Categories
Every post belongs to at most one category. Pick a lane, or browse the full archive instead.
14 categories · 316 posts
Agent Basics
Core concepts, the agent loop, foundations for newcomers.
24 posts
Big Picture
Adoption strategy, trends, team impact, opinion.
61 posts
Design & Patterns
Planning, reflection, task decomposition, which pattern fits.
29 posts
Engineering
Building things, and what broke along the way.
2 posts
Memes
Memes and lighter takes on agents, AI, and the business of building software.
No posts yet
Memory & Context
23 posts
Notes
Shorter thoughts and working notes.
No posts yet
Real-World Agents
Case studies: coding, support, research, ops.
26 posts
Running in Production
Deployment, cost, latency, monitoring, scaling.
24 posts
Safety & Guardrails
Prompt injection, permissions, sandboxing, human checkpoints.
24 posts
Testing & Reliability
Evals, debugging, tracing, why agents fail.
30 posts
Tools & Connections
Function calling, MCP, APIs, browser and computer use.
24 posts
Tools of the Trade
Frameworks, SDKs, platforms, build-vs-buy.
26 posts
Working Together
Multi-agent setups, handoffs, delegation, supervisor patterns.
23 posts
Popular tags
#ai-agents 303#intermediate 222#reliability 124#agent-design 112#deep-dive 107#evaluation 98#tutorial 92#tool-use 76#adoption 72#strategy 69#human-in-the-loop 64#future-of-work 57#coding-agents 49#failure-analysis 49#advanced 48#comparison 48#testing 43#beginner 42#token-cost 42#monitoring 41#observability 40#deployment 39#guardrails 39#automation 36#context-window 36#orchestration 35#debugging 34#multi-agent 28#permissions 28#agentic-ai 27#memory 27#security 27#frameworks 26#latency 25#function-calling 22#devops 20#llm 20#case-study 17#rag 16#handoffs 14