Get to Know Your AI Agent Engine
Last updated
Last updated
AI Agent Engine is designed to comprehend and respond instantly to highly specific questions using a combination of advanced natural language processing (NLP) and generative AI capabilities. It utilizes large language models (LLMs) for flexibility and efficiency, ensuring effective communication with users while maintaining brand control.
The user initiates the conversation by sending a message.
Our platform employs vigilant moderation for 11 categories of inappropriate inputs, including those related to violence, harassment, and hate speech.
Our platform analyzes the user intent and directs the message to one of four possible response types:
Answers that are generated by the LLM model using data from your website, documents, or feeds.
Generated Responses will be moderated for offensive language and hallucinations.
Prewritten answers are written in advance by you and surfaced to the user exactly as written.
Prewritten answers take precedence over generated responses.
For intents that require a live agent, users can escalate their conversation to a live chat agent, which routes directly to your Live Escalation Platform (our default is Bridge Live Chat).
Security Alerts
When offensive content is flagged, you can provide a custom-prewritten answer or a silent response.
In the event that a direct threat is detected, the system triggers an email alert to your chat's admins.
Both Generated and Prewritten Responses can have enrichments like buttons, quick replies, images, and videos.
Generated Responses can be enriched with actionable items (buttons, quick replies, images) through the request portal.
Prewritten Responses can be enriched with actionable items (buttons, quick replies, images, gifs, and videos) directly in the response editor.
The response is sent to the user.
