Inside Cogent's three-agent architecture for autonomous defense | Geng Sng (Co-founder, Cogent)

Geng Sng is co-founder and CTO of Cogent, which builds autonomous agents that remediate vulnerabilities for enterprise security teams. Today, Cogent's agents process billions of security events per day, maintaining a live context graph of every asset and vulnerability across customer environments. In this conversation, Geng walks through Cogent's hot vs cold context split, the sub-agents that handle side quests, and the two graphs they run in parallel. We also discuss: • Why defensive security is harder for AI than offensive • Under the hood of Cogent's three agents • Inside Cogent's “read only” by-default sandboxes • Why graph databases don't scale for security data • Cogent Research and the move into formal verification • Why interactive agents need a deeper planning phase to one-shot References: • Abnormal AI: https://abnormal.ai/ • Amazon S3: https://aws.amazon.com/s3/ • Anthropic: https://www.anthropic.com/ • Bash: https://www.gnu.org/software/bash/ • ChatGPT: https://chatgpt.com/ • Claude Code: https://www.anthropic.com/claude-code • Claude Mythos: https://red.anthropic.com/2026/mythos-preview/ • CodeMender: https://deepmind.google/blog/introducing-codemender-an-ai-agent-for-code-security/ • Codex: https://openai.com/codex/ • Cogent: https://www.cogent.com/ • Cursor: https://cursor.com/ • Google DeepMind: https://deepmind.google/ • GPT-5.5-Cyber: https://openai.com/index/gpt-5-5-with-trusted-access-for-cyber/ • Jupyter: https://jupyter.org/ • Letta: https://www.letta.com/ • Mozilla: https://www.mozilla.org/ • OpenAI: https://openai.com/ • Opus 4.6: https://www.anthropic.com/news/claude-opus-4-6 • Opus 4.7: https://www.anthropic.com/news/claude-opus-4-7 • Vercel: https://vercel.com/ Where to find Geng: • LinkedIn: https://www.linkedin.com/in/geng-sng/ Where to find Harrison: • LinkedIn: https://www.linkedin.com/in/harrison-chase-961287118/ • Twitter/X: https://x.com/hwchase17 Where to find LangChain: • Website: http://langchain.com • Docs: https://docs.lan