User Manual – AI SuperAgent App

Welcome! This app unifies several AI models (like Gemini, Mistral, OpenAI, Claude, LLaMA) in one place. You can register API keys for each, use dictation, attach files, capture photos, and even request automatic internet searches. This guide explains all key features.

1. Application Overview

SuperAgent allows you to interact with different AI models via specialized agents (Medicine, Law, General). You can:

• Type or speak your questions
• Use automatic photo capture and AI image analysis
• Share results or send them via email
• Integrate web search summaries with AI responses

2. Access & Login

2.1 Registration

1. Enter a valid email and password
2. Click 📝 Register
3. Enter your name, city, state, and country
4. Optionally, provide API keys for internet search and AI models

2.2 Login

Enter your credentials and click 🔓 Login

2.3 Password Reset

Click 🔐 Forgot your password? to request a reset link.

3. Interface Overview (Tabs)

• Main: Ask questions, speak prompts, attach files, take photos
• Settings: Manage your profile, API keys, and model selection
• History: View and clear past prompts and answers
• About: Manuals, language settings, and privacy policy
• Logout: Ends the session and clears local data

4. Asking Questions (Main Tab)

4.1 Input Methods

• 📤 Submit via text or voice
• 🎙️ Enable dictation
• 🔊 Enable reading responses aloud
• 📎 Attach files to be analized: jpeg, jpg, png, pdf, plain, msword, mp4, webm, avi, excel, mpeg, wav, ogg, aac, flac, webm, mp4, m4a, opus
• 📷 Commands to take a picture: what are you seeing, what do you see, see something, take a picture, show what you see
• ✉️ Commands to send Email: send by email, email to me, send me an email
• ✉️ Commands to share: share
• 📅 Agenda-related commands: insert, list, remove, schedule, switch off

4.2 Smart Image Processing

• AI image analysis only triggers with words like "describe" or "analyze"
• Voice commands like "send email" or "share" trigger those actions directly

5. Settings Tab

• Manage name, location, email
• Set Internet Search API Key and Search Engine ID
• Select AI model and provide respective API key
• Remove saved API keys

6. History Tab

Review or clear past interactions.

7. About Tab

• Access this manual
• Select dictation language
• View Privacy Policy

8. Dictation & Speech Features

• Supports multiple languages
• Automatic pause during AI speaking

9. Image + AI Capabilities

• Captures and analyzes photos via camera
• Shares or emails image + AI response if requested

10. Troubleshooting

• API Key Errors: Check key validity
• No Internet Results: Verify search key + engine ID
• Camera Not Opening: Check permissions
• Audio Issues: Check volume / TTS settings

11. Security Notes

API keys and user data are encrypted. The app does not share your data with third parties.

📧 Support: support@olhovivo.app.br
🌐 Site: https://olhovivo.app.br

🔙 Back to Application