Frequently Asked Questions
Find answers to the most frequently asked questions here. If you can't find what you're looking for, you can contact us.
Global Pozitif AI Platform is a cloud-based AI assistant (SaaS) platform that automates the communication traffic of enterprise businesses on email and web channels using Gemini and GPT models. The email assistant securely connects to your IMAP/SMTP servers to automatically draft replies or respond directly; the web assistant engages visitors 24/7 via a smart widget embedded in your site, routing them to WhatsApp or support teams when necessary.
No, our platform is designed to be managed without any technical knowledge. To integrate your email assistant, you only need to enter your email account details (IMAP and SMTP address/port) and run the connection test. For the web assistant, simply copy and paste the single-line JavaScript code we provide into your site's template. All other AI routing, model selection, temperature, and persona definitions are configured via visual panels.
Our platform supports a multi-model architecture. Currently, Google Gemini (Gemini 2.0 Flash and Gemini 2.5 Pro) and OpenAI GPT (GPT-4o, GPT-4o mini, and GPT-5 mini) models are ready to use. You can select a different AI model for each assistant based on task complexity and budget. Token consumptions are deducted from your unified credit pool according to model multipliers (e.g., Gemini 2.0 Flash 1.0x, GPT-4o 10.0x).
Yes! All newly registered companies are automatically assigned a Free Plan without requiring credit card information. Under the free plan, you receive trial credits to test all platform modules (Email assistant, Web assistant, AI Functions, API Connectors) within certain limits. When you reach your limits during the trial, operations are paused and no data is processed until you upgrade to a higher plan.
Yes, data security is our top priority. Email passwords are encrypted using the AES-256-GCM standard. Thanks to the multi-tenant structure, each company's data is completely isolated — no company can access another's data. The platform operates in compliance with GDPR, and all communications occur over encrypted channels.
Yes. Your web assistants are equipped to analyze the content of web pages on demand. Our AI engine examines the main body content, heading structure (H1-H6), meta titles and descriptions, keyword distribution, and readability scores to generate a detailed SEO and content quality report. Along with the report, it provides actionable optimization and content improvements to help push your pages higher in search engine result pages (SERPs).
The email assistant works with all email servers that support IMAP and SMTP protocols. You can use all standard email service providers including Gmail, Outlook, Yahoo Mail, Yandex Mail, and corporate mail servers (Exchange, Zimbra, etc.). SSL/TLS encrypted connections are supported.
No. Our chat widget JavaScript file loads asynchronously (async) on your website. This means it doesn't affect the loading of your site's visual elements or page speed. Once loaded, it only sends API requests in the background when the user clicks and opens the chat window. Our server responses are highly optimized.
Our web assistant supports 15 languages in total, including Turkish, English, German, French, and Spanish. Thanks to the automatic language detection feature, no matter what language the visitor writes in, the assistant detects it and continues to respond fluently in the same language. This allows you to serve your international clients in their local languages 24/7.
An assistant is the artificial intelligence agent that directly chats or communicates with the user via email or web widget. An AI function, on the other hand, is a tool in the hands of this assistant. For example, while an assistant on its own can only provide general information, when assigned a "query_stock" function, it can trigger this function to query the database when a customer asks about stock and return exact stock numbers to the client.
Credit is the unit of measurement for your AI usage on the platform. When an AI model processes a request, it consumes tokens. These tokens are converted into credits based on the selected model's multiplier. For example, in the GPT-5 mini model, 1000 tokens consume approximately 5 credits (5.0x multiplier). More powerful models have higher multipliers, consuming more credits but generating higher-quality responses.
Yes! In subscription plans with the credit rollover feature enabled, your unused credits at the end of the month are carried over to the next month. Carried over credits have an expiration date and become invalid if not used within a certain period. Details are specified in your subscription plan conditions.
Go to the Settings > Subscription section in your company panel. You will see your current plan and other plan options. Choose the plan you want to upgrade to and confirm the transaction. The plan upgrade takes effect instantly, and new limits are activated immediately. Your usage in the current period will be pro-rated for billing.
Global Pozitif AI Platform is a cloud-based AI assistant (SaaS) platform that automates the communication traffic of enterprise businesses on email and web channels using Gemini and GPT models. The email assistant securely connects to your IMAP/SMTP servers to automatically draft replies or respond directly; the web assistant engages visitors 24/7 via a smart widget embedded in your site, routing them to WhatsApp or support teams when necessary.
No, our platform is designed to be managed without any technical knowledge. To integrate your email assistant, you only need to enter your email account details (IMAP and SMTP address/port) and run the connection test. For the web assistant, simply copy and paste the single-line JavaScript code we provide into your site's template. All other AI routing, model selection, temperature, and persona definitions are configured via visual panels.
Our platform supports a multi-model architecture. Currently, Google Gemini (Gemini 2.0 Flash and Gemini 2.5 Pro) and OpenAI GPT (GPT-4o, GPT-4o mini, and GPT-5 mini) models are ready to use. You can select a different AI model for each assistant based on task complexity and budget. Token consumptions are deducted from your unified credit pool according to model multipliers (e.g., Gemini 2.0 Flash 1.0x, GPT-4o 10.0x).
Yes! All newly registered companies are automatically assigned a Free Plan without requiring credit card information. Under the free plan, you receive trial credits to test all platform modules (Email assistant, Web assistant, AI Functions, API Connectors) within certain limits. When you reach your limits during the trial, operations are paused and no data is processed until you upgrade to a higher plan.
Yes, data security is our top priority. Email passwords are encrypted using the AES-256-GCM standard. Thanks to the multi-tenant structure, each company's data is completely isolated — no company can access another's data. The platform operates in compliance with GDPR, and all communications occur over encrypted channels.
Yes. Your web assistants are equipped to analyze the content of web pages on demand. Our AI engine examines the main body content, heading structure (H1-H6), meta titles and descriptions, keyword distribution, and readability scores to generate a detailed SEO and content quality report. Along with the report, it provides actionable optimization and content improvements to help push your pages higher in search engine result pages (SERPs).
The email assistant works with all email servers that support IMAP and SMTP protocols. You can use all standard email service providers including Gmail, Outlook, Yahoo Mail, Yandex Mail, and corporate mail servers (Exchange, Zimbra, etc.). SSL/TLS encrypted connections are supported.
No. Our chat widget JavaScript file loads asynchronously (async) on your website. This means it doesn't affect the loading of your site's visual elements or page speed. Once loaded, it only sends API requests in the background when the user clicks and opens the chat window. Our server responses are highly optimized.
Our web assistant supports 15 languages in total, including Turkish, English, German, French, and Spanish. Thanks to the automatic language detection feature, no matter what language the visitor writes in, the assistant detects it and continues to respond fluently in the same language. This allows you to serve your international clients in their local languages 24/7.
An assistant is the artificial intelligence agent that directly chats or communicates with the user via email or web widget. An AI function, on the other hand, is a tool in the hands of this assistant. For example, while an assistant on its own can only provide general information, when assigned a "query_stock" function, it can trigger this function to query the database when a customer asks about stock and return exact stock numbers to the client.
Credit is the unit of measurement for your AI usage on the platform. When an AI model processes a request, it consumes tokens. These tokens are converted into credits based on the selected model's multiplier. For example, in the GPT-5 mini model, 1000 tokens consume approximately 5 credits (5.0x multiplier). More powerful models have higher multipliers, consuming more credits but generating higher-quality responses.
Yes! In subscription plans with the credit rollover feature enabled, your unused credits at the end of the month are carried over to the next month. Carried over credits have an expiration date and become invalid if not used within a certain period. Details are specified in your subscription plan conditions.
Go to the Settings > Subscription section in your company panel. You will see your current plan and other plan options. Choose the plan you want to upgrade to and confirm the transaction. The plan upgrade takes effect instantly, and new limits are activated immediately. Your usage in the current period will be pro-rated for billing.
Still not resolved?
Our support team is ready to help. Contact us and we'll get back to you as soon as possible.