Blog
AXO is bigger than your website
Agent experience optimisation already has a definition, and it's a good one. It just stops at the edge of your site — where the agent's actual job begins.
Everyone says you can't measure task completion. You can.
The best model on the biggest MCP benchmark finishes 79% of tasks. Most finish half that. The number that explains the gap is the one the tooling has quietly agreed to stop measuring.
Your agents aren't erroring. They're picking the wrong tool.
On a small, well-documented tool catalogue, models correctly declined out-of-scope work 100% of the time. On a large fuzzy one, 50%. The other half didn't fail — they confidently called something plausible.
Soon, AI assistants will sign up your customers for you
Today the Claude and ChatGPT marketplaces only reach people who already have an account. That wall is coming down — and when it does, these channels flip from retention to acquisition.
The MCP marketplace is the new App Store, and the ranking game has already started
Rank on the Claude and ChatGPT marketplaces is driven by usage, reviews don't exist yet, and the early window is open right now. The Google Play console playbook, replayed for the new shelf.