Practical field notes on finding the evidence your CRM, health score, and forecast leave out.
Find deal risk outside the opportunity record.
Connect adoption, support, billing, and relationships.
Detect contract, billing, usage, and delivery gaps.
Find missing, stale, duplicate, and conflicting evidence.
Build explainable health from cross-system signals.
Featured article
RevOps·Support·Context
Support knows the account is unhappy. The forecast does not. The two systems hold the same customer under different identifiers and never compare notes.
Craig Tracey ·
AI Agents·MCP·Context·RevOps
SaaS spent 20 years selling silos. Agents and MCP finally give us a way out, and the incumbents are pulling everything back into their own box. The silo was never the database. It was the meaning.
Craig Tracey ·
AI Agents·Postmortems·RevOps·Context
A practical guide to running an AI agent postmortem: what evidence to capture, a worked renewal example, a checklist, and the false roots that waste the review.
Craig Tracey ·
RevOps·Context·Data
Why Salesforce and Gainsight customer health data disagree, when syncing destroys useful signal, and how to keep each value tied to its source.
Craig Tracey ·
RevOps·Context·Data
The CRM records what was sold. Stripe records what is being invoiced. When those diverge, the gap is usually a real event nobody logged.
Craig Tracey ·
Enterprise AI·Context·Agents
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 ·
Enterprise AI·Context·RevOps
Palantir's CEO says the winners in enterprise AI will own the application layer and the ontology underneath it. Here's why that is right, and what it takes to keep that layer current.
Craig Tracey ·
AI·Agents·AI Harness
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
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 ·
AI·Context·Operations
Most AI readiness advice says build a data team and document everything first. For a mid-sized company that is months of work before a single outcome.
Craig Tracey ·
Context·Agents·AI
Context engineering operates at the prompt layer. Context management is the infrastructure underneath. Mixing them up is why agent pilots fail.
Craig Tracey ·
Operations·Enterprise AI·Context
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
Policies and approval workflows can't constrain agents that don't share your view of reality.
Craig Tracey ·