For stubborn bugs, use an advanced prompting technique: instruct the AI to 'spin up specialized sub-agents,' such as a QA tester and a senior engineer. This forces the model to analyze the problem from multiple perspectives, leading to a more comprehensive diagnosis and solution.
Related Insights
Instead of prompting a specialized AI tool directly, experts employ a meta-workflow. They first use a general LLM like ChatGPT or Claude to generate a detailed, context-rich 'master prompt' based on a PRD or user story, which they then paste into the specialized tool for superior results.
Including the special keyword "ultra think" in a prompt signals Claude Code to engage in a more intensive thought process. This undocumented feature can significantly improve the quality of output for difficult bugs or complex tasks without noticeably impacting token usage.
Codex lacks a built-in feature for parallel sub-agents like Claude Code. The workaround is to instruct the main Codex instance to write a script that launches multiple, separate terminal sessions of itself. Each session handles a sub-task in parallel, and the main instance aggregates the results.
Many AI tools expose the model's reasoning before generating an answer. Reading this internal monologue is a powerful debugging technique. It reveals how the AI is interpreting your instructions, allowing you to quickly identify misunderstandings and improve the clarity of your prompts for better results.
To improve the quality and accuracy of an AI agent's output, spawn multiple sub-agents with competing or adversarial roles. For example, a code review agent finds bugs, while several "auditor" agents check for false positives, resulting in a more reliable final analysis.
When a prompt yields poor results, use a meta-prompting technique. Feed the failing prompt back to the AI, describe the incorrect output, specify the desired outcome, and explicitly grant it permission to rewrite, add, or delete. The AI will then debug and improve its own instructions.
Separating AI agents into distinct roles (e.g., a technical expert and a customer-facing communicator) mirrors real-world team specializations. This allows for tailored configurations, like different 'temperature' settings for creativity versus accuracy, improving overall performance and preventing role confusion.
When an agent fails, treat it like an intern. Scrutinize its log of actions to find the specific step where it went wrong (e.g., used the wrong link), then provide a targeted correction. This is far more effective than giving a generic, frustrated re-prompt.
Instead of relying on a single, all-purpose coding agent, the most effective workflow involves using different agents for their specific strengths. For example, using the 'Friday' agent for UI tasks, 'Charlie' for code reviews, and 'Claude Code' for research and backend logic.
Define different agents (e.g., Designer, Engineer, Executive) with unique instructions and perspectives, then task them with reviewing a document in parallel. This generates diverse, structured feedback that mimics a real-world team review, surfacing potential issues from multiple viewpoints simultaneously.
