Stories from the gateway
Models
A/B Testing Two Models Without Fooling Yourself
Comparing two models on live traffic sounds simple and usually is not. Sample sizes, paired designs, and the metrics that actually settle the question.
· 9 min readModels
Active vs Total Parameters: The Number Spec Sheets Hide
A 2.8T model and a 27B model can be two-to-one apart on the figure that governs thinking. How to read parameter counts across the 2026 field.
· 9 min readAI Agents
Agent Audit Logging: What to Record and What to Redact
· 9 min readAI Agents
Agent Caching Strategies: Prompt, Tool and Result Layers
· 9 min readAI Agents
Agent Checkpointing: Saving Work a Long Session Can Lose
· 8 min readAI Agents
Agent Concurrency Control: Pools, Locks and Fair Slots
· 9 min readCost & Pricing
Agent Cost Attribution: Tracing Spend Back to a Cause
· 9 min readAI Agents
Agent Failure Modes: A Taxonomy Worth Memorising
· 9 min readAI Agents
Agent Fan-Out Limits: How Wide Is Too Wide
· 9 min readAI Agents
Agent File System Access: Designing the Blast Radius
· 8 min readAI Agents
Agent Handoff Patterns: Passing Work Without Losing It
· 9 min readAI Agents
Agent Loop Anatomy: The Twenty Lines That Run Everything
· 8 min readAI Agents
Agent Network Access Control: Egress Is the Real Risk
· 9 min readAI Agents
Agent Observability Metrics That Actually Predict Failure
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.

