> ## Documentation Index > Fetch the complete documentation index at: https://docs.trilo.chat/llms.txt > Use this file to discover all available pages before exploring further. # Chatting with AI > How to have effective conversations with AI coworkers AI coworkers are designed to understand natural language and help with a wide range of tasks. This guide will help you communicate effectively to get the best results. ## Starting a Conversation ### Opening a Chat Click on an AI coworker in the sidebar or Direct Messages. Enter your question or request in the message box. Press Enter to send your message. The AI processes your message and responds in real-time. ### First Messages Good opening messages: * State what you need help with * Include relevant context * Be specific about the desired outcome **Examples:** ``` "I need help writing a project proposal for a new mobile app feature" "Can you explain how API rate limiting works?" "Help me brainstorm marketing ideas for our product launch" ``` ## Effective Communication ### Be Specific Vague requests get vague answers. Be specific about what you need. **Less effective:** ``` "Help with the email" ``` **More effective:** ``` "Help me write a professional email to a client explaining that their project will be delayed by two weeks due to technical issues. The tone should be apologetic but confident about the new timeline." ``` ### Provide Context The more relevant information you share, the better the response. **Include when helpful:** * Background on the situation * Your goals or objectives * Constraints or requirements * Target audience * Tone or style preferences **Example:** ``` "I'm preparing a presentation for our executive team about Q3 results. They prefer concise bullet points with key metrics highlighted. Our main achievement was 40% revenue growth. Can you help me structure the presentation outline?" ``` ### Be Direct State exactly what you want the AI to do. **Less effective:** ``` "I was thinking maybe the document could be better?" ``` **More effective:** ``` "Please review this document and: 1. Fix any grammar errors 2. Improve the clarity of the introduction 3. Add a stronger conclusion" ``` ## Conversation Flow ### Building on Previous Messages AI coworkers remember the conversation context. Build on previous messages: ``` You: Can you summarize this article? [attachment] AI: Here are the main points from the article... You: Now create a tweet thread from those points AI: Here's a thread with 5 tweets covering the key ideas... You: Make the second tweet more engaging AI: Here's a revised version of tweet #2... ``` ### Asking Follow-Up Questions Continue the conversation naturally: ``` You: What are best practices for user authentication? AI: Here are key best practices: [explanation] You: Can you explain point 3 in more detail? AI: Of course! Point 3 is about... [detailed explanation] You: How would I implement that in Node.js? AI: Here's how you would implement it... [code example] ``` ### Redirecting If the conversation goes off track: ``` You: Actually, let's go back to the original topic. Can you focus on the security aspects? AI: Of course! Let me refocus on security... ``` ## Giving Feedback ### When Output Is Good Confirm when you're happy: ``` You: Perfect, that's exactly what I needed! ``` ### When Output Needs Changes Be specific about what to change: ``` You: This is good, but can you: - Make it shorter (about half the length) - Use simpler language - Add more concrete examples ``` ### When Output Is Wrong Correct misunderstandings: ``` You: That's not quite right. I meant [clarification]. Can you try again with this in mind? ``` ## Types of Requests ### Questions Ask for information or explanations: ``` "What is the difference between REST and GraphQL?" "How do I calculate compound interest?" "What are the best practices for code reviews?" ``` ### Task Completion Request specific work to be done: ``` "Write a product description for our new feature" "Create a list of interview questions for a marketing manager role" "Generate test cases for the login functionality" ``` ### Analysis Ask for analysis of information: ``` "Summarize the key points from this document" "What are the pros and cons of this approach?" "Identify potential issues with this proposal" ``` ### Creative Help Get creative assistance: ``` "Brainstorm names for our new product" "Help me come up with a tagline for the campaign" "Suggest alternative solutions to this problem" ``` ### Editing Request improvements to content: ``` "Make this email more professional" "Simplify this explanation for a non-technical audience" "Check this text for grammar and clarity" ``` ## Using Attachments ### Sharing Files Include files in your conversation: 1. Click the attachment icon 2. Upload your file (document, image, etc.) 3. Add your question or request 4. Send **Example:** ``` [Attachment: quarterly_report.pdf] "Can you summarize the key findings from this report?" ``` ### What You Can Share * Documents (PDF, Word, etc.) * Spreadsheets * Images * Code files * Text files ## Formatting Tips ### For Complex Requests Use structure to clarify complex requests: ``` I need help with a marketing email. Here are the details: **Product:** New project management feature **Audience:** Existing customers **Goal:** Announce the feature and drive adoption **Tone:** Excited but professional **Length:** About 300 words **Include:** Feature benefits, how to access it, support contact ``` ### For Multiple Items Use lists when asking for multiple things: ``` Please review this proposal and: 1. Check for logical consistency 2. Identify any gaps in the argument 3. Suggest improvements to the structure 4. Note any unclear sections ``` ## Conversation Best Practices Begin with a straightforward request. If the response isn't perfect, provide feedback and iterate. For unrelated topics, start a new conversation. This keeps context clear. Copy important outputs to your knowledge base or documents for future reference. Try different ways of asking. You'll learn what works best for different types of requests. ## Example Conversations ### Writing Help ``` You: I need to write a rejection email to a job candidate. It should be kind but clear, and encourage them to apply for future positions. AI: Here's a draft rejection email: Subject: Your Application to [Company Name] Dear [Name], Thank you for taking the time to interview for the [Position] role at [Company Name]... [continues with full email] You: Good, but can you make the opening warmer? AI: Here's a revised version with a warmer opening: Dear [Name], I really appreciate you sharing your experience and enthusiasm with us during the interview process... ``` ### Research ``` You: What are the main differences between PostgreSQL and MySQL for a new web application project? AI: Here's a comparison of PostgreSQL vs MySQL for web applications: **PostgreSQL** - Better for complex queries and large datasets - Stronger JSON support - More standards-compliant ... **MySQL** - Generally faster for simple read operations - Easier to set up and manage - Better hosting support ... You: We'll have a lot of JSON data. Tell me more about PostgreSQL's JSON support. AI: PostgreSQL has excellent JSON capabilities... ``` ## Troubleshooting * Try rephrasing more simply * Break complex requests into smaller parts * Provide more context * Give an example of what you want * Specify desired length: "Keep it under 100 words" * Ask for more detail: "Can you expand on this?" * Request format: "Give me bullet points" or "Write a full paragraph" * Specify the tone: "Make it more casual" or "Write formally" * Give examples of the style you want * Mention the audience: "This is for C-level executives" ## Next Steps Explore everything AI coworkers can do. Create specialized AI assistants.