AI agents.
An agent that works in a demo and an agent that still runs six months later have almost nothing in common. Here I write about what separates them: architecture, guardrails, memory and the boring half nobody posts about.
- /31 oct 2026
AI Agent Security: Limit What the Agent Can Do, Not What It Reads
AI agent security in plain terms: why prompt injection can't be filtered away, how to scope access, which actions need approval and what to log.
- /29 oct 2026
Agentic Workflows: 5 Patterns and How to Pick the Right One
Agentic workflows put an AI model inside a set of steps you define. The five patterns, when each one fits, and how to design your first one safely.
- /24 oct 2026
AI Agent Templates: The One-Page Spec I Fill In Before Any Build
AI agent templates that work on any platform: a one-page spec covering the job, inputs, tools, rules, checkpoints and fallbacks, plus where to find builds.
- /22 oct 2026
AI Lead Qualification: Score Inbound Leads in Minutes, Not Days
How AI lead qualification works for inbound leads: the scoring rubric, routing rules, where a person stays involved and how to test it before going live.
- /20 oct 2026
n8n Templates: How to Pick One and Make It Production-Ready
How to find a good n8n template, import it safely, swap in your own credentials and logic, and turn a demo workflow into one you can trust every day.
- /19 oct 2026
AI SDR: What It Can Do, What It Can't, and How to Start
What an AI SDR really does, which sales development tasks to hand it first, where it hurts your pipeline, and a step-by-step way to set one up safely.
- /17 oct 2026
AI Agent Observability: What to Trace, Measure and Review
AI agent observability in plain terms: what to record per run, the five numbers worth watching, how to review quality, and which tools to start with.
- /16 oct 2026
AI Agent for Customer Service: What It Should and Shouldn't Do
How to set up an AI agent for customer service that drafts, routes and answers the easy questions, while a person keeps refunds, complaints and promises.
- /12 oct 2026
How to Build an AI Agent: 7 Steps From Process to Production
How to build an AI agent that does real work: pick one process, write it down, choose a stack, add tools and checks, then run it in shadow mode first.
- /9 oct 2026
AI Agent Examples: 10 That Hold Up in a Real Business
Ten concrete AI agent examples for sales, inbox, data and voice, with the trigger, tools and human checkpoint each one needs to work every day.
- /31 may 2026
Why AI agents break in production: 5 patterns and their fixes
The model is rarely why an AI agent gets switched off. Poor design for failure is. Five patterns I keep seeing, each with its fix and what that fix costs.
The build log · newsletter
Steal my automations.
One agent I built, the workflow behind it and the tools that made it work. Copy, paste, ship.
10,000+ builders already subscribed. Free.