Insights
Field notes on governed Salesforce AI and the data foundation it runs on.
Practical writing on building governed AI on the Salesforce platform — unifying data with Data 360, grounding agents, and the foundation that has to come first. The first articles are in progress; here's what we're writing about, and how to get our perspective sooner.
What we're writing about.
No filler and no recycled vendor blog posts — these will be practical pieces drawn from the work itself, written for the people who have to live with the result.
Unifying data with Data 360
Turning scattered records into one trusted view — and what that actually takes before agents and AI can rely on it.
Putting Agentforce 360 & Einstein to work
Where conversational and predictive AI earn their keep on the Salesforce platform, and where they don't yet.
Integration that holds up
Choosing between MuleSoft, Synatic and custom builds, and keeping systems in sync without brittle glue.
Building AI on a governed foundation
Why grounded, governed data has to come first — and how to engineer Salesforce AI that stays trustworthy past go-live.
Need that thinking applied now, not after we publish?
The fastest way to get our read on your situation is a direct conversation with the team building it.
Where your AI runs
A trust boundary you can actually defend.
The hard part of enterprise AI isn't the model. It's keeping the reasoning on your governed data instead of shipping it to tools you don't control. We engineer that in from the first phase, not bolt it on at the end.
“Your AI runs inside Salesforce’s trust boundary. We don’t pipe your data out to third-party AI tools. Agentforce operates on your governed Salesforce data, under the Einstein Trust Layer, with your permissions, sharing rules, and audit trail.”
One honest caveat: Integration (MuleSoft, Data 360) moves and federates data through governed, audited connectors, by design and under your control. What stays on-platform is your AI and its reasoning.
Salesforce engineers, not a bench
Computer-science engineers who do the Salesforce work: the data model, the flows, the sharing rules, the Agentforce build. The people who scope it stay on it through go-live.
Inside the trust boundary
Agentforce reasons over your governed Salesforce data under the Einstein Trust Layer, with your permissions, sharing rules and audit trail. Your CRM isn't copied into a third-party AI tool to do its work.
Evidence, not a demo
A named, evidence-gated method. Agents are scored against a held-out eval set before go-live, and you keep the kill-switch, permission matrix and audit log.
Skip the queue. Bring us the actual problem.
While the writing is underway, you can get a grounded, hands-on perspective on your Salesforce, data or AI challenge in a single working session.