• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

Provides a specific architecture for stopping an agent from running destructive or data-leaking SQL on production databases, illustrated with a real demo where an unguarded agent deletes a table to fix an error.

• 0:00Introductions, MCP Toolbox and managed MCP
• 2:56Common tool patterns for databases
• 4:37Structured SQL tools for production
• 5:20Build time against run time
• 6:16When a build time tool deletes the table
• 8:46Your database is only as secure as your agent
• 9:13The lethal trifecta and the confused deputy
• 11:19Separating user, application, and agent identity
• 12:33Evolving a tool from super user to constrained
• 14:55Custom tools and prepared statements
• 15:52Best practices for tool quality
• 17:39Bound parameters, keeping PII from the agent

• videoHow long can your skills be before your agent forgets what you told it? — Laurie Voss, Arize AI
• video500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIn
• videoDeep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher
• videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax

• videoThe Death of Developer Advocates — Stephanie Jarmak, SourcegraphAI Engineer
• video500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedInAI Engineer
• videoIT Admin for the AI Workforce — Sarthak Aggarwal, DecaworkAI Engineer

Checking sign-in…

Loading comments…