Data Engineering's Durable Skills: What AI Can't Automate
The data engineer who survives the next five years isn't the one who codes the fastest — it's the one who understands context. Here's what that means in practice.
Blog
AI & Agents
5 min read
Which parts of your eval framework you can stop maintaining
A managed evaluation service can take over the judge, but not the contract tests, the drift canary, or anything needing provenance for the judge itself. Testing one produced four faults that each returned a plausible number instead of an error.
By Jeremy
Continue reading →
AI & Agents
25 min read
Multi-turn context safety alerting: catching what a per-message filter cannot
Per-message filters like Model Armor correctly pass most of a multi-turn probe. Adding the conversation tier that catches it, and the alerting fallback that turned out to matter more.
By Jeremy
Continue reading →
AI & Agents
5 min read
Ask the AI to Interview You
It takes ten minutes to generate a research report, a deck, or a recommendation list now, and the ability to explain any of it is what is quietly slipping. The fix I landed on is to have the AI turn around and interview me.
By Jeremy
Continue reading →
AI & Agents
5 min read
Stacking Governance Layers Without Losing Track of Them
Seven or eight layers all answering some version of "is this allowed". Two questions sort almost all of it: where does each one bind, and who can actually change it.
By Jeremy
Continue reading →
AI & Agents
16 min read
Policy as Code Without a Cluster: Adding OPA to FinChat
FinChat already had five layers of policy, and every one of them evaluates an action that is already happening. None could see a change that does not exist yet. What OPA is, and how I filled that gap.
By Jeremy
Continue reading →
AI & Agents
7 min read
Routing AI guardrail violations to ServiceNow
Model Armor blocks a prompt and tells the user, and on most builds that is where it stops. Here is the full path from a guardrail violation to a correlated ServiceNow incident on Google Cloud, with screenshots from the running system.
By Jeremy
Continue reading →
AI & Agents
5 min read
Your AI Risk Register Has Four Bullets. FINOS Has 46.
SR 26-2 punted generative AI out of model risk scope and told you to govern it anyway. The FINOS AI Governance Framework is a free catalogue of 46 risks and controls, with the regulatory mapping already done.
By Jeremy
Continue reading →