The agentic loop: how to judge AI development work
A practical development loop for AI coding agents: define acceptance criteria, make a bounded change, inspect evidence, and decide when to repair, stop, or ship.
AhmedAIAI
Lessons, how-tos, and current links.
One page for practical AI learning: agent workflows, useful prompts, coding patterns, model news, and original sources.
How-to / AI lessons
Start with practical reads.
AhmedAIAI dubbing still needs a rights packet
Zack turns AI dubbing into a creator workflow checklist: voice consent, translation review, usage scope, editability, and source links before release.
ZackAIAI evaluations need the harness
Cara gives AI buyers and reviewers a checklist for reading evaluation claims: disclose the harness, tools, budget, retries, validity checks, and failure rules.
CaraAIWhere Ahmed is more confident than Claude
A running log of the moments where Ahmed's hands-on BIM experience beat the model's confident generalizations, starting with Revit journal save history.
AhmedRevitPort the behavior, not the identity
A field note on how to ask AI coding agents to copy useful tools between projects without crossing manifests, namespaces, IDs, deployment paths, or ownership boundaries.
AhmedAI
What I learned from a 250 GB C:\Autodesk\WI folder
A field note on what the C:\Autodesk\WI folder is, why Autodesk installer files can pile up, and what I checked before cleaning disk space.
AhmedRevitAI links
Original reporting and release notes.
Frontier models Boston Children's uses AI to unlock new diagnoses OpenAI / May 29, 2026 Agents How Braintrust turns customer requests into code with Codex OpenAI / May 29, 2026 Creator tools 9 demos of Gemini Omni and Gemini 3.5 in action Google AI / May 29, 2026 AI news Check out real-life AI prototypes from the Futures Lab. Google AI / May 29, 2026 Agents New and improved: Agent governance, intelligent workflows, and connected app experiences Microsoft 365 Blog / May 11, 2026