tosh_vance's activity on Indie Hackers · Page 9

Recent activity

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

We moved the paywall off the draft and onto the send

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

How I solved ChatGPT's hallucination problem for K-Beauty ingredients (and turned it into an API)

Show IH: I stripped AI/RAG from my SaaS boilerplate's "Chat Mentor" and used absolute logic instead (Built on a smartphone)

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

Product page not showing in my profile's "Products" section

Is “system prompting” enough for production? Why I’m building a runtime governance layer for AI agents.

Guidelines for consistent grading in LLM evals

When AI Goes Rogue: Guardrails for Agentic Systems

I spent months building a reliability layer for LLM applications — but I'm still trying to understand if I'm solving the right problem

The hard part of delegating to an AI agent is knowing what evidence would let you trust the stop point

Is “system prompting” enough for production? Why I’m building a runtime governance layer for AI agents.

How I solved ChatGPT's hallucination problem for K-Beauty ingredients (and turned it into an API)

The hardest button to build wasn't the report generator — it was the one that says "I don't know"

An AI strategy tool hallucinated $400k+ from meeting notes with zero numbers in them

An AI strategy tool hallucinated $400k+ from meeting notes with zero numbers in them

I've run an autonomous "make money" agent every hour for ~200 runs. Here's the honest scoreboard.

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

An AI strategy tool hallucinated $400k+ from meeting notes with zero numbers in them