Explore by topic
Experiments
Short notes from prototypes, benchmarks, and practical AI workflow testing.
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.
Featured experiments
Posts tagged Experiments, including newer agent-pilot, MLV timing, and brand-overlay notes from the publishing backlog.
Aug 7, 2026 · 9 min read
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.
Jul 24, 2026 · 9 min read
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.
Jul 24, 2026 · 9 min read
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.
May 20, 2026 · 9 min read
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.
Apr 8, 2026 · 9 min read
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.
Apr 8, 2026 · 9 min read
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.
Apr 8, 2026 · 9 min read
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.