AI agents in production
14 moments from 14 videos · 33:56 min total
This collection focuses on scaling, rate limiting, and observability challenges when running agents. These talk segments help platform engineers maintain stable agentic systems.
Introduction to building reliable AI agents in production
Overcoming the experimental nature of AI tools requires strict evaluation and testing frameworks before enterprise deployment.
Tool call dominance in production AI agents
Analyzing internal agent data reveals knowledge base search as the most utilized tool over native product actions.
Moving an impressive AI agent demo into production environments
While building a compelling demo took only two weeks, reaching internal beta and design partners required six months of refinement.
Four core challenges for production agents
The critical need for auditability, governance, drift control, and fine-grained kill switches in agentic systems.
Building client-facing AI agents for engineering teams
Practical implementations of AI agents focus primarily on serving internal engineering teams and end customers.
Evolution and challenges of building AI applications
Transitioning from basic chatbots to multi-agent production configurations introduces severe workflow integration complexities.
Expanding AI agents across workflows and team structures
Deploying dedicated agents for tasks like deployment monitoring while experimenting with manager-less, cross-functional engineering roles.
Introduction to Amazon Bedrock Agent Core capabilities
Agent Core provides production-ready building blocks to simplify the overall development and infrastructure of AI agents.
Empowering site reliability engineers with integrated AI agents
AI agents embedded directly within production infrastructure help engineers quickly identify the root cause of late-night system failures.
Architectural checklist for reliable and secure agent deployment
Ensuring resilient production systems involves implementing model gateways, assigning agent identities, integrating open telemetry, and rehearsing failovers.
Assessing production risks from AI agents and unencrypted servers
While tools predicting JavaScript memory leaks are unproven, unencrypted FTP servers and rogue AI agents deleting production datasets pose real risks.
Best practices for implementing reliable AI agent frameworks
Defining clear operational boundaries for autonomous execution scopes while deliberately integrating human expert validation for safe production rollouts.
Securing local AI development workflows against production failures
Leveraging open-source tracing locally to run safety checks on coding agents without extra overhead.
The gap between enterprise AI promises and production reality
Agentic AI projects frequently stall as disconnected rule-based automation instead of reaching real production deployment.
Your mix. Instantly.
More mixes
AI & Machine Learning
AI coding agents
AI & Machine Learning
MCP (Model Context Protocol)
AI & Machine Learning
RAG
Languages & Frameworks
TypeScript
Languages & Frameworks
React
Languages & Frameworks
Java
Cloud, Platform & Data
Platform engineering
Cloud, Platform & Data
Observability
Cloud, Platform & Data
Infrastructure as code
Architecture, Quality & Security
System architecture
Architecture, Quality & Security
Code review
Architecture, Quality & Security
Software supply chain security
Leadership, Career & Community
Engineering strategy
Leadership, Career & Community
Developer experience
Leadership, Career & Community