This article presents Analysis / Implementation / Reflection, a simple pattern for resolving issues. While the core of this pattern, the implementation, is quite conventional, there are a couple of novel additions. In the analysis phase, the agent is used to explore the issue and create a suitable harness to evaluate the solution. While the reflection phase probes the agent to provide a qualitative assessment of the implementation.

The Scott Logic Blog offers insights, thought leadership, and technical expertise across various domains including software development, UX design, and financial services technology. Developers can explore articles on emerging technologies, industry trends, and software engineering best practices. Additionally, the blog covers case studies, project insights, and client success stories, providing  perspectives for technology professionals and enthusiasts.

Scott Logic

A practical three-phase workflow for resolving software issues using agentic AI: Analysis (using the agent to understand the issue and write failing tests via TDD), Implementation (driving the agent through a Red/Green loop until tests pass), and Reflection (using targeted prompts to challenge the solution's architecture, maintainability, and security). Additional tips cover establishing project baselines via copilot instructions, faster issue contextualisation with multimodal models, managing context window limits with MCP, and debugging AI chat via the harness layer.

Analysis → Implementation → Reflection – a practical technique for issue resolution with agentic AI

Analysis → Implementation → Reflection loop