Why This Company Won't Let AI Agents Touch Bash
Summary
The presentation details the evolution of an internal AI agent platform at Cyera, transforming a personal assistant project into an enterprise-wide tool for data security and operational efficiency. The core focus is on building robust guardrails to prevent agents from becoming uncontrolled 'black boxes.' Key architectural innovations include whitelisting tools over blacklisting them, implementing a structured citation system for verifiable claims, and replacing traditional RAG with a Knowledge Graph (KG) that allows agents to navigate interconnected data like an LLM wiki. The platform emphasizes controlled deployment, allowing multiple developers to build and own specialized agents while maintaining centralized security and governance.
Key takeaways
-
Controlled Agent Architecture
The system prioritizes control by whitelisting specific tools rather than blacklisting forbidden actions. A critical guardrail is the use of structured, validated output, ensuring that an agent cannot execute arbitrary code (like unrestricted Bash) or leak sensitive data outside its designated context.
-
Citation and Hallucination Mitigation
20:55
To ensure reliability, every claim generated by the agent must be backed by a citation. This is achieved by forcing the model to output structured blocks containing both the claim and the source reference. A second model then performs clean-context verification against the raw data to drastically reduce hallucinations.
-
Knowledge Graph over RAG
32:33
The platform utilizes a Knowledge Graph (KG) instead of standard RAG for context retrieval. This allows agents to 'walk' connections between entities (e.g., an exception, a service, and the related pull request), providing more structured and reliable data exploration than simply dumping retrieved documents.
-
Adoption through Platform Engineering
50:27
To drive adoption across engineering teams, the platform was designed to be easily customizable. By allowing users to name and modify their own agents (e.g., 'It's my agent'), the barrier to entry is lowered, promoting organic growth with a strategy of 'carrots, not sticks.'
Technical details
-
Agent Guardrails and Constraints
2305s
The system uses deterministic constraints by ensuring an agent can only send messages to the specific thread or context it was triggered in. Tools are shared across agents but must pass schema validation and run code through deterministic checks.
-
Knowledge Graph Structure
2450s
The KG indexes diverse data sources (code, Slack messages, exceptions) by defining entities and relations between them. Agents use specialized tools (e.g., `find exact`, `semantic search`, `find related`) to navigate this graph efficiently.
-
Confidential Data Handling
3680s
For highly sensitive data, two agents ('Mulder and Scully') are used: one agent investigates the issue in a controlled environment, outputting only findings in a fixed vocabulary. A second agent then reads this structured output to generate an explainer for unapproved personnel.
-
Agent Lifecycle and Improvement
2750s
The platform includes a 'Dream State' mechanism where the agent periodically reviews its own interactions and feedback. It can then autonomously submit a pull request to improve its own code or suggest new tools.
Mentioned resources
- Cyera
- DSPM (Data Security Posture Management)
- OpenClaw
- Sentry
- Tessl
Channel & topics
Watch on YouTube · Back to latest
This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.
