Docs & API Directly from Claude Code
BitGo's new MCP server lets Claude Code search and interact with institutional crypto documentation and API references using natural language prompts.
3 Official System Prompts That Stop Claude Code From Hallucinating APIs
Anthropic's official documentation reveals three system prompt instructions that dramatically reduce hallucinations when Claude Code researches APIs or libraries.
How an Industrial Piping Contractor Uses Claude Code for Real-World Engineering
A contractor shares how Claude Code handles complex industrial piping calculations and documentation, proving it's not just for software developers.
How to Vibe Code Safely: 3 Proven Techniques for Claude Code in Production
Implement a structured documentation pipeline and specific prompting techniques to minimize risk when using Claude Code for agentic, autonomous development.
Wikigen: Automate GitHub Wiki Generation with a Single CLI Command
Wikigen is a Go CLI that uses Claude Code to analyze your repo and generate comprehensive GitHub Wiki documentation automatically.
Cisco Launches DevNet MCP Server: Bring API Docs Directly to Your AI Coding Assistant
Cisco's new DevNet Content Search MCP Server integrates Cisco's API documentation directly into Claude Code and other MCP-compatible IDEs, providing context-aware code generation without browser switching.
Beyond Prompts: How Project Architecture Unlocks Claude Code's True Potential
AI developer Hasn T. reveals that Claude Code's effectiveness depends less on clever prompts and more on thoughtful project structure. The key insight: treat AI as a team member needing clear documentation and organized workflows.
The AGENTS.md File: How a Simple Text Document Supercharges AI Coding Assistants
Researchers discovered that adding a single AGENTS.md file to software projects makes AI coding agents complete tasks 28% faster while using fewer tokens. This simple documentation approach eliminates repetitive prompting and helps AI understand project structure instantly.
The Autonomous Company: How 14 AI Agents Are Running a Startup Without Human Intervention
Auto-Co introduces a fully autonomous AI company operating system where 14 specialized agents debate, decide, and ship software 24/7. Using Claude Code CLI and a simple bash loop, this open-source system has built its own infrastructure, documentation, and community presence across 12 self-improvement cycles.
Beyond Single Prompts: How 'Codified Context' Solves AI's Memory Problem in Large-Scale Development
A new research paper reveals why single-file AI agent instructions fail for complex projects and introduces a three-tier memory architecture that successfully managed a 108,000-line distributed system. The approach replaces simple prompts with structured, evolving documentation that becomes load-bearing infrastructure for AI development.
How Top Tech Engineers Are Using Claude Code's 'GSD' Method to Revolutionize Development Workflows
Engineers at Amazon, Google, and Shopify are adopting a method called 'GSD' (Get Shit Done) using Claude Code to dramatically accelerate development cycles. This approach transforms how teams approach coding tasks, debugging, and system documentation.
Only 20% of MCP Servers Are 'A-Grade' Secure — Here's How to Vet Them Before Installing
Most MCP servers lack documentation or contain security flags. Use specific tools and criteria to install only vetted, safe servers.
Anthropic Launches Self-Hosted Sandboxes and MCP Tunnels at London Event
Anthropic launched self-hosted sandboxes (public beta) and MCP tunnels (research preview) at Code with Claude London on March 4, 2026, per @bcherny.
Neo4j's agent-memory: Open-source unified memory for AI agents via knowledge graphs
Neo4j releases agent-memory, an open-source unified memory layer for AI agents using knowledge graphs, enabling persistent structured recall.
Google CodeWiki Turns Any GitHub Repo Into Interactive Docs
Google released CodeWiki, an open-source tool turning GitHub repos into interactive docs with Gemini chat. Free, URL-based, no setup required.
11-Agent Company Earned $0: CLAUDE.md Mistakes Cost Revenue
11-agent company experiment earned $0 after 896 tasks. Operator open-sourced CLAUDE.md template with 72 lessons on coordination failures and legal constraints.