> ## Documentation Index > Fetch the complete documentation index at: https://utoken-docs.yoostudio.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # WorkBuddy > Guide to Integrating UToken with Tencent WorkBuddy ## Overview **WorkBuddy** is Tencent's all-scenario workplace AI agent desktop workstation. Users simply describe their requirements in natural language, and WorkBuddy autonomously plans and executes tasks, delivering ready-to-use artifacts such as documents, spreadsheets, presentations, and research reports. Unlike traditional AI chat tools, WorkBuddy goes beyond answering questions — it can: * Autonomously decompose complex tasks * Operate local files * Invoke Skills * Call MCP services * Connect to enterprise knowledge bases and office systems * Execute multi-step workflows and deliver results With UToken, you can use a single unified API Key within WorkBuddy to invoke 100+ mainstream models — including Claude, GPT, Gemini, Qwen, DeepSeek, Kimi, and GLM — while benefiting from unified billing, automatic failover, and enterprise-grade reliability. *** # Quick Integration ## 1. Navigate to Model Configuration 1. Open WorkBuddy 2. Click your avatar in the bottom-left corner 3. Go to: ```text theme={null} Settings └── Model Configuration ``` Model Provider 4. On the Model Management page, click: ```text theme={null} Add Model ``` WorkBuddy supports: * OpenAI Compatible API * Tencent Cloud Token Plan * Coding Plan * Ollama (local models) * Custom API *** ## 2. Create a Custom Model Select: ```text theme={null} Custom API ``` Fill in the following parameters: | Field | Value | | -------------- | ---------------------------------------------------------------- | | Model Name | gpt-5.5 | | API Key | sk-xxxxxxxx | | Base URL | [https://utoken.yoostudio.ai/v1](https://utoken.yoostudio.ai/v1) | | Model | gpt-5.5 | | Tool Calling | Enabled | | Vision Support | Enable based on model capability | Example: ```yaml theme={null} provider: custom base_url: https://utoken.yoostudio.ai/v1 api_key: sk-xxxxxxxx model: gpt-5.5 ``` Model Provider *** ## 3. Recommended Model Configuration | Use Case | Recommended Model | | ------------------------ | ----------------- | | Daily office tasks | gemini-3.5-flash | | In-depth research | claude-opus-4-7 | | Long-form analysis | claude-opus-4-7 | | Data analysis | gpt-5.5 | | Presentation generation | gpt-5.5 | | Code development | qwen3-coder-plus | | Multimodal understanding | gemini-3.5-flash | | Agent tasks | claude-opus-4-7 | *** ## 4. Auto Mode WorkBuddy provides an: ```text theme={null} Auto ``` mode. It is recommended to specify a model explicitly in production environments to avoid result variance caused by automatic model switching across different tasks. *** # Core Capabilities ## 1. AI Office Assistant Most common usage: ```text theme={null} Generate my weekly work summary Output requirements: 1. Work accomplishments 2. Risks and issues 3. Plan for next week Keep within 1000 words ``` Recommended models: ```text theme={null} gpt-5.5 claude-opus-4-7 ``` *** ## 2. In-Depth Research WorkBuddy can autonomously: ```text theme={null} Search for information → Read web pages → Organize findings → Output a research report ``` Example: ```text theme={null} Research the current landscape of global AI Coding products Focus on: - Cursor - Claude Code - Gemini CLI - OpenAI Codex Output: Market analysis report ``` Recommended model: ```text theme={null} claude-opus-4-7 ``` *** ## 3. Data Analysis Upload: ```text theme={null} Excel CSV Database export files ``` Example: ```text theme={null} Analyze this sales dataset Output: 1. Monthly trends 2. Top 10 customers 3. Risk alerts 4. Charts ``` Recommended models: ```text theme={null} gpt-5.5 gemini-3.5-flash ``` *** ## 4. Automated Presentation Generation Input: ```text theme={null} Generate a presentation titled: "2026 AI Industry Development Trends" 15 slides Target audience: executive leadership ``` WorkBuddy automatically handles: ```text theme={null} Content planning → Slide design → Chart generation → PPT export ``` *** ## 5. Local File Processing WorkBuddy can read from authorized directories: ```text theme={null} Documents Downloads Projects ``` Example: ```text theme={null} Organize the Downloads directory Requirements: - Archive images - Archive PDFs - Archive compressed files - Delete duplicate files ``` *** # Skills and MCP ## 1. Skills WorkBuddy supports capability extension via Skills. Commonly used skills: ```text theme={null} Web Search Local Whisper Office Tools Browser Agent Obsidian SkillHub ``` Usage example: ```text theme={null} Use the Web Search skill Aggregate today's AI industry news Generate a daily briefing ``` *** ## 2. MCP Integration Supported integrations: ```text theme={null} GitHub Notion Jira Linear Slack Google Drive Enterprise internal systems ``` Example: ```text theme={null} Fetch this week's Jira tasks Output: Project risk analysis ``` *** ## 3. Enterprise Knowledge Base Supported sources: ```text theme={null} Tencent Docs IMA Knowledge Base Lexiang Knowledge Base Custom MCP knowledge base ``` Example: ```text theme={null} Answer employee questions based on company policies ``` *** # Use Case Examples ## Intelligent Operations ```yaml theme={null} Task: Aggregate industry news Pipeline: 1. Search for news 2. Categorize and organize 3. Generate daily briefing 4. Output as Markdown Model: gemini-3.5-flash ``` *** ## Market Research ```yaml theme={null} Task: AI Agent market research Pipeline: 1. Search for competing products 2. Collect information 3. SWOT analysis 4. Compile report Model: claude-opus-4-7 ``` *** ## Development Assistant ```yaml theme={null} Task: Refactor project codebase Capabilities: - Code comprehension - Bug fixing - Unit testing - Documentation generation Model: qwen3-coder-plus ``` *** # Best Practices ## 1. Use Structured Task Descriptions Recommended format: ```text theme={null} Objective: Generate a market analysis report Input: Upload industry materials Output: Markdown format Requirements: - Data accuracy - Minimum 5000 words - Include charts ``` *** ## 2. Model Selection Strategy ```yaml theme={null} Fast tasks: model: gemini-3.5-flash Complex reasoning: model: claude-opus-4-7 Code development: model: qwen3-coder-plus Data analysis: model: gpt-5.5 ``` *** ## 3. Principle of Least Privilege for File Access Recommendation: ```text theme={null} Grant access only to necessary directories ``` Avoid granting access to the entire disk. *** ## 4. Enable Skills On-Demand Recommendation: ```text theme={null} Install only the Skills you need Reduces context pollution Improves execution efficiency ``` *** # Troubleshooting ## Invalid API Key Check: ```text theme={null} Whether the API Key is correct Whether the account balance is sufficient ``` *** ## Model Not Found Check: ```text theme={null} Whether the model name is the canonical identifier Examples of correct values: gpt-5.5 claude-opus-4-7 Do NOT use: GPT 5.5 Claude Opus ``` *** ## Tool Calling Failure Check: ```text theme={null} Whether Tool Calling is enabled Whether the model supports Function Calling ``` *** ## Slow Response Recommendation: ```yaml theme={null} model: gemini-3.5-flash max_tokens: 2000 ``` Also reduce the number of attachments. *** # Security Recommendations ## API Key Management Do NOT: ```text theme={null} Hardcode keys in shared configuration files ``` Recommended: ```text theme={null} Environment variables Secret Manager ``` *** ## Access Control Recommendation: ```text theme={null} Grant access only to working directories Avoid access to system directories ``` *** ## Enterprise Deployment Recommended: ```text theme={null} Centralized UToken gateway Unified audit logging Unified billing Unified access control ``` ***