# Guru Sattanathan

> Practitioner writing on AI agents, systems architecture, MCP, and production patterns. Principal Solutions Architect at Arcade.dev.

## Articles

- [Every Way to Secure an AI Agent (and What Breaks When You Don't)](/blog/agent-security-patterns/): A practitioner's guide to 8 credential management patterns for AI agents. From .env files to zero-trust architectures. Real incidents, trade-offs, code examples.
- [The AI You Dismissed Isn't the AI That's Coming](/blog/the-ai-you-dismissed-isnt-the-ai/): The gap between AI skeptics and believers isn't intelligence - it's exposure.
- [The App You Should Be Building Is You](/blog/the-app-you-should-be-building-is/): Everyone's racing to ship. Maybe the real leverage is standing still.
- [Federation Over Embeddings: Let AI Agents Query Data Where It Lives](/blog/federation-over-embeddings-let-ai/): Before building vector infrastructure, consider federation: AI agents with tool access to your existing systems.
- [Java's Agentic Framework Boom is a Code Smell](/blog/javas-agentic-framework-boom-is-a/): Stop building orchestration frameworks and start building agents.
- [You Don't Need an Agentic Framework to Start Building Agents](/blog/you-dont-need-an-agentic-framework/): The pattern is simpler than you think.
- [Low latency Serving on Iceberg with Apache Pinot](/blog/low-latency-serving-on-iceberg-with/): Apache Pinot now supports native querying of Iceberg tables with low-latency serving directly on the data lake.
- [Your Next Software Decision Won't Be Easy](/blog/your-next-software-decision-wont/): For architects in an era where AI rewrites the rules overnight.
- [Query Streams for Apache Pinot](/blog/query-streams-for-apache-pinot/): Lightweight tool to push real-time query results from Apache Pinot to webhooks.
- [The Truth About AI Agents: Are They Really That New?](/blog/the-truth-about-ai-agents-are-they/): AI agents build on familiar integration patterns, enhanced with smarter tools.
- [Partial UPSERTs in Apache Pinot](/blog/partial-upserts-in-apache-pinot/): Column-level update strategies for real-time analytics.
- [The Coriander Effect](/blog/the-coriander-effect-elevating-user/): How small design details drive user activation and retention.

## Author

Guru Sattanathan is a Principal Solutions Architect at Arcade.dev, focused on AI agent security, MCP (Model Context Protocol), and production deployment of agent systems. Previously at Confluent, StarTree, and Deloitte. Builder of nerd-lang-core (LLVM-backed language for machine-generated code) and not7-core (declarative agent runtime in Go).

## Links

- [LinkedIn](https://linkedin.com/in/gnanaguru)
- [Twitter/X](https://x.com/avoguru)
- [GitHub](https://github.com/avoguru)