Using Aymo AI
Learn how to work inside Aymo using chats, prompts, model switching, file workflows, and response tools. Build efficient multi-model workflows with ease.
This section explains how to begin working inside Aymo, including starting a chat, selecting models, uploading files, using fast models, understanding model tiers, and managing chats.
First Chat
A new chat can be created from the sidebar or dashboard.
Enter a prompt, upload or drag and drop a file, select an AI model, and optionally enable enhancement tools before sending a message.
Aymo supports long prompts, structured inputs, code snippets, uploaded files, and multi-step instructions. Each chat is saved automatically and appears in the recent chats list.
Switching Models
The model selector below the chat composer allows switching between Light, Pro, and Max models at any time. Switching models changes how responses are generated and can be used to compare:
- Reasoning capabilities
- Coding performance
- Writing style
- Response speed
- Usage limits and model availability
Model switching is instant and does not require starting a new chat.
Uploading and Parsing Files
Files can be uploaded using the attachment button next to the message field.
Supported formats include:
- PDFs
- Documents
- Spreadsheets
- Code files
- Text files
Aymo can:
- Summarize documents
- Extract insights
- Analyze data
- Understand code
- Provide context for multi-step tasks
Uploaded files remain attached to the current thread.
Using Max Models
Max models are optimized for advanced reasoning, research, coding, and high-accuracy tasks.
Examples include:
- GPT-5.5
- Claude Opus 4.8
- Claude Sonnet 4.6
- Gemini 3.1 Pro
- Qwen3.7-Max
Max models are suitable for:
- Complex reasoning
- Research and analysis
- Advanced coding tasks
- Long-form content creation
- High-accuracy responses
They prioritize capabilities, reasoning quality, and output quality for demanding workloads.
Understanding Model Tiers
Models in Aymo are organized into several tiers:
- Max models: GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro, Qwen3.7-Max, and others
- Pro models: GPT-5.4 Mini, Gemini 3.5 Flash, and others
- Light models: GPT-5 Nano, Llama 4 Maverick, Mistral Nemo, and others
- Specialized models: DeepSeek, Kimi, MiMo, Perplexity Sonar, and others
- BYOK: Available on Business plans, allowing access to supported provider models using connected API keys.
Each tier provides different strengths in reasoning, speed, capabilities, and usage limits.
Selecting the appropriate tier helps balance performance, cost, and workflow requirements.
Basic Prompting
Aymo supports a wide range of prompt formats. Effective prompts include:
- Clear instructions
- Desired output style
- Examples when needed
- Structured inputs for complex tasks
Prompts can include text, code, lists, tables, or uploaded files. Aymo interprets context and generates responses aligned with the given instructions.
Thread Management
Chats can be organized for clean and consistent workflows.
Supported actions include:
- Rename chat threads
- Duplicate threads
- Move threads to projects
- Archive or remove threads
- Pin important responses for quick access
Thread management keeps long-term work structured and easy to revisit.
Aymo provides a flexible multi-model environment that supports writing, coding, planning, research, and analysis within a simple, streamlined interface.