🤖 AI Agents & Workflows
Personal Trainer
Example outputs
Here is what ChatGPT, Claude, and Gemini typically return for this prompt:
I'd be happy to help design a weight loss exercise program! To create the most effective plan, I'll need some additional information: What is the person's current fitness level (beginner, intermediate, advanced)? Do they have any injuries or physical limitations? How many days per week can they commit to exercising? Based on typical weight loss goals, I'd recommend a combination of 3-4 days of cardio (like brisk walking, cycling, or swimming for 30-45 minutes) and 2-3 days of strength training to preserve muscle mass while creating a caloric deficit.
I'd be glad to help with a weight loss exercise program, though I'll need more specifics to tailor it properly. Generally, effective weight loss programming combines cardiovascular work (150+ minutes weekly of moderate intensity) with resistance training 2-3x per week to maintain lean muscle. However, the person's age, current activity level, any health conditions, available time, and equipment access would significantly shape my recommendations. Could you share those details so I can create something truly suitable rather than generic?
For weight loss, an effective program typically includes 150-300 minutes of moderate-intensity aerobic activity weekly (like brisk walking or cycling) plus strength training 2+ days per week targeting major muscle groups. A sample week might include: 3 days of 45-minute cardio sessions, 2 days of full-body resistance training, and 2 rest/active recovery days. To provide a more personalized plan, I'd need details on their current fitness level, age, available equipment, time constraints, and any health conditions or injuries.
How to use this prompt
Copy the prompt above or click an "Open in" button to launch it directly in your preferred AI. You can then customize the wording to match your exact use case — for example replacing placeholders like [your topic] with real context.
Which AI model works best
Claude excels at agent workflows thanks to its long context window (up to 1M tokens) and nuanced instruction-following. ChatGPT has native Actions (tool-calling) built in. Gemini integrates best with Google Workspace data. For autonomous workflows, Claude Sonnet 4.6 is the current sweet-spot for quality and cost.
How to customize this prompt
Adjust the agent's role and constraints to your environment. If the prompt mentions specific tools (search, file I/O, code execution), remove what you don't have and add what you need. Add guardrails: "Always ask for confirmation before writing files." Define success criteria explicitly.
Common use cases
- Building autonomous research assistants for a specific domain
- Creating chatbots with defined personalities and knowledge limits
- Orchestrating multi-step workflows (research → draft → review → publish)
- Defining system prompts for custom GPTs or Claude Projects
- Building agent loops that call tools and self-correct
Variations
Adapt the tone (more casual, more technical), change the output format (bullet points vs. paragraphs), or add constraints (word limits, target audience).