Enterprise AI·Context·Agents
Hallucination Is the Feature, Not the Bug
A talk on why agents need ontologies nails the diagnosis but stops short of the hard parts. This is exactly what we've been building.
Craig Tracey ·
Revenue risk, account context, and the systems between them.
Practical field notes on finding the evidence your CRM, health score, and forecast leave out.
AI·Agents·AI Harness
Stop Letting Your Agent Thrash
A trivial question took our agent two and a half minutes. The model was fine, the harness let it thrash. Bounded loops beat a bigger model every time.
Craig Tracey ·
RevOps·Context·Agents
What Your CRM Can't Tell You About a Deal at Risk
Your CRM tracks the deal. It cannot see the support tickets, the usage drop, or the AE who went quiet. Deal risk lives between your systems.
Craig Tracey ·
Context·Agents·AI
Context Engineering vs Context Management: What's the Difference?
Context engineering operates at the prompt layer. Context management is the infrastructure underneath. Mixing them up is why agent pilots fail.
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 ·
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 ·
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 ·
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 ·
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.
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 ·
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 ·