Articles

AI engineering notes from real workflow work

Practical writing on agentic systems, orchestration, automation design, and the operating patterns behind reliable AI delivery.

EV
Evaluation • May 29, 2026

DropTicks Field Notes: AI eval datasets

Opinionated engineering notes for practical AI and software delivery. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 27, 2026

Scaling Notes: AI eval datasets

How the workflow changes as traffic, users, or data volume grows. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 26, 2026

Tooling Map: AI eval datasets

A map of useful tools, libraries, and platform decisions. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 24, 2026

Team Workflow: AI eval datasets

How engineering, product, and operations teams should collaborate. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 23, 2026

Deployment Playbook: AI eval datasets

How to prepare the workflow for CI/CD and production operations. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 21, 2026

Security Review: AI eval datasets

The security and permission concerns that should be reviewed. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 20, 2026

Evaluation Strategy: AI eval datasets

How to measure quality, reliability, and operational readiness. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 18, 2026

Common Failure Modes: AI eval datasets

The mistakes teams should identify before launch. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 17, 2026

Implementation Checklist: AI eval datasets

A practical checklist for building and reviewing the workflow. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • May 15, 2026

Architecture Guide: AI eval datasets

A system-design view for planning production implementation. how to build representative tests from real customer and workflow cases

Read article → Save
EV
Evaluation • Mar 10, 2026

AI Evaluation Is the Difference Between a Demo and a Product

How to create practical eval loops for prompts, RAG, agents, tool use, and production regressions.

Read article → Save