sixdegree

Revenue risk, account context, and the systems between them.

Practical field notes on finding the evidence your CRM, health score, and forecast leave out.

Context layer vs data catalog: what every AI initiative needs to know

Context·Enterprise AI·Data

Context layer vs data catalog: what every AI initiative needs to know

Data catalogs document assets. AI context layers connect live entities, relationships, and evidence. Compare their purpose, limits, and when to use each.

Craig Tracey ·

Levie Nailed the Job Description. He Left Out the Hard Part.

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 ·

10 Best Practices for AI Context Management

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 ·

The Service Catalog Problem Isn't Backstage. It's the Catalog.

Platform Engineering·Context

The Service Catalog Problem Isn't Backstage. It's the Catalog.

Backstage is hard to run and Cortex and OpsLevel made it easier. None of them changed what a catalog is: a human-authored approximation that drifts.

Craig Tracey ·

Why Live Knowledge Graphs Are the Missing Context Layer for Safe Agentic AI in 2026

Agents·Context·Governance·MCP

Why Live Knowledge Graphs Are the Missing Context Layer for Safe Agentic AI in 2026

Support agents fail in production because they lack live context: who owns the account, what they use, what is at risk. Live graphs fix the substrate.

Craig Tracey ·

Operating MCP Servers in Production

MCP·Agents

Operating MCP Servers in Production

Getting an MCP server working is not the hard part. Operating one is: who can access what, catching failures early, and enough visibility to improve.

Craig Tracey ·

Building MCP Servers That Models Can Actually Use

MCP·Agents

Building MCP Servers That Models Can Actually Use

MCP has moved fast, but implementation quality lags adoption. Tool design and context quality are the two areas where most MCP servers fail.

Craig Tracey ·

Your RAG Passed Every Test and Failed Every User

AI·Context

Your RAG Passed Every Test and Failed Every User

Eval overfitting is real and underdiagnosed. Most RAG systems have no model of the organization. They have documents about it.

Craig Tracey ·

Building AI Agents: The Fundamentals

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 ·

We Gave LLMs 150 Tools: Here's What Broke.

Agents·MCP

We Gave LLMs 150 Tools: Here's What Broke.

We benchmarked six LLMs with 25 to 150 MCP tools and measured accuracy loss, latency spikes, and hard API limits. The cheapest model won.

Craig Tracey ·

MCP vs CLI: You're Asking the Wrong Question

MCP

MCP vs CLI: You're Asking the Wrong Question

The debate between MCP and CLI for agent tooling misses the point. The real question is which mode you are building for, and where token costs hide.

Craig Tracey ·

Internal Developer Portals vs Context Layers

Platform Engineering·Agents·Context

Internal Developer Portals vs Context Layers

IDPs were built for humans browsing catalogs. Agents need queryable relationships, real-time state, and cross-system reasoning. IDPs cannot close that gap.

Craig Tracey ·

Previous
123
Next