# Agentic Workflows

- [Agentic Coding 101: When Your AI Plans, Builds, Tests, and Ships](https://sdd.sh/2026/05/agentic-coding-101-when-your-ai-plans-builds-tests-and-ships.md): Most engineers still think of AI coding as an advanced autocomplete. They're missing the paradigm shift. Agentic coding is fundamentally different — the AI plans the work, writes the code, runs the tests, fixes the failures, and iterates until the task is done.
- [Microsoft Agent 365 Is Live: The Enterprise Control Plane That Governs Agents You're Already Running](https://sdd.sh/2026/05/microsoft-agent-365-is-live-the-enterprise-control-plane-that-governs-agents-youre-already-running.md): Microsoft Agent 365 reached general availability on May 1, 2026, bundled into the new M365 E7 Frontier Suite at $99/user. It is not a coding agent or a development tool. It is governance infrastructure — a control plane for discovering, governing, and securing every AI agent in your organization. Here is what it actually does, what it cannot govern, and why it matters.
- [Cursor SDK: The IDE Escapes the IDE — But Does It Break the Ceiling?](https://sdd.sh/2026/04/cursor-sdk-the-ide-escapes-the-ide-but-does-it-break-the-ceiling.md): Cursor launched a TypeScript SDK in public beta on April 29 that lets developers invoke Cursor agents programmatically from CI/CD pipelines, backend services, or other products — with sandboxed cloud VMs, subagents, and durable agent lifecycle. It's Cursor's most significant architectural shift since Composer. The question is whether it actually solves the autonomy problem, or just relocates it.
- [Claude Code in 2026: The Complete Deep Dive](https://sdd.sh/2026/04/claude-code-in-2026-the-complete-deep-dive.md): Claude Code isn't a coding assistant. It's a terminal-native autonomous agent that plans, implements, tests, and iterates on software with minimal supervision. This is the definitive 2026 guide to what it is, how it works, and how to get the most from it.
- [Google's 75% Threshold: When AI Became the Primary Author of Production Code](https://sdd.sh/2026/04/googles-75-threshold-when-ai-became-the-primary-author-of-production-code.md): Sundar Pichai revealed at Google Cloud Next 2026 that 75% of new code at Google is now AI-generated and reviewed by engineers. That number crossed a threshold most didn't expect this fast — and it reframes every assumption about what software teams look like in 2026.
- [Claude Design Is Not a Figma Clone. It's the Missing First Half of Your Agentic Stack.](https://sdd.sh/2026/04/claude-design-is-not-a-figma-clone.-its-the-missing-first-half-of-your-agentic-stack..md): Anthropic's Claude Design launched April 17 as a research preview. It's not a Figma alternative — it's the upstream half of the Claude Code shipping pipeline, and the handoff mechanism changes the conversation entirely.
- [Salesforce Headless 360: The World's Largest CRM Just Became an MCP Server](https://sdd.sh/2026/04/salesforce-headless-360-the-worlds-largest-crm-just-became-an-mcp-server.md): At TDX 2026, Salesforce shipped 60+ MCP tools and 30+ coding skills under the 'Headless 360' banner, making every corner of its platform natively callable from Claude Code, Cursor, Codex, and Windsurf. When the world's largest CRM goes headless for AI, the enterprise software landscape just shifted.
- [OpenAI's Agents SDK Gets Sandboxed Execution and a Model-Native Harness: The Agent Infrastructure Layer Is Now Table Stakes](https://sdd.sh/2026/04/openais-agents-sdk-gets-sandboxed-execution-and-a-model-native-harness-the-agent-infrastructure-layer-is-now-table-stakes.md): OpenAI's April 15 Agents SDK update ships sandboxed execution, a model-native harness with configurable memory, provider-agnostic model support, and durable state via snapshotting. The primitives Claude Code has offered since day one are becoming the standard SDK layer. Here's what that means.
- [The Orchestrator Seat: Claude Code's Desktop Redesign Makes Parallel Agents Native](https://sdd.sh/2026/04/the-orchestrator-seat-claude-codes-desktop-redesign-makes-parallel-agents-native.md): Anthropic's April 14 Claude Code desktop redesign isn't a UI polish — it's a rethinking of how developers manage multiple AI agents simultaneously. Multi-session sidebar, git worktree isolation, side chats, and an integrated toolkit mean you can orchestrate five agents without leaving the app.
- [Claude Code Routines: The AI Cron Job That Actually Understands Your Codebase](https://sdd.sh/2026/04/claude-code-routines-the-ai-cron-job-that-actually-understands-your-codebase.md): Claude Code's new Routines feature — launched April 14 as a research preview — turns your AI agent into a cloud-native automation engine. Schedule it, trigger it via API, or fire it on GitHub events. Here is what routines are, how each trigger type works, and why this is a bigger architectural shift than it looks.
- [Microsoft Agent Framework 1.0: The Enterprise .NET World Just Adopted MCP](https://sdd.sh/2026/04/microsoft-agent-framework-1.0-the-enterprise-.net-world-just-adopted-mcp.md): Microsoft shipped Agent Framework 1.0 on April 3 with full MCP and A2A protocol support for .NET and Python. This isn't just another framework — it's Microsoft committing the entire enterprise .NET developer ecosystem to MCP as the standard tool integration layer.
- [Claude Code Ultraplan: When 30 Minutes of Cloud Thinking Beats 5 Seconds of Local Guessing](https://sdd.sh/2026/04/claude-code-ultraplan-when-30-minutes-of-cloud-thinking-beats-5-seconds-of-local-guessing.md): Ultraplan hands your planning task to a dedicated cloud session running Opus 4.6 for up to 30 minutes — while your terminal stays free. Here's what it actually is, how the three modes differ, and when to reach for it.
- [Claude Managed Agents: Anthropic Just Built the Agent Loop You Were Going to Write Anyway](https://sdd.sh/2026/04/claude-managed-agents-anthropic-just-built-the-agent-loop-you-were-going-to-write-anyway.md): Anthropic launched Claude Managed Agents on April 8 — a managed API that handles the agent loop, sandboxing, checkpointing, and tool orchestration you'd otherwise build yourself. Here's what it actually offers, how the pricing model works, and why it matters for teams shipping production agents.
- [Cursor 3: Agent-First Branding, IDE-Last Architecture](https://sdd.sh/2026/04/cursor-3-agent-first-branding-ide-last-architecture.md): Cursor 3 shipped a genuinely redesigned interface built around parallel agents. The Agents Window, Design Mode, /worktree, and /best-of-n are real features with real uses. But 'agent-first' describes the UI layer, not the architecture — and the distinction matters more than Cursor's marketing suggests.
- [GitHub Copilot Finally Got Autopilot Mode. It's Still Not an Agent.](https://sdd.sh/2026/04/github-copilot-finally-got-autopilot-mode.-its-still-not-an-agent..md): GitHub Copilot's April 8 VS Code update ships Autopilot Mode, nested subagents, and MCP sandboxing. These are real improvements. They're also a demonstration of why bolting autonomy onto an IDE produces something fundamentally different from a real agent.
- [Claude's 1M Context Window Is Now Standard: What Actually Changes for Agentic Coding](https://sdd.sh/2026/04/claudes-1m-context-window-is-now-standard-what-actually-changes-for-agentic-coding.md): On March 13, Anthropic made the 1M token context window standard on Sonnet 4.6 and Opus 4.6 — no beta header, no pricing premium above 200K. Here is what that actually changes for coding agents, how it compares to the competition, and what it still cannot solve.
- [Gemma 4: Google Just Made the Case for Running Your Coding Agent Locally](https://sdd.sh/2026/04/gemma-4-google-just-made-the-case-for-running-your-coding-agent-locally.md): Google's Gemma 4 dropped on April 2 with Apache 2.0 licensing, 80% on LiveCodeBench v6, a Codeforces ELO of 2,150, and agentic tool-use scores that make the previous generation look like a prototype. The 26B MoE model runs on a single consumer GPU with 256K context. Here's what it actually means.
- [Pinterest's MCP Blueprint: 66,000 Invocations a Month, 7,000 Hours Saved — This Is What Production MCP Looks Like](https://sdd.sh/2026/04/pinterests-mcp-blueprint-66000-invocations-a-month-7000-hours-saved-this-is-what-production-mcp-looks-like.md): MCP hit 97 million downloads. Pinterest just showed what you do with them. Their production MCP ecosystem — domain-specific servers, a central registry, two-layer JWT auth, and hard ROI numbers — is the blueprint every serious engineering team will follow.
- [What Anthropic's Accidental 512K-Line Leak Reveals About Claude Code's Future](https://sdd.sh/2026/04/what-anthropics-accidental-512k-line-leak-reveals-about-claude-codes-future.md): Anthropic accidentally published Claude Code's full TypeScript source to npm. Fifty thousand downloads later, we know about KAIROS — a proactive always-on daemon — plus ULTRAPLAN, undercover mode, anti-distillation traps, and a virtual pet. This isn't a scandal. It's an accidental roadmap.
- [Claude Code Computer Use: The Agent That Can Now See, Click, and Ship](https://sdd.sh/2026/04/claude-code-computer-use-the-agent-that-can-now-see-click-and-ship.md): Anthropic's March 23 Computer Use launch for Claude Code is the closest thing yet to a fully autonomous coding agent. It can open your files, run your app, spot the bug, and fix it — without you touching a keyboard.
- [MCP Crosses 97 Million Downloads: The Protocol That Won](https://sdd.sh/2026/03/mcp-crosses-97-million-downloads-the-protocol-that-won.md): Sixteen months after Anthropic published a draft spec, MCP has crossed 97 million monthly SDK downloads — and OpenAI's adoption paired with retiring the Assistants API has effectively handed MCP the crown. Here's what that means for agentic development.
- [Jules Deep Dive: Google's Async Agent That Closes the CI Loop Without You](https://sdd.sh/2026/03/jules-deep-dive-googles-async-agent-that-closes-the-ci-loop-without-you.md): Jules is now generally available with Gemini 3.1 Pro at its core, an autonomous CI failure detection and fix loop, and audio changelogs. This is what a fully async coding agent actually looks like — and how it compares to the terminal-native model Claude Code represents.
- [Claude Code Agent Teams: One Developer, Fifteen AI Teammates](https://sdd.sh/2026/03/claude-code-agent-teams-one-developer-fifteen-ai-teammates.md): Claude Code's experimental Agent Teams feature lets a single session orchestrate up to 15 independent AI teammates, each with its own context window and toolset. Here's what the architecture looks like — and why a Rust C compiler built by 16 agents is a stress test worth understanding.
- [From Vibe Coding to Agentic Engineering: The Paradigm Shift That Outran Its Own Branding](https://sdd.sh/2026/03/from-vibe-coding-to-agentic-engineering-the-paradigm-shift-that-outran-its-own-branding.md): Andrej Karpathy coined 'vibe coding' on February 2, 2025. Collins Dictionary named it Word of the Year. Then Karpathy declared it passé and replaced it with 'agentic engineering.' Here's what happened in the 13 months between the tweet and the paradigm shift.
- [Anthropic's 8 Agentic Coding Trends: A Manifesto, Not Just a Report](https://sdd.sh/2026/03/anthropics-8-agentic-coding-trends-a-manifesto-not-just-a-report.md): Anthropic just published the most data-rich statement on where agentic coding is headed. Here's what the eight trends actually mean — and what it tells you about the next two years of software development.
- [Windsurf Arena Mode: Let the Models Fight It Out](https://sdd.sh/2026/03/windsurf-arena-mode-let-the-models-fight-it-out.md): Windsurf Arena Mode runs two AI agents on the same task in parallel isolated worktrees, then asks you to pick the winner. It's a clever answer to a real problem — but it also reveals something telling about where IDE-centric AI is stuck.
- [Claude Code AutoDream: Your AI Agent Finally Sleeps on It](https://sdd.sh/2026/03/claude-code-autodream-your-ai-agent-finally-sleeps-on-it.md): Anthropic quietly shipped AutoDream — a background memory consolidation system for Claude Code that runs between sessions, prunes stale notes, and fixes conflicting data. Think REM sleep for your coding agent.
- [Cursor Composer 2: The Model That Learns to Forget — and Sparked a Controversy](https://sdd.sh/2026/03/cursor-composer-2-the-model-that-learns-to-forget-and-sparked-a-controversy.md): Cursor's new coding model beats Claude Opus 4.6 on key benchmarks — but the real story is a training breakthrough called compaction-in-the-loop RL, and a transparency controversy that revealed Cursor quietly built it on a Chinese open-source model.
- [Cursor Automations: Your IDE Just Became an Always-On Agent](https://sdd.sh/2026/03/cursor-automations-your-ide-just-became-an-always-on-agent.md): Cursor Automations turns your IDE into a reactive system that writes code, triages bugs, and responds to incidents while you sleep. Here's what it can do — and what it can't yet.
- [Claude Code Auto Mode: Anthropic Hands AI More Control (But Keeps It on a Leash)](https://sdd.sh/2026/03/claude-code-auto-mode-anthropic-hands-ai-more-control-but-keeps-it-on-a-leash.md): Auto Mode lets Claude decide which actions are safe to take without asking permission — but adds an AI safety layer that screens every action for prompt injection and risky behavior. Here's what changed and why it matters.
- [Claude Code Channels: Your AI Agent, Now on Telegram and Discord](https://sdd.sh/2026/03/claude-code-channels-your-ai-agent-now-on-telegram-and-discord.md): Anthropic shipped Claude Code Channels on March 20, letting you message Claude Code directly from Telegram or Discord. The real story isn't convenience — it's the shift from synchronous IDE sessions to asynchronous agent partnerships, and what that means for how you work.
- [Xcode 26.3: Apple Goes All-In on Agentic Coding](https://sdd.sh/2026/03/xcode-26.3-apple-goes-all-in-on-agentic-coding.md): Apple's mid-cycle Xcode 26.3 release isn't a minor patch — it's a bet-the-ecosystem move that bakes Claude Agent and OpenAI Codex directly into the IDE. Here's what changed, what it means for iOS and Mac developers, and why MCP is the most important detail in the release notes.
- [MCP's 2026 Roadmap: From Prototype Protocol to Production Standard](https://sdd.sh/2026/03/mcps-2026-roadmap-from-prototype-protocol-to-production-standard.md): The MCP 2026 roadmap published by lead maintainer David Soria Parra reveals a protocol growing up fast — shifting from milestone releases to working groups, tackling stateless transport, enterprise auth, and governance maturity. Here's what's actually changing and why it matters for developers building on MCP today.