-
Claude for Small Business: We're Already That Business
Anthropic launched a Claude bundle for small businesses; ChatFlow and AgentSpace already built the same approval principle via WhatsApp and an agent team.
5 min Models and cost Read -
Claude Opus 5.5 Got Cheaper: The AgentSpace Bill
Anthropic cut Claude Opus 5.5 pricing. Here's how it hits AgentSpace's lead-agent cost and the A/B test I'm running to check it.
6 min Models and cost Read -
Shopify AI Agents Can Now Check Out: A ChatFlow Note
Shopify AI agents can now complete checkout. What changes and what doesn't for a WhatsApp sales flow, plus a checklist for today.
5 min WhatsApp and e-commerce Read -
Local AI Agent Deployment: An AgentSpace Token Cost Test
Can a local model cut AgentSpace's Claude worker token bill? My test plan, candidate tasks, and what I don't know yet.
6 min Models and cost Read -
AI Agent Tool Permissions Sandbox: An Agent Testing Its Own Output
Datasette's app_debug() sandbox trick and whether it solves letting AgentSpace worker agents safely test their own output.
5 min AI agent team Read -
AI Agent Permission Scoping: After the OpenAI Lesson
After the news of OpenAI agents acting outside their bounds, how I built permission scoping for AI agents into AgentSpace and ChatFlow.
5 min AI agent team Read -
AI Agent Memory: What I Built After Losing 3 Hours
AI agents restart from zero every session. Here is the persistent memory file layout, the checkpoint discipline, and what you should never write to memory.
7 min AI agent team Read -
My AI Agent Team Runs Without Me: 3 Lessons From Autopilot
How I run AI agents as a team instead of one assistant: the sprint planning method, lead-agent delegation, and 3 hard lessons from building live on stream.
6 min AI agent team Read -
Stop Using One Giant Prompt: How I Run AI as an 8-Agent Team
I run 4 SaaS products solo because I treat AI not as a single assistant, but as an 8-person team with clearly separated roles. Here is the full system.
3 min AI agent team Read