Episode
How Cogent builds AI agents that have to be right every single time | Geng Sng (Co-founder & CTO - Cogent)
- Podcast
- Max Agency
- Published
- May 22, 2026
- Duration seconds
- 4497
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/max-agency-7807113/episodes/how-cogent-builds-ai-agents-that-have-to-be-right-every-single-time-geng-sng-co-founder-cto-cogent/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/max-agency-7807113/how-cogent-builds-ai-agents-that-have-to-be-right-every-single-time-geng-sng-co-founder-cto-cogent.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
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 – Referenced: Abnormal AI Amazon S3 Anthropic Bash ChatGPT Claude Code Claude Mythos CodeMender Codex Cogent Cursor Google DeepMind GPT-5.5-Cyber Jupyter Letta Mozilla OpenAI Opus 4.6 Opus 4.7 Vercel – Where to find Geng: LinkedIn – Where to find Harrison: LinkedIn Twitter/X – Where to find LangChain: Website Docs – Send feedback or questions to [email protected] – Timestamps: (00:00) Why mean time to exploit collapsed from years to minutes (02:08) Inside Cogent's Agent Lake architecture (05:11) Why Cogent rejected graph databases (10:48) The trust ladder before agents touch production (15:13) The three types of agents inside Cogent (17:07) How Cogent sandboxes its agents (19:16) Short-circuiting interactive agents with a deeper planning phase (24:31) What to do when users believe agents too much (31:21) Why sub-agents let agents go on side quests (34:59) Two-tiered evals and the metric that catches bad prompts (40:00) Cogent’s unique approach to context (48:39) Cogent Research and the move…