Posts that touch this subject but live under another topic.
Working with Claude Code
82 agents, one bug: running Claude's security scanner on my own code
I pointed the new claude-security plugin at this very site. It spawned 82 agents, proposed 10 vulnerabilities, and then argued itself out of 9 of them. The one that survived was real — and it shipped to prod the same afternoon.
24 Jul 2026
·
6 min read
Shipping an AI feature into my own product
·
Part 3
Adding a job description match to my AI Concierge
I added job-description matching to the AI concierge on my career site. It shipped with no new bean, no new table, and no migration — because the leverage was in a seam I'd already built. A design note on shared streaming cores, streamable structured output, and treating a pasted JD as hostile.
13 Jul 2026
·
11 min read
Shipping an AI feature into my own product
·
Part 2
I red-teamed my own AI concierge
My site has an 'Ask Zakaria' AI box that answers untrusted recruiter input. So I spent an afternoon trying to break it — prompt leaks, tool-call injection, XSS, a cross-language jailbreak. Here's what held, and why the real defense isn't a clever prompt.
7 Jul 2026
·
5 min read