Skip to main content

Explore by topic

Experiments

Short notes from prototypes, benchmarks, and practical AI workflow testing.

PrototypesBenchmarksWorkflows7 posts

What you will find here

  • Prototypes that expose how a model or service behaves under real latency, input quality, and deployment constraints.
  • Benchmarks that compare accuracy, cost, and operational overhead instead of relying on vendor claims.
  • Workflow tests that document what broke, what scaled, and what I would change on the next pass.
  • Architecture notes that separate demo-ready paths from production-ready ones.

Posts tagged Experiments, including newer agent-pilot, MLV timing, and brand-overlay notes from the publishing backlog.

Most NEE warnings are noise: measure real MLV wall-clock

Teach teams to measure where MLV DAG time actually goes and fix only actionable native-execution engine fallbacks.

Pilot the use case, not the agent catalog

Make the case that enterprise agent programs should start from ranked use cases (orchestrator vs single agent vs tools) instead of from a menu of model endpoints.

Agent sessions vs the shell app: what should survive refresh

Where conversation state should live when a browser shell wraps a platform agent, and why refresh and quit behavior is an architecture choice.

Lineage explorers beat tribal notebooks

Argue for a small lineage explorer over ad-hoc pipeline docs so engineers can see dependencies before they break them.

Can Databricks Genie Build My Deck and Deploy My App?

What Databricks Genie Code actually changes for deck generation and app deploy when the assistant already sits inside your governed lakehouse context.

Image Classification Web App with Azure AI Services

How to shape an image classification web app on Azure AI Services so the UI stays simple, the backend stays operable, and Custom Vision iteration does not become a demo trap.

Real-time Motion Tracking and Pose Estimation

Why real-time pose estimation is a systems problem of capture, inference, and rendering, and how to design for latency, stability, and demos that survive messy video.