Workflow

The most thorough walkthrough yet of Opus 4.7's Adaptive Thinking, the new effort levels, and the 1M-context workflow changes. Covers when to reach for which effort level, how Adaptive Thinking actually allocates compute, and ten concrete workflows that are newly viable. The kind of practitioner read you come back to twice while rewiring your agents.

Anthropic's own recommended patterns for pairing Opus 4.7 with Claude Code — effort levels, plan-mode prompts, and when to switch to Sonnet for a subtask. Worth the read even if you've been running Claude Code since day one.

The Honeycomb team shares their second round of hard-won patterns for running MCP and canvas-based agent workflows in real observability work. Rare glimpse of the integration grief no vendor doc admits to.

A close reading of the six Opus 4.7 tips circulating from inside the Claude Code team, with a view on when the new Cowork mode is actually the better default. Short and opinionated.

A solo developer's honest sketch of how to actually learn and ship AI in 2026 — the rare roadmap that admits which pieces are still in flux. Worth it for the "what I would skip" list.

Swyx's take on what "slop" actually means for AI engineering — and why the next year of agent work will be decided by who can scale quality-control without drowning in noise. The kind of piece that quietly becomes a reference in team Slacks.

Microsoft shipped in-app agents for Copilot that plug directly into SAP, ServiceNow, Salesforce, and Workday. Users can trigger multi-system workflows from inside Teams or Outlook without switching contexts, the clearest signal yet of Microsoft's "agents wherever work happens" strategy.

A detailed practitioner argument for designing "harnesses"—structured planning environments that make coding agents think before they type. Covers symbol analysis, repository-impact mapping, and scoped permissions with concrete patterns. One of the clearest articulations of how teams are adapting their tooling to agentic workflows.

Simon Willison's practitioner-grade survey of where we are: why November 2025 was the real agentic-coding inflection, the three patterns he uses daily, and what the "dark factories" of automated content mean for product builders. Honest, specific, and useful.

A solo game developer's field notes on building a profitable studio with heavy AI leverage—what delegated well, what broke, and the operating rhythms that held up. The kind of pragmatic ground-truth you rarely find in company case studies.

End-to-end walkthrough for building an autonomous AI agent from scratch in 2026. Covers the four essential components—LLM, memory, tools, and runtime—with code examples and deployment patterns.

Hermes v1.0 released April 3 with four-stage learning: execute task, evaluate outcomes, abstract into reusable skills, refine during use. Transforms agent behavior from one-off to continuously improving.

Agentic AI is emerging as the biggest trend of 2026, with enterprises moving from pilots to full deployments. AI agents now handle code, legal, finance, and admin tasks autonomously.

Individual perspective on how AI is redefining the software engineering discipline. No longer about building features—it's about orchestrating autonomous systems and managing emergent behavior.

The Dropbox engineering team walks through how they used the DSPy framework to systematically optimize prompt-based relevance judgments for Dash at production scale. Covers the full loop from metric definition through prompt compilation, with real before-and- after numbers. The clearest DSPy-in-production case study to date.