AI automation ideas that save real time (and the ones that don't)
Most automation effort goes into impressive-looking projects that save twenty minutes a month. Here's where the actual hours are.
Read →Workflow and agent systems in Make.com and n8n. Building automations that survive contact with real data instead of breaking the first time something unexpected arrives.
7 posts on Automation.
Most automation effort goes into impressive-looking projects that save twenty minutes a month. Here's where the actual hours are.
Read →The word 'agent' is doing a lot of marketing work. Here's the useful definition, and how to build something that actually holds up.
Read →Tokens, context windows and why your bill isn't what you expected. How to model cost before committing to a build.
Read →I use both. Here's the honest comparison, including where each one gets painful, and which I'd choose for a given job.
Read →Webhooks are behind most useful marketing automation. Here's what they are, in plain terms, and the three things that go wrong.
Read →A week of 401s, silent failures and one genuinely embarrassing naming collision. What actually went wrong building the audit tool, in order.
Read →Eight modules, one webhook, and a Claude API call. A walkthrough of the automation behind the free audit tool, including what it costs to run.
Read →