AI agents
Working with AI coding agents that run real commands: context, permissions, review, safety rails, and where they should run.
117 posts · page 1 of 5
What Is Windsurf? The AI Code Editor, Now Called Devin Desktop
Windsurf was an AI-first code editor built on VS Code, known for its Cascade agent and Tab completions. Cognition bought it in 2025 and renamed it Devin Desktop in June 2026. What it is, what changed, how it compares with Cursor and Claude Code, and what existing users should know.
What Is n8n? Workflow Automation (and AI Agents) Explained Simply
n8n is a workflow automation tool: you connect apps and APIs with visual nodes so that something happening in one place triggers actions in others. What n8n is used for, how workflows and nodes work, its AI agent features, the fair-code licence, and cloud vs self-hosted.
What Is Google Antigravity? Google's Agent-First Coding Tool Explained
Google Antigravity is an agent-first development platform: a desktop IDE, a CLI and an SDK built around Gemini models, where you dispatch AI agents to plan, code and test while you review their work. What it does, how it differs from a normal editor, whether it's free, and who it suits.
What Is Claude Cowork? Claude Code for the Rest of Your Work
Claude Cowork is Anthropic's agent for non-coding work: you describe an outcome and Claude plans and carries out the steps — organising files, building spreadsheets and decks, researching, filling in web forms. What it is, how it runs, what it costs, and how to use it safely.
What Is Agentic AI? A Plain-English Explanation (With Examples)
Agentic AI means AI systems that pursue a goal by taking actions — using tools, checking results and deciding what to do next — instead of only producing text. What makes AI "agentic", how it differs from generative AI and chatbots, real examples, and the risks to watch.
Replit Can Now Be Driven From Desktop MCP Clients, and Agent Gets Custom API Connectors
In September 2026 Replit made its platform usable from any compatible desktop MCP client — create, find, inspect, update and publish apps from your AI tool of choice (11 September) — and launched custom API connectors in beta for Pro and Enterprise teams (18 September). Plus newer models in Agent. What it enables and what to watch.
OpenAI DevDay 2026: Codex Gets Persistent Cloud Environments, Voice and Security Scanning
At DevDay on 29 September 2026, OpenAI expanded Codex with reusable, persistent cloud environments reachable from any device, a refreshed CLI with voice control and an /agents view, a new code review experience, and Codex Security Cloud for scanning repositories. What was announced and what it signals about where coding agents run.
MCP Transports: stdio vs Streamable HTTP (and What the 2026 Spec Changed)
MCP servers talk to clients over stdio (a local subprocess) or Streamable HTTP (a remote endpoint). How each works, when to choose which, how to add both to Claude Code, why the old HTTP+SSE transport is deprecated, and what the stateless 2026-07-28 specification means for building and hosting HTTP servers.
MCP's 2026-07-28 Specification: A Stateless Protocol and What Breaks
The Model Context Protocol released its 2026-07-28 specification, the first since November 2025. The core becomes stateless request/response — no initialize handshake, no Mcp-Session-Id — with routing headers, multi round-trip requests, cacheable lists, auth hardening and deprecated Roots, Sampling, Logging and HTTP+SSE. What changes for server builders and users.
Gemini API: New Antigravity Agent Version, Gemini 3.8 Flash GA and Model Deprecations
Google's Gemini API replaced antigravity-preview-05-2026 with antigravity-preview-09-2026 on 17 September (the old version shut down on 5 October), made Gemini 3.8 Flash generally available on 2 September, limited Gemini 2.5 access to recent users, and deprecated gemini-3.1-flash-image. What developers need to change.
Docker Launches Cloud Sandboxes for AI Agents — and Open Kits on OCI
On 24 September 2026 Docker launched Cloud Sandboxes, extending its local agent sandboxes to Docker-managed cloud infrastructure with the same microVM isolation, policies and CLI, boot times in the low hundreds of milliseconds and 1–16 vCPUs. It also published next-generation Kits, an OCI-based spec for packaging an agent, its tools and its access rules.
Cursor vs Windsurf (Devin Desktop): Which AI Editor in 2026?
Cursor and Windsurf (renamed Devin Desktop in 2026) are both AI code editors built on VS Code. How they compare on agents, completions, models, cloud and parallel work, pricing approach and who owns them — and a simple way to choose.
Cursor: Remote Control for Local Agents, Plus Rollouts and Security Review Bots
Cursor's iOS app can now show and reply to agents running on your own computer (6 October 2026), without cloud agents. Earlier, on 23 September, Cursor launched Rollouts, which monitors a pull request from merge to production and flags regressions, and Security Review, which posts exploitable-bug findings on each PR, for Teams and Enterprise.
Cursor Adds Projects (Multi-Agent, Beta) and Self-Hosted Machines
In September 2026 Cursor launched self-hosted machines (2 Sept), which keep agent tool execution on your own laptops, VMs or sandboxes, and Projects (10 Sept, beta), where a coordinator agent plans long-running work and delegates it to parallel agents that can react to Slack, schedules and pull requests.
Cloudflare's Registrar API Lets Agents Search, Buy and Transfer Domains
During Birthday Week 2026 Cloudflare expanded its Registrar API (beta since April) with a test sandbox, transfers from other registrars and an endpoint describing 420+ extensions, made it available through Cloudflare MCP and the cf CLI, and rebuilt domain search. What it enables, at-cost pricing, and why agents should never buy domains without your approval.
Cloudflare Birthday Week 2026: The Announcements That Matter for App Builders
Cloudflare's 16th Birthday Week (28 September–2 October 2026) brought 46 announcements. The ones relevant to developers and small teams: the cf CLI, agent-ready Registrar APIs, Protected Quick Tunnels, plans for a free public CA with post-quantum Merkle Tree Certificates, AI Gateway's Auto Router and Web Search API, Basin and AI Search GA, and rebuilt Containers.
Claude Desktop App: AGENTS.md in Code, Wider Cowork Folder Access, and macOS 13 Required
The Claude desktop app's September and early October 2026 releases added AGENTS.md support in the Code tab, Opus 5.5 and Sonnet 5.5, attaching your home folder or whole drives to Cowork, built-in browser controls, file comments and Office previews in Code, Google Docs creation from Chat — and moved to Electron 44, which requires macOS 13 or later.
Claude Code vs Cowork: Which Claude Agent Should You Use?
Claude Code and Claude Cowork are both Anthropic agents that do the work instead of just answering. Claude Code is built for software; Cowork is built for files, documents, spreadsheets and the web. How they differ on what they touch, where they run, safety and usage — and how to pick.
Claude Code Routines: Scheduled, API and GitHub-Triggered Agents in the Cloud
Routines are saved Claude Code tasks — a prompt, repositories and connectors — that run on Anthropic's cloud or an organization's self-hosted environment. How to create one with /schedule or the web, use schedule, API and GitHub triggers, and manage limits and security.
Claude Code /goal: Keep Claude Working Until the Job Is Actually Done
/goal sets a completion condition and Claude keeps taking turns until a separate model confirms it's met — no prompting each step. How to write conditions the evaluator can verify, how evaluation and check-ins work, combining it with auto mode, running it headless, and when to use /loop or a Stop hook instead.
Claude Code Background Sessions and Agent View: Run Many Agents at Once
Agent view (claude agents) lets you dispatch Claude Code sessions that keep running in the background, peek at them, answer their questions and attach when needed. How to start background sessions with --bg and /bg, the attach/logs/stop commands, background shell jobs, worktrees, and the limits on usage and idle sessions.
Claude API: Files, Agent Skills and Computer Use Leave Beta, and a New Browser Use Tool
On 19 August 2026 Anthropic took the Files API, Agent Skills and the computer use toolset out of beta, and launched a browser use tool that drives a browser your app hosts. What no longer needs a beta header, what changed in responses, and what the browser tool adds over screenshot-and-click.
How to Write a Product Requirements Document (PRD) — With AI's Help
A PRD says what you're building, for whom, and how you'll know it works — before anyone writes code. What goes in a good one, a short template, how to use AI to draft and pressure-test it, and why a clear PRD is the best input you can give an AI coding tool.
Why Does AI Hallucinate? And How to Reduce It in Your App
AI models sometimes state false things with complete confidence. Why it happens — they predict plausible text rather than look up facts — the kinds of hallucination you'll meet in coding and apps, and practical ways to reduce it: grounding, tools, structure, checks and room to say 'I don't know'.