# AI Capabilities Source: https://docs.trilo.chat/ai-coworkers/ai-capabilities Explore the full range of what AI coworkers can do for you AI coworkers in Trilo are capable of helping with a wide variety of tasks. This guide covers their key capabilities and how to make the most of them. ## Writing & Content ### Drafting Content AI coworkers can write many types of content: * **Emails**: Professional correspondence, follow-ups, announcements * **Documents**: Reports, proposals, specifications * **Messages**: Slack messages, announcements, updates * **Social media**: Posts, threads, captions * **Marketing**: Copy, taglines, descriptions **Example:** ``` "Write a product announcement email for our new analytics dashboard. Target audience is existing customers. Include the main features: real-time data, custom reports, and mobile access." ``` ### Editing & Improving Get help polishing your writing: * Fix grammar and spelling * Improve clarity and flow * Adjust tone and style * Simplify complex content * Expand on ideas **Example:** ``` "Review this email and improve the clarity. Keep the professional tone but make it more concise." ``` ### Summarizing Condense long content into key points: * Summarize documents and articles * Extract main ideas * Create executive summaries * Generate TL;DR versions **Example:** ``` "Summarize this 20-page report into a one-page executive summary highlighting the key findings and recommendations." ``` ## Research & Analysis ### Information Retrieval Get answers to questions: * Explain concepts and terms * Compare options and alternatives * Provide background information * Answer technical questions **Example:** ``` "What are the main differences between microservices and monolithic architecture? Include pros and cons of each." ``` ### Data Analysis Help with understanding data: * Identify patterns and trends * Explain what data means * Suggest insights * Create interpretations **Example:** ``` "Here's our monthly sales data [attachment]. What trends do you see and what might be causing the Q3 dip?" ``` ### Competitive Research Gather competitive intelligence: * Compare features and capabilities * Identify differentiators * Research market positioning * Analyze competitor content **Example:** ``` "Based on our product features, what would be our key differentiators compared to competitors like X and Y?" ``` ## Tasks & Productivity ### Task Creation AI coworkers can create tasks from conversations: ``` "Create a task to review the Q3 marketing budget. Set it as high priority with a due date of next Friday." ``` ### Task Management AI can help manage your tasks: * Suggest task breakdowns * Recommend priorities * Identify dependencies * Create project plans **Example:** ``` "I need to launch a new feature by March 1st. Help me break this down into tasks and milestones." ``` ### Meeting Preparation Get ready for meetings: * Create agendas * Draft talking points * Prepare questions * Summarize background information **Example:** ``` "I have a client meeting tomorrow about their mobile app project. Create an agenda and list of discussion points based on their requirements document [attachment]." ``` ## Creative & Brainstorming ### Idea Generation Generate ideas and options: * Brainstorm solutions to problems * Generate name ideas * Create taglines and slogans * Explore different approaches **Example:** ``` "Brainstorm 10 names for our new project management feature. It helps teams track progress visually." ``` ### Problem Solving Work through challenges: * Analyze problems from multiple angles * Suggest potential solutions * Identify risks and considerations * Evaluate trade-offs **Example:** ``` "Our user onboarding completion rate is only 40%. What might be causing this and how could we improve it?" ``` ## Technical Assistance ### Code Help Get programming assistance: * Explain code concepts * Debug issues * Suggest implementations * Review code logic **Example:** ``` "How would I implement pagination in a REST API using Node.js? Show me a basic example with query parameters." ``` ### Technical Writing Create technical content: * Documentation * API descriptions * Technical specifications * How-to guides **Example:** ``` "Write API documentation for an endpoint that creates a new user. Include request/response examples and error codes." ``` ## Image Generation ### Creating Images Some AI coworkers can generate images: * Illustrations and graphics * Concept visualizations * Social media images * Simple designs **Example:** ``` "Generate an illustration of a team collaborating around a virtual whiteboard, in a modern flat design style." ``` Image generation capabilities depend on which AI coworkers are configured in your workspace. ## Specialized Skills ### By AI Coworker Type Different AI coworkers have different strengths: | Coworker | Best For | | ----------------------- | ------------------------------------------ | | **Writing Assistant** | Content creation, editing, tone adjustment | | **Research Assistant** | Finding information, analysis, comparisons | | **Productivity Helper** | Task management, planning, organization | | **Software Assistant** | Code help, technical questions, debugging | | **Creative Assistant** | Brainstorming, creative writing, ideation | ### Choosing the Right Coworker Select based on your need: * Writing tasks → Writing Assistant * Technical questions → Software Assistant * Project planning → Productivity Helper * Creative work → Creative Assistant ## Capabilities by Context ### In Chat * Real-time conversation * Multi-turn discussions * File analysis * Content generation ### With Tasks * Task creation * Assignment (AI as assignee) * Task updates * Progress tracking ### With Knowledge Base * Document summarization * Content suggestions * Q\&A about resources * Draft creation ## Limitations ### What AI Coworkers Can't Do Be aware of limitations: * **No real-time internet access**: Can't browse live websites * **Knowledge cutoffs**: Information has a training date * **Subjective judgment**: May not understand nuanced context * **Verification needed**: Outputs should be reviewed * **No system access**: Can't access your files directly (unless attached) ### When to Use Human Judgment * Final decisions on strategy * Sensitive communications * Legal or compliance matters * Complex interpersonal situations * Critical business decisions ## Getting Better Results ### Tips for Better Outputs Show examples of what you want. "Write it like this example: \[example]" Tell the AI how to structure output. "Use bullet points" or "Create a table" Add limits. "Keep it under 200 words" or "Use simple language" Specify who will read it. "This is for technical developers" or "For executive stakeholders" Refine through conversation. "Make it more formal" or "Add more detail to section 2" ### Quality Review Always review AI outputs: * Check factual accuracy * Verify tone is appropriate * Ensure completeness * Confirm it meets your needs * Add personal touches ## Next Steps Create AI coworkers tailored to your needs. Master AI conversation techniques. # Chatting with AI Source: https://docs.trilo.chat/ai-coworkers/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. # Custom AI Coworkers Source: https://docs.trilo.chat/ai-coworkers/custom-coworkers Create AI assistants tailored to your team's specific needs While Trilo provides built-in AI coworkers, you can create custom AI coworkers that are specialized for your team's unique needs. Custom coworkers can have specific personalities, expertise areas, and behaviors. ## Why Create Custom Coworkers? Custom AI coworkers let you: * Match your brand voice and tone * Specialize in your domain knowledge * Create consistent responses for your use cases * Define specific behaviors and constraints * Build AI that understands your context ## Creating a Custom Coworker ### Getting Started Navigate to the **AI Coworkers** section in settings. Click **Create AI Coworker** or **+ New**. Set up name, avatar, and description. Write instructions for how the AI should behave. Save your custom coworker. It's now available to your team. ### Basic Settings #### Name Choose a clear, memorable name: * Reflects the coworker's purpose * Easy to identify in lists * Professional and appropriate **Examples:** * "Brand Voice Editor" * "Customer Support Assistant" * "Technical Documentation Helper" #### Avatar Set a visual identity: * Upload a custom image * Use generated avatars * Choose colors that fit your brand #### Description Write a brief description that helps users understand: * What this coworker does * When to use it * Its areas of expertise **Example:** ``` Helps write customer-facing communications in our brand voice. Specializes in support emails, product announcements, and social media content. ``` ## Defining Behavior ### Base Prompt The base prompt tells the AI how to behave. This is the most important configuration. **Structure your prompt to include:** 1. **Role definition**: Who is this AI? 2. **Expertise**: What does it know? 3. **Tone and style**: How should it communicate? 4. **Guidelines**: Rules it should follow 5. **Constraints**: What it should avoid ### Example Base Prompt ``` You are a Customer Support Assistant for Acme Corp. **Role:** Help team members draft responses to customer inquiries, ensuring consistent and helpful communication. **Expertise:** - Product knowledge for Acme's software suite - Common customer issues and solutions - Support best practices **Tone:** - Friendly and professional - Empathetic to customer concerns - Clear and concise - Solution-oriented **Guidelines:** - Always acknowledge the customer's concern first - Provide clear next steps - Offer additional resources when relevant - End with a helpful closing **Avoid:** - Technical jargon customers won't understand - Blaming the customer - Making promises we can't keep - Sharing internal processes ``` ### Writing Effective Prompts Vague instructions lead to inconsistent results. Clearly state what you want. Show the AI what good output looks like. ``` Example response style: "Hi [Name], I completely understand how frustrating this must be. Let me help you resolve this right away..." ``` Tell the AI what NOT to do as clearly as what to do. After creating, test with real scenarios. Adjust the prompt based on results. ## Advanced Configuration ### Skills and Capabilities Enable or configure specific capabilities: | Capability | Description | | --------------------- | ------------------------------------------ | | **Task Creation** | Can create tasks from conversations | | **Image Generation** | Can generate images (if available) | | **Document Analysis** | Can process uploaded files | | **Web Search** | Can search for information (if configured) | ### Temperature Setting Control how creative vs. consistent the AI is: * **Lower (0.1-0.3)**: More consistent, focused responses * **Medium (0.5-0.7)**: Balanced creativity and consistency * **Higher (0.8-1.0)**: More creative, varied responses **When to adjust:** * Support responses: Lower temperature for consistency * Creative writing: Higher temperature for variety * Technical answers: Lower temperature for accuracy ### Token Limits Set maximum response length: * Shorter limits for concise answers * Longer limits for detailed content * Balance between thoroughness and brevity ## Use Case Examples ### Customer Support Assistant ``` **Name:** Support Helper **Description:** Drafts customer support responses following our guidelines and tone. **Base Prompt:** You help draft customer support emails. Follow these principles: - Always empathize first - Provide clear solutions - Use simple, jargon-free language - Include relevant help center links - Sign off warmly Avoid: defensive language, technical terms, acknowledging bugs not yet announced publicly. ``` ### Content Editor ``` **Name:** Brand Voice Editor **Description:** Reviews and edits content to match our brand voice and style guide. **Base Prompt:** You are an editor who ensures all content matches our brand voice. Our voice is: - Confident but not arrogant - Friendly and approachable - Clear and concise - Optimistic and helpful When reviewing content: 1. Check for brand voice alignment 2. Suggest specific improvements 3. Flag any issues 4. Provide the edited version ``` ### Onboarding Guide ``` **Name:** Onboarding Buddy **Description:** Helps new team members learn our processes and tools. **Base Prompt:** You help new team members get up to speed. You're friendly, patient, and thorough. Knowledge areas: - Company tools and how to use them - Team processes and workflows - Where to find documentation - Who to ask for what Always: - Welcome questions, no matter how basic - Point to relevant resources - Suggest logical next steps - Encourage asking follow-up questions ``` ## Managing Custom Coworkers ### Editing To update a custom coworker: 1. Go to AI Coworkers in settings 2. Find your custom coworker 3. Click **Edit** 4. Make changes 5. Save Changes apply to new conversations. ### Duplicating Create variations based on existing coworkers: 1. Find the coworker to copy 2. Click **Duplicate** 3. Modify as needed 4. Save with a new name ### Deleting Remove coworkers no longer needed: 1. Find the coworker 2. Click **Delete** 3. Confirm deletion Deleting a custom coworker removes it permanently. Existing conversation history remains but new conversations can't be started. ## Sharing Custom Coworkers ### Workspace Availability Custom coworkers can be available to: * **Entire workspace**: Everyone can use it * **Specific projects**: Only in certain projects * **Specific roles**: Only certain team members ### Permissions Control who can: * **Use**: Start conversations with the coworker * **Edit**: Modify the coworker's configuration * **Delete**: Remove the coworker ## Best Practices Begin with a basic configuration. Add complexity as you learn what works. Before rolling out, test with various scenarios to ensure consistent behavior. Ask team members how well the coworker performs. Use feedback to improve. Write clear descriptions so team members know when to use each coworker. Review and update coworkers as your needs evolve. Outdated prompts give outdated results. ## Troubleshooting * Make instructions more explicit * Add examples of correct behavior * Remove conflicting guidelines * Test with the prompt to refine * Lower the temperature setting * Be more specific in the prompt * Add constraints and boundaries * Include more examples * Add instruction: "Be concise" * Set lower token limits * Specify desired response length * Include examples of ideal length ## Next Steps Explore what AI coworkers can do. Learn effective AI communication. # AI Coworkers Overview Source: https://docs.trilo.chat/ai-coworkers/overview Work alongside intelligent AI assistants that help you get more done AI Coworkers are intelligent assistants built into Trilo that can help you with a wide range of tasks. From drafting content to analyzing data, these AI team members are ready to assist whenever you need them.