what's the best way to construct prompts for the clay's claygent model? I'd like to ideally use chatgpt (or another llm) to help me construct the most effective prompts for it. how should i ask chatgpt to construct a prompt that best works with Clay's claygent model?
When asking ChatGPT to construct effective Claygent prompts, follow these principles: 1. Request a system prompt that provides context and outlines the goal of your task. 2. Ask for clear, step-by-step instructions for Claygent to follow. 3. Specify how you want the output formatted (structure, tone, style). 4. Mention that Claygent combines generative AI with agent models for web-based tasks. You can also use Clay's built-in "Help me" button in the Use AI panel for tailored prompt assistance, or browse templates for pre-configured examples.
Sources: Prompt Engineering Crash Course [Limitless Research] - Clay University Prompt Engineering Crash Course [Limitless Research] - Clay University 11 AI Prompts to Automate Prospect Research with Claygent [Automated Outbound] - Clay University Writing AI prompts in Clay | Documentation | Clay University
No specific advice on this one, Miguel, since the best practice advice for any LLMs will largely apply for Claygent. I'd recommend using the built-in "Generate" button, where you can use Clay to generate the prompts for Clay.
Hot off the press: https://www.notion.so/clayrun/Prompt-Engineering-at-Scale-The-Complete-Clay-Guide-21a7e66eb01480f48fcdcf5fdc8f8319 Not specific to Claygent, but the Clay perspective on best practices.
This thread was picked up by our in-app web widget and will no longer sync to Slack. If you are the original poster, you can continue this conversation by logging into https://app.clay.com and clicking "Support" in the sidebar. If you're not the original poster and require help from support, please post in 02 Support.