Topics
Read by series, or find a post by tag.
15 posts · 3 series · 45 tags
Series
AI governance in practice
5 posts · read in order
- 1AI Governance Is the New Cloud Security
- 2Guardrail Enforcement Must Live in Your SCPs, Not as an Afterthought in Your Application Code
- 3Cost Attribution for LLM Usage: What to Tag, What to Report, Who Reads It
- 4Observability for LLM Calls: What a Trace Should Contain, and How to Debug a Blocked Prompt
- 5MCP Servers in the Enterprise: What Changes When Tools Can Act
Leadership
3 posts
Agents and architecture
7 posts
- Prompt Routing: Why Every Request Shouldn’t Go to Your Most Expensive Model
- Bedrock AgentCore in Practice: What the Managed Primitives Buy You, and What They Don’t
- The Agent Harness, Explained: What It Is, and Which Parts Bedrock and AgentCore Give You
- Four Kinds of Repeated Tokens, and Four Ways to Stop Paying for Them
- Who Did It? Identity and Least Privilege for AI Agents
- Seven Architecture Decisions That Outlive the Model
- The Approval Gate Finally Has a Place to Live: AgentCore Lifecycle Hooks