Security Agents Orchestrating Developer Agents
joshua_saxe · x · 2026-07-17
The author points out that in the security organizations of major tech companies, fixing security issues often relies on privately messaging engineers for weeks and fighting for a "don't rush to launch" window under PM pressure.
Their startup direction is to restructure this process into a coordination problem between "security agents ↔ developer agents". They believe this approach is an inevitable trend in an era of mechanized attacks, and invite security professionals to provide feedback or connect at Black Hat / Def Con.
More from coding & agent
- Soft Clamp cuts tool-call overuse in multi-teacher distillation, from 13.7% to 9.0% — antgroup · 2026-07-21
- SpecJudge runs locally on Ollama to pick the right-sized AI model for your project — jokiruiz · 2026-07-21
- A developer maps out six design rules for CLIs that humans and AI agents can both use — yujiezha · 2026-07-21
- A coding-agent skill that forces ADHD-friendly, answer-first output — ayghri · 2026-07-21
- A set of agent skills for CAD, robotics, and hardware design — earthtojake · 2026-07-21
- Outlines keeps LLMs on-rails with structured outputs — dottxt-ai · 2026-07-21