Agent Evaluation Framework Selection for GitHub-Hosted Pipelines
Trajectory-level evaluation catches agent failures that outcome metrics hide before merge.
Deja Okonkwo
Section
Agent Harness Design
6 stories in Agent Harness Design.
Memory Scope Configuration for Long-Running Coding Agents
Larger context windows make long-running agents worse, not better—here's why.
Soren Lau-Espinoza
System Prompt Engineering for Production Coding Agents
Organize system prompts in five layers to keep coding agents coherent across sessions.
Deja Okonkwo
Tool Call Interface Design for Coding Agent Skills
Separating tool calling, tool search, and MCP prevents teams from optimizing the wrong layer.
Deja Okonkwo
Skill Set Bloat and AI Agent Performance Degradation
Larger skill libraries make AI agents pick the wrong tool more often, not because of context limits.
Soren Lau-Espinoza
Dead Skill Detection in AI Coding Agent Harnesses
Dead skills bloat AI agent prompts, wasting tokens and slowing inference with unused capabilities.
Deja Okonkwo