AI models are trained to be agreeable, often providing uselessly positive feedback. To get real insights, you must explicitly prompt them to be rigorous and critical. Use phrases like "my standards of excellence are very high and you won't hurt my feelings" to bypass their people-pleasing nature.

To get beyond generic advice, instruct ChatGPT's voice mode to act as a challenging mentor. Prime it with a specific framework like the Theory of Constraints (TOC) and provide your resource limitations. This structured dialogue forces the AI to challenge your assumptions and generate realistic, actionable solutions instead of pleasantries.

To simulate interview coaching, feed your written answers to case study questions into an LLM. Prompt it to score you on a specific rubric (structured thinking, user focus, etc.), identify exact weak phrases, explain why, and suggest a better approach for structured, actionable feedback.

To get truly honest feedback, Webflow's CPO programmed her AI chief of staff to be "mean." The AI delivers a "brutal truth" section, criticizing her for spending time on tasks below her role. This demonstrates how AI can serve as an unflinching accountability partner, providing feedback humans might hesitate to give.

Don't let performance reviews sit in a folder. Upload your official review and peer feedback into a custom GPT to create a personal improvement coach. You can then reference it when working on new projects, asking it to check for your known blind spots and ensure you're actively addressing the feedback.

Rehearse difficult conversations by having an AI adopt the persona of your boss, partner, or employee. This allows you to practice your approach, refine your messaging, and anticipate reactions in a safe environment, increasing your confidence and effectiveness for the real discussion.

To scale the CEO's feedback, his EA created a custom GPT trained on his feedback style, strategy docs, and company norms. Team members use this 'CEO clone' to stress-test their proposals before official review, improving document quality and saving executive time.

After receiving feedback that his writing was too long, a PM built a custom GPT to make messages more concise. He fed it newsletters and books on effective writing from experts, creating a personalized coach that helped him apply the feedback in his daily work, leading to better engagement from colleagues.

A marketing leader uses her personalized GPT to coach junior writers more efficiently. She inputs shorthand notes on their work, and the AI structures it into coherent feedback that explains the reasoning behind the edits. This transforms a time-consuming rewrite into a scalable coaching opportunity.