Featured
AI·MCP·Platform Engineering
Introducing SixDegree - The Context Layer for Enterprise AI
Introducing SixDegree - the context layer for enterprise AI. Business is about relationships. Now AI can reason over them.
Craig Tracey ·
sixdegree
Thinking in Relationships
Operations·Enterprise AI·Context
Your operations run on tribal knowledge. AI will make that worse.
Every operations leader has tried to fix the opacity problem. AI agents make the cost of failure visible and immediate. Here is what changes now.
Craig Tracey ·
AI Agents·Governance·Enterprise AI·Context
Governance Theater Won't Survive Agentic AI
Policies and approval workflows can't constrain agents that don't share your view of reality.
Craig Tracey ·
Context·Enterprise AI·Data
Context layer vs data catalog: what every AI initiative needs to know
Every enterprise AI initiative hits the same wall. The model is fine. The agent still gives wrong answers. Here is why, and what to do about it.
Craig Tracey ·
Agents·Context·AI
Levie Nailed the Job Description. He Left Out the Hard Part.
Aaron Levie nailed the job description. But the person he wants to hire will spend most of their time doing plumbing nobody planned for.
Craig Tracey ·
Context·Agents·Platform Engineering
10 Best Practices for AI Context Management
Most teams managing AI context are using markdown files. Here's what better looks like.
Craig Tracey ·
Platform Engineering·Context
The Service Catalog Problem Isn't Backstage. It's the Catalog.
Backstage is hard to run. Cortex and OpsLevel made it easier. But none of them changed what a catalog fundamentally is: a human-authored approximation of system state that starts drifting the moment someone forgets to update it.
Craig Tracey ·
Agents·Context·Governance·MCP
Why Live Knowledge Graphs Are the Missing Context Layer for Safe Agentic AI in 2026
Live knowledge graphs solve the biggest barriers to production agentic AI: governance, accuracy, and orchestration that RAG and raw MCP can't touch.
Craig Tracey ·
MCP·Agents
Operating MCP Servers in Production
Getting an MCP server to work is not the hard part. The hard part is operating one: knowing who can access what, catching failures before users do, and building enough visibility to improve over time.
Craig Tracey ·
MCP·Agents
Building MCP Servers That Models Can Actually Use
Model Context Protocol has moved fast, but implementation quality lags behind adoption. This post covers tool design and context quality: the two areas where most MCP servers fail.
Craig Tracey ·
AI·Context
Your RAG Passed Every Test and Failed Every User
Eval overfitting is real and underdiagnosed. Most RAG systems are built on a flat, static, insider-authored approximation of organizational knowledge. They don't have a model of the organization. They have documents about it.
Craig Tracey ·
AI·Agents·Platform Engineering
Building AI Agents: The Fundamentals
Twelve rules for building AI agents that actually work. What agents are, how the agentic loop works, and the mental models that matter.
Craig Tracey ·
Agents·MCP
We Gave LLMs 150 Tools: Here's What Broke.
MCP tool overload is real. We benchmarked six LLMs with 25 to 150 MCP tools and measured accuracy degradation, latency spikes, and hard API limits. The cheapest model won.
Craig Tracey ·