Stories from the gateway
AI Agents
Agent Permission Models: Who Decides What a Tool May Do
Per-call prompts, session grants, capability scoping and policy engines. How the main agent permission models behave once real work runs through them.
· 9 min read
AI Agents
Agent Prompt Versioning: Treat Prompts Like Deployed Code
A prompt edit is a production change with no compiler and no stack trace. How to give prompts a stable identity, trace them, roll them out and roll them back.
· 9 min readAI Agents
Agent Queueing and Backpressure: When to Say No
· 9 min read
AI Agents
Agent Regression Suites: Catching Breaks Before Users Do
· 9 min read
AI Agents
Agent Resumption Patterns: Restarting Without Starting Over
· 8 min readAI Agents
Agent Self-Correction: When Reflection Helps and When It Does Not
· 9 min readAI Agents
Agent Shell Access Safety: Giving a Model a Terminal
· 9 min readAI Agents
Agent State Machines: Constraining the Loop That Wanders
· 8 min readAI Agents
Agent Task Decomposition: How Small Is Small Enough?
· 9 min read
AI Agents
Agent Test Harnesses: Testing a System That Is Not Deterministic
· 9 min readAI Agents
Agent Timeout Strategies: Bounding a Loop That Cannot Stop
· 9 min readAI Agents
Agent Token Budgets: Capping Spend Without Capping Capability
· 8 min readAI Agents
Agent-to-Agent Protocols: What They Solve and What They Do Not
· 9 min read
Models
Agentic Coding Models Compared: Who Survives the Loop
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.