AI Agents & Orchestration
Meet ADLC
Introducing the ADLC — the Agent Development Lifecycle. The loop that governs how you calibrate AI agents to produce reliable output.
← All posts
AI Agents & Orchestration
AI Agents & Orchestration
6 posts
This is the live documentation of an actual multi-agent system, not a thought experiment. It starts with why specialist agents beat one generalist, works through how orchestration, context management, and model selection hold the system together, and ends at the guardrails — auto mode, drift detection — that stop it from drifting off the rails. The thread running through all of it: the QE role isn't shrinking as agents take on more of the work, it's changing shape.
AI Agents & Orchestration
The AI-Powered Developer
How 15 specialized agents go from ADO story to shipped PR — orchestration, context management, quality gates, and drift detection.
AI Agents & Orchestration
Auto Mode Needs a Referee
Author agents enforce quality structurally — rating AI output, retrying on partial passes, and escalating when something is fundamentally wrong.
AI Agents & Orchestration
Match the Model to the Job
Using the most powerful model for everything isn't a strategy — it's expensive and slow. Here's how to match models to tasks.
AI Agents & Orchestration
Specialists Beat Generalists
A single generalist agent doing everything sounds simpler. It isn't. Here's why specialists produce better output and preserve context at handoffs.
AI Agents & OrchestrationFeatured
Making the Case for QE in the Age of AI
AI isn't replacing QE — it's making the discipline more essential. The judgment behind good testing is exactly what AI can't supply.