SuperMcG's activity on Indie Hackers · Page 10

Recent activity

We've now shipped 300+ products in 21 countries using AI Velocity Pods — here's what we learned about scope, speed, and fixed-price contract

How we ship production apps in 38 days using AI Velocity Pods — a methodology breakdown

How we built a governance layer for AI Velocity Pods — and why it made us faster, not slower

I think AI agents have an authority problem we're treating as a permissions problem

I think AI agents have an authority problem we're treating as a permissions problem

I think AI agents have an authority problem we're treating as a permissions problem

I think AI agents have an authority problem we're treating as a permissions problem

How do you troubleshoot a production server today?

Our AI kept overruling the corrections users made

The thing that kills AI pilots is not accuracy.

I let a chain of AI agents run my store for four days. 27 products, 3 visitors, 0 sales — and the worst bug was my laptop.

Building AI Agents Control Tower: the observability layer the AI stack diagrams forget

Building AI Agents Control Tower: the observability layer the AI stack diagrams forget

Stop the Workflow, Ask a Human: Human-in-the-Loop Approvals in ByteChef

We stopped treating agents as features once they could take actions

We spent a year talking to 30+ teams about AI costs. Caching saved them 90% of tokens—and their bills still went up.

Confirmation-before-action is harder to design than I expected

Stop the Workflow, Ask a Human: Human-in-the-Loop Approvals in ByteChef

Building the "Cloudflare for AI Agents" (Open-Source) 🛡️

An AI agent saying “I stopped” is not the same as the system blocking the action

This is as far back as this page goes.