Overview
Chat is Wegent's core interaction feature that allows you to have real-time conversations with AI agents to complete various tasks.
π Core Conceptsβ
Chat Tasksβ
A Chat Task is the basic unit of the Chat feature. Every interaction with AI creates a task:
- Single-turn: Simple one-time Q&A
- Multi-turn: Continuous contextual conversation
- Code Task: Programming tasks related to code repositories
Chat Modesβ
Wegent provides multiple conversation modes for different scenarios:
| Mode | Description | Use Case |
|---|---|---|
| Clarification | AI asks questions to clarify requirements | Complex tasks with unclear requirements |
| Correction | AI suggests modifications | Code review, document optimization |
| Direct Execution | AI executes tasks immediately | Simple tasks with clear requirements |
π― Main Featuresβ
1. Task Managementβ
Centralized management of all chat tasks:
- View conversation history list
- Filter by status (in progress, completed, failed)
- Search and archive tasks
- Export conversation records
2. Multi-Agent Collaborationβ
Support for various collaboration methods:
- Single Agent: One-on-one conversation with one agent
- Group Chat: Multiple agents participating in discussions
- Team Mode: Agents collaborate with assigned roles
3. Code Tasksβ
Enhanced features designed for programming:
- Automatic code repository cloning
- Agents read and analyze code
- Execute code modifications and commits
- Real-time execution monitoring
4. Conversation Controlβ
Flexible conversation control options:
- Pause/resume conversation
- Regenerate responses
- Modify context
- Switch agents
π Documentation Navigationβ
| Document | Description |
|---|---|
| Managing Tasks | Creating and managing chat tasks |
| Clarification Mode | Using clarification mode to clarify requirements |
| Correction Mode | Using correction mode to optimize results |
π Quick Startβ
Create Your First Conversationβ
- Navigate to the Chat page
- Click New Conversation
- Select an agent or agent team
- Enter your question or task description
- Wait for AI response
Create a Code Taskβ
- Click New Task
- Select a programming-type agent
- Select a code repository
- Describe the task to complete
- AI will automatically clone the repository and start working
π‘ Use Casesβ
Programming Assistanceβ
- Code Review: Have AI check code quality and potential issues
- Bug Fixing: Describe the problem, let AI locate and fix it
- Feature Development: Describe requirements, let AI implement new features
- Code Explanation: Have AI explain complex code logic
Content Creationβ
- Documentation Writing: Have AI help write technical documents
- Content Polishing: Optimize existing content expression
- Translation Services: Multi-language content translation
Knowledge Q&Aβ
- Technical Consulting: Ask technical questions and best practices
- Concept Explanation: Understand complex technical concepts
- Solution Design: Discuss system architecture and design solutions
π Related Resourcesβ
- Agent Settings - Configure agents
- Configuring Models - Set up AI models
- Feed Overview - Automated task execution