# Agentic-Workflows

- [The Spec File as Source of Truth: How to Write Specs That AI Can Actually Implement](https://sdd.sh/2026/05/the-spec-file-as-source-of-truth-how-to-write-specs-that-ai-can-actually-implement.md): Writing specs instead of code is the core premise of SDD — but a bad spec produces bad code just as reliably as a bad prompt does. Here's what separates specs that AI can execute reliably from the ones that waste hours of compute and your afternoon.
- [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.
- [Claude Code at $2.5B ARR: How a Terminal Agent Outpaced Every AI IDE](https://sdd.sh/2026/05/claude-code-at-2.5b-arr-how-a-terminal-agent-outpaced-every-ai-ide.md): Claude Code hit $1B ARR in six months after launch — faster than Slack, Zoom, or any AI coding competitor. By February 2026 it had crossed $2.5B, accounting for more than half of all Anthropic enterprise spending. Here's what those numbers actually mean for the AI coding market.
- [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.
- [MiniMax M2.7: The Open-Source Agent That Rewrote Its Own Training Loop](https://sdd.sh/2026/04/minimax-m2.7-the-open-source-agent-that-rewrote-its-own-training-loop.md): MiniMax M2.7 is the first open-source model to participate in its own development cycle — 100 autonomous rounds of scaffold optimization, 30% performance gain, 56.22% on SWE-Pro. It's not just a strong model. It's a glimpse of what model self-improvement looks like in practice.
- [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.
- [Five Claude Code Features That Don't Make Headlines But Change Everything](https://sdd.sh/2026/04/five-claude-code-features-that-dont-make-headlines-but-change-everything.md): The benchmark releases get the press. The unglamorous power-user features don't. Here's what /ultrareview, auto mode for Max, xhigh effort, /recap, and the new prompt caching TTL controls actually change about your daily Claude Code workflow.
- [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.
- [Claude Opus 4.7 Is Your New API Default on April 23. Here's What Changes.](https://sdd.sh/2026/04/claude-opus-4.7-is-your-new-api-default-on-april-23.-heres-what-changes..md): On April 23, the 'opus' API alias switches to Opus 4.7. Same price, one-third the tool errors, best SWE-bench Pro score on the market. If your pipeline uses the bare alias, you're upgrading automatically. Here's what that actually means.
- [OpenAI Codex Goes Desktop Agent. It's Still Not Claude Code.](https://sdd.sh/2026/04/openai-codex-goes-desktop-agent.-its-still-not-claude-code..md): OpenAI's April 17 Codex update ships multi-agent desktop control, 90+ MCP plugins, and persistent memory. It's a real step forward in autonomy — built on exactly the wrong architecture.
- [Lucidworks MCP: $150K Per Integration Saved, and What It Says About MCP's Real Value](https://sdd.sh/2026/04/lucidworks-mcp-150k-per-integration-saved-and-what-it-says-about-mcps-real-value.md): Lucidworks launched an MCP server that connects AI assistants to enterprise search with claimed $150K savings per integration and 10x faster rollout. The numbers are impressive. The bigger story is what it reveals about MCP's role in enterprise AI architecture.
- [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.
- [The Three-Layer AI Coding Stack That Nobody Planned (But Everyone Is Building)](https://sdd.sh/2026/04/the-three-layer-ai-coding-stack-that-nobody-planned-but-everyone-is-building.md): Cursor, Claude Code, and OpenAI Codex are not converging into a single winner-take-all tool. They are stratifying into three distinct layers — orchestration, execution, and review — and the most sophisticated developers are building workflows that use all three. Here is what each layer does, why Claude Code wins at the execution layer, and what the emergence of OpenAI's Codex plugin for Claude Code signals about where this is heading.
- [84% of Developers Use AI Code Tools. Only 29% Trust What They Ship.](https://sdd.sh/2026/04/84-of-developers-use-ai-code-tools.-only-29-trust-what-they-ship..md): Stack Overflow's developer survey exposed a paradox: AI coding tool adoption is at an all-time high, but trust in AI-generated code just hit an all-time low. The gap isn't irrational — it's diagnostic. And it points directly to what's broken about the autocomplete paradigm.
- [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.
- [SDD Is Eating Software Engineering: The Methodology That Went From Blog Post to Industry Movement](https://sdd.sh/2026/04/sdd-is-eating-software-engineering-the-methodology-that-went-from-blog-post-to-industry-movement.md): Spec-Driven Development has crossed from niche methodology to recognized category — with 30+ competing frameworks, a conference track at Agentic Conf Hamburg, AWS Kiro as the first commercial SDD IDE, and enterprise backing from McKinsey and Anthropic's own trend reports. Here's what's happening and what it means.
- [The CLAUDE.md Trap: How a New Supply-Chain Attack Targets Agentic Developers](https://sdd.sh/2026/04/the-claude.md-trap-how-a-new-supply-chain-attack-targets-agentic-developers.md): A patched vulnerability in Claude Code (CVE-2026-21852) reveals an entirely new attack surface: poisoned project config files that silently bypass your deny rules and exfiltrate credentials. Here's what happened, how the exploit works, and what it means for agentic security.
- [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.
- [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.
- [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.
- [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.