Overcommitted | Software Engineering and Programming Insights podcast

Agentic AI Development | What Your Agents Should Know with Alex Patterson

0:00
43:36
15 Sekunden vorwärts
15 Sekunden vorwärts

What does agentic AI development look like once you take it past the demo? Alex Patterson, a Senior Solutions Architect at Sanity and the founder of CodingCat.dev, joins us to talk about giving AI agents verified knowledge instead of guesses, why compiled knowledge bases beat naive RAG, and what changes when an MCP server goes to production, from authentication to agents acting on behalf of other agents. He also shares software engineering career advice for programming through the AI boom from someone who graduated during the dot-com bubble, and why he thinks most AI work could run on local models within a couple of years.


Links

https://codingcat.dev/post/sanity-knowledge-bases

https://codingcat.dev/post/the-five-layers-of-agentic-context-why-canon-only-turns-when-someone-signs-off

https://codingcat.dev/course/mcp-in-production

https://codingcat.dev/sponsorships

https://codingcat.dev

https://alexpatterson.dev/


Hosts

Overcommitted: https://overcommitted.dev

Bethany Janos: https://www.trustyduck.dev

Brittany Ellich: https://brittanyellich.com


Weitere Episoden von „Overcommitted | Software Engineering and Programming Insights“