Blake Jacobs' profile on Product Hunt

About

I am a content engineer at PentesterLab. I design hands-on security exercises that teach people to find real vulnerabilities. I started in cybersecurity more than ten years ago as a young hacker. I had a curious mindset and a passion for technology from the start. That work shaped how I see software: every system has a weakness, and you find it by reading closely. In my spare time, I build things. Next goal: a SaaS of my own. The plan is to ship small tools, learn from real users, and grow the best one into a product. Away from the keyboard, I lift weights. Slow, measurable progress. Security and software reward the same habits: show up, train, measure, repeat.

Links

Github

Github (Personal)

Twitter

Badges

Tastemaker

Gone streaking

Forums

•

1h ago

We Benchmarked Whether a Pattern Reference Actually Changes How an AI Agent Refactors

Hi everyone,

We spend our days watching AI coding agents refactor legacy code, and we kept seeing the same failure. Agents know design patterns from training data, but they know them unevenly. They invent one-off abstractions where a named pattern would fit. They force patterns where they don't belong. And they skip the small, safe steps that keep tests green. So we built a pattern reference that an agent can pull mid-task. It's a website, an MCP server, and a set of agent skills. Then we asked ourselves a simple question. Does it actually change what the agent produces?

p/ai-patterns

•

2h ago

The Refactor Benchmark

The setup

We wrote a deliberately messy TypeScript codebase: an order system with 840 lines, 11 modules, and 67 tests. It carries the debt you find in legacy code. A duplicated pricing engine. Deep nesting. Magic numbers. Dead code. We copied the codebase into two identical repositories. The same coding agent, with the same model and the same prompt, refactored both. The MCP run could call the aipatterns MCP server and read its skills. The plain run had no server and no skills. One static analyzer scored both results after the runs. This was a small test: one run per condition. We say more about that below.

p/ai-patterns

•

22h ago

Design Patterns for AI Coding Agents

The problem

AI coding agents write production code now. Ask one which design pattern fits your problem. You get a confident answer. Nobody measured it.