// building in public
Building in public.
One problem at a time.
I'm Richard, a cybersecurity and SaaS product manager tinkering on personal projects with AI. This is where I share what works, what breaks, and what I'd tell someone starting from zero.
Richard Muffler
PM · security · AI builder
currently building
probl.me, this blog, in public.
+ Celly, a sister product.
+ Celly, a sister product.
// what I write about · click a topic
// latest
Fresh from the workbench
ai-development
Prompt Injection Is Already Hiding in What AI Agents Read
Prompt injection hides in webpages, DNS records, emails, and PDFs that AI agents read. Here's what happened to me, and the defenses that actually help.
tech-tools
Why I SHA-Pin Every GitHub Action (and Automate Updates)
I lock every GitHub Action to its commit SHA instead of a mutable tag, then let Dependabot keep the pins current. Here's why a tag alone isn't enough.
ai-development
How Context Limits Changed the Way I Build with AI
I was getting inconsistent answers and the AI kept forgetting what we'd built. Here's how I stopped fighting context limits and started designing around them.