By continuing to visit this website, you agree to our privacy policy and use of cookies.

AI Assistants

Control generative AI customer experiences

Proto’s AICX Platform delivers multilingual customer support automation with its AI Assistants module for AI training, API integration, and more.

Auto-training on websites and documents

Instantly train AI with new information from URLs or documents, keeping responses up-to-date and relevant.

Customised AI assistants

Combine the best of traditional chatbot capabilities with modern LLMs, allowing you to create multiple assistants tailored to your brand voice and customer service guidelines, delivering personable interactions.

LLM-powered AI assistants

Leverage generative AI for powerful conversations. Third-party LLMs from providers like OpenAI and Anthropic can be optionally integrated into any assistant to enhance its capabilities.

Multi-channel deployment

Deploy your assistants across a variety of channels and platforms, including webchat, WhatsApp, and Facebook Messenger among others.

Multilingual capabilities

Set up assistants in a host of languages, as required by your location and customer preferences.

Proactive messaging

Engage website visitors with a proactive popup message triggered by custom page-based rules or API.

Central Bank of the Philippines

The multilingual Proto chatbot empowers consumers by providing an accessible channel for complaints, supporting the central bank’s commitment to financial service innovation.

Benjamin E. Diokno

Governor, Central Bank of the Philippines

See case study

Custom actions

Create scripted chat flows by designing custom triggers and actions. From simple, automated responses to complex API integrations, easily build and visualize your assistant's decision tree.

Chat memory

Use chat variables to store information from a chat session, including data about the app, user, and any inputs during the interaction. Utilise these variables in an AI assistant's subsequent actions.

Automatic ticket creation

Create tickets automatically, leveraging info collected from chats to auto-populate and auto-assign the new cases.

API actions

Supercharge your AI assistant with API calls, allowing it to send custom requests to external systems and receive responses.

User intervention

Enable your live reps to seamlessly intervene in assistant-led conversations, ensuring human touch in critical situations for elevated customer service.

AI Assistants FAQ

Can I edit the training data at any time?

You can sync the AI assistant with any URLs and upload various documents, including PDFs, json, tables, and chat transcripts. Training sources can be deleted, edited, and added at any time.

Can I see the AI assistant chat history and accuracy?

Proto's AI assistants provide accuracy close to 100% when trained with sufficient data sources such as websites and documents. For example, if a query is about a promotion that the assistant was not trained on, the assistant will respond generally but not specifically. You can access all chat history within the AI assistant and identify questions it could not answer, giving you ideas for further training data and intents.

Can I set up prompts to direct the AI assistant on how to behave?

Yes, Proto allows you to adapt prompts and behaviour for LLM-powered assistants. You can also use intents to set up dialogue flows. For example, AI assistants can use branch logic and JSON APIs to conduct a refund dialogue.

Can Proto's AI assistants handle complex queries?

Yes, Proto uses large language models (LLMs) to understand and craft relevant responses for any type of query, considering the context and material used to trained the assistant such as websites and PDFs.

Can the AI assistant be trained to correct its answers?

Yes, you can monitor the chats handled by the AI assistant and modify the data the assistant was trained on. You can also adjust the prompts to control the AI assistant's behaviour and re-training.

Can the AI assistants be customised?

Proto AI assistants can be fully customised. You can train your AI assistants on any content available, such as websites, knowledge bases, or documents. Additionally, you can modify prompts to control the behaviour and tone of the assistant, or set up specific rules for particular requests specific to types of audiences.

Does Proto support hybrid conversation design on top of generative AI?

Yes, you can train your assistant with your content and build structured conversation flows for specific use cases such as complaint intake, account setups and service bookings.

What AI models are used by Proto AI assistants?

Proto AICX Platform AI assistants leverage a combination of ChatGPT for common languages and Proto's proprietary ProtoAI™ natural language processing (NLP) engine for local and mixed languages. This ensures high accuracy and response speed for all markets. In terms of privacy, this also allows you to specify which information will be processed by ChatGPT and limit actions such as personal information collection to ProtoAI™ only.

What AI models do the AI assistants use?

Proto AICX Platform AI assistants leverage a combination of LLMs for common languages and Proto's proprietary ProtoAI natural language processing (NLP) engine for local and mixed languages. This ensures high accuracy and response speed for all markets. In terms of privacy, this also allows you to specify which information will be processed by LLMs and limit actions such as personal information collection to ProtoAI only.