Letting non-technical users directly modify agent code is risky. A better pattern is to use a higher-level 'meta-agent'. Business users provide feedback in natural language to this agent, which then interprets the request and safely implements the updates to the primary agent's logic.

When iterating on content like an email, re-prompting can cause unwanted changes. Use the 'Canvas' feature to create a Google Doc-like environment within the chat. This allows you to lock in parts you like, manually tweak specific words or sentences, and then use that refined version as the basis for further AI generation.

Markdown plans from AI agents are becoming too long and unreadable. HTML allows for richer, more engaging artifacts with visuals and better formatting. This improves human oversight and collaboration with the AI, as the plans are more likely to be read and understood by the engineer.

The handoff between AI generation and manual refinement is a major friction point. Tools like Subframe solve this by allowing users to seamlessly switch between an 'Ask AI' mode for generative tasks and a 'Design' mode for manual, Figma-like adjustments on the same canvas.

Instead of immediately asking an AI to perform a complex task, first prompt it to create a functional spec or a sequential plan. Go back and forth to align on this plan before instructing it to execute, which significantly improves the final output's quality and relevance.

Establish a powerful feedback loop where the AI agent analyzes your notes to find inefficiencies, proposes a solution as a new custom command, and then immediately writes the code for that command upon your approval. The system becomes self-improving, building its own upgrades.

Instead of prompting for code line-by-line, "Plan Mode" has the AI agent generate a detailed plan in a markdown file first. The user reviews and modifies this plan like a spec document, elevating their role from coder to architect before the AI executes the build.

Achieve higher-quality results by using an AI to first generate an outline or plan. Then, refine that plan with follow-up prompts before asking for the final execution. This course-corrects early and avoids wasted time on flawed one-shot outputs, ultimately saving time.

To get better results from AI, don't ask for the final output immediately. Instead, prompt the AI to first provide a detailed process. This allows you to review and debug its logic, then instruct it to execute each step for a more accurate outcome.