Data, Engineering, and Beyond

Fable 5 as the architect, cheaper models as the builders: multi-model coding with predictable costs

The $10 architect and the $2 builders — a worked session with real rates, the three places predictability leaks, and a hard stop you can prove.

Jul 6 • Sergey

Frontier AI Is No Longer Globally Available by Default

A European 5 eurocents on a fragmented world, passport-gated compute, and why the best models are becoming a privilege.

Jul 1 • Sergey

June 2026

How to Manage AI Spending Before It Becomes Cloud Spend Again

Why AI Cost Control is Becoming an Infrastructure Problem

Jun 30 • Sergey

Your compliance records are missing your AI traffic

You have log entries for HR and CRM, but not the prompts going to OpenAI/Anthropic or Mistral. But your team may sends EU customer data to OpenAI every…

Jun 11 • Sergey

Controlling LangGraph Tool Calls

Prompting Is Not Governance:

Jun 2 • Sergey

How to Make a LangGraph Agent GDPR-Safe

Use customer data in AI agents without losing control

Jun 1 • Sergey

May 2026

Data quality In Delta Lake and Iceberg

Part 3: Getting practical with data quality

May 29 • Sergey

Data quality In Delta Lake and Iceberg

Part 2: Three Pillars of Data Engineering Monitoring

May 28 • Sergey

Data quality In Delta Lake and Iceberg

Part 1: Stable Metadata + Operational Evidence

May 28 • Sergey

1

April 2026

The Deletion Delusion: Your Modern Data Platform is Probably failing compliance

Modern data architectures vs GDPR

Apr 20 • Sergey

March 2026

If we redact PII before the model sees the prompt, can we still preserve enough context for good reasoning?

Same privacy boundary. Better answers. Measured across 200 A/B prompts.

Mar 27 • Sergey

1

Why AI Agents Work in Demos but Fail in Production

Unless you’re doing it right—and right now, almost nobody is

Mar 18 • Sergey

2