Stories from the gateway
AI Agents
Replaying Agent Traces: Debugging a Run You Cannot Reproduce
Agent runs rarely reproduce, so the stored trace is the only evidence. What to capture, how to replay it, and where replay stops being faithful.
· 9 min read
AI Agents
Rollback Strategies for Agents That Changed Things
An agent stopped halfway through eleven changes. Checkpoints, compensating actions, staging areas and the undo plan you should require before it acts.
· 9 min read
AI Agents
Scratchpad Patterns: Giving an Agent Somewhere to Think
· 8 min readAI Agents
Shared Memory Between Agents: Designs That Actually Hold
· 9 min read
AI Agents
Speculative Agent Execution: Running Ahead of the Decision
· 9 min read
AI Agents
Summarisation in Agent Loops: Compressing Without Forgetting
· 8 min read
AI Agents
The MCP Security Model: Trust Boundaries You Actually Have
· 9 min read
AI Agents
Tool Call Retries: Retry the Transport, Not the Judgement
· 8 min readAI Agents
Tool Result Formatting: Shaping What the Model Reads Back
· 8 min readAI Agents
Tool Schema Design: The Prompt You Forgot You Were Writing
· 8 min readAI Agents
Tracing Multi-Step Agents: Building a Trace Tree That Holds
· 9 min readAI Agents
Verifier Agents: Gating Completion on a Check That Passes
· 9 min readAI Agents
Agent Cost Control: Patterns That Bound the Worst Case
· 9 min readAI Agents
Agent Error Recovery: Patterns That Keep the Loop Alive
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.