Articles / Foundations
Topic
How AI agents actually work. Frameworks, orchestration, workflows, guardrails, observability — the concepts you need before picking a platform.
10 articles
May 17, 2026 · 6 min read
A short mental model for deciding which tasks belong with an AI agent and which don't. Three letters. Autonomous, Recurring, Reviewable. Skip the rest.
Read →
May 17, 2026 · 8 min read
Stop prompting. Start directing. The mindset change builders need to make once they move from chatbots to agents — and the practices that come with it.
Read →
May 17, 2026 · 8 min read
Three capabilities safe alone, catastrophic combined: private data, internet access, untrusted input. How the AI agent security trap works and how to break it.
Read →
Mar 25, 2026 · 5 min read
Brain-and-muscle model routing: use expensive models for planning, cheap models for execution. Real cost breakdowns and the routing logic that makes it work.
Read →
Mar 20, 2026 · 13 min read
Best AI agent observability tools and what to instrument. LangSmith, Paperclip, OpenTelemetry, Datadog — the four metrics every production agent needs.
Read →
Mar 17, 2026 · 13 min read
Seven AI agent guardrails every production deployment needs — approval gates, action boundaries, budget caps, blast radius. Why 9 seconds ended Pocket OS.
Read →
Mar 12, 2026 · 13 min read
Best AI agent orchestration platforms compared — Paperclip, LangGraph, CrewAI, n8n. When to use which, and what makes multi-agent systems reliable.
Read →
Mar 9, 2026 · 10 min read
Six proven AI agent workflow patterns — with real examples, cost shapes, and failure modes. Skip the theory. Build the one that fits your use case.
Read →
Mar 4, 2026 · 10 min read
The best AI agent frameworks compared — LangGraph, CrewAI, AutoGen, Semantic Kernel. Which fits which workflow, and when to skip them entirely.
Read →
Mar 2, 2026 · 10 min read
Skills files, context management, and routines turn a one-trick agent into a system that improves. The architecture behind agents that compound over time.
Read →
Other topics
Use Cases
Where agents are doing real work. Email, support, finance, small-business operations — by job-to-be-done, not by tool.
Comparisons
Head-to-head reviews and editorial picks. When two tools answer the same question, here's how to choose.
Cost & Pricing
What agents actually cost in production, and where the savings really are.
Strategy
Broader market analysis and contrarian takes on where the AI agent space is going.
Claude Skills
Deep coverage of Claude's agentic capabilities — what Skills are, how they relate to MCP, and how to build them.