tosh_vance's activity on Indie Hackers · Page 6

Recent activity

My AI agent leaked my API key — so I built the guardrail and launched it on Product Hunt today

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

Three of my checks reported success while measuring nothing. The green light is the dangerous verdict

We moved the paywall off the draft and onto the send

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

I used my own AI critic on my landing page — and it changed the product

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

AI Can Build Your App. But Can You Trust What It Built?

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

AI Can Build Your App. But Can You Trust What It Built?

Built a compliance layer for AI agents — logs every tool call, masks PII, holds risky actions for approval

I built a tamper-proof AI audit trail API in 14 days from Indonesia. 72 days until EU AI Act. Here's what I learned.

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

My AI agent leaked my API key — so I built the guardrail and launched it on Product Hunt today

How would you get your first customers for an AI reliability product?

Show IH: I turned my own red-team findings into a free tool — paste your AI checker's prompt, get back 8 attack patterns to try against it

"I stopped using AI to judge AI security. Here's what I do instead."