We build AI products and write about what works, what doesn't, and what we'd do differently. Real lessons from real projects.
Our Writing
A growing share of your visitors are AI agents, not people. On our own site we log around 4,000 AI-crawler requests a day. Here's what agentic readiness means for SaaS, which levers are real versus hype, and how to check where you stand.
Jozef
Pixelhooks records every HTTP request sent to a throwaway URL and lets you program exactly what it sends back - a see-both-sides scratch endpoint for building against webhooks and agents, with an MCP server so your assistant can drive it.
Chris
Agentic search pairs a conversational AI assistant with a live, interactive canvas, so customers describe what they want instead of wrestling with filters. A repeatable AI-native search pattern, shown across three niches.
Jozef
Our first real-world test of Anthropic's Fable 5: running inside Claude Code, it autonomously rebuilt a messy, already-deployed prototype onto our production stack in a single afternoon. Hugely impressive and near-faultless, but slow and notionally pricey, which raises a real question once API pricing lands.
Jozef
We loved Notion, until the agent era made it feel too slow, closed, and awkward to work with. Treehouse is our attempt to keep the polish of Notion, combine it with the freedom of Dropbox, and make a workspace that humans and AI agents can share properly.
Jozef
I do SEO work for a few clients, and the monthly report is the thing they actually pay for. For ages I was hand assembling it.. which is fine once, miserable every month. This post is about how that turned into a little pipeline of Claude skills and scripts, and how each piece quietly made the next one easier to build. People call this compound engineering and honestly the name fits.
ChrisLike what you’re reading? Sign up to receive our updates straight to your inbox. No spam, unsubscribe anytime!