AI agent

An AI that answers from your content, not the open internet

The agent is grounded in a knowledge base you supply — your product docs, policies, price lists, and FAQs. It retrieves the relevant passage and answers from it, which is what keeps replies specific to your business instead of plausible-sounding generic text.

When a question falls outside what it can answer, or the customer asks for a person, the conversation hands off to a human in the shared inbox with the full thread intact.

Bring your own key, or use the included allowance

You can point the agent at your own LLM API key, or use the allowance included with your plan. Bring-your-own-key means model spend sits with your provider account and you keep direct control over it.

Platform AI starts on Growth. Free, Starter, and Pro do not include it — those plans still run the rule-based journey builder and shared inbox.

FAQ

Can I put ChatGPT-style AI on my WhatsApp?

Yes. The AI agent answers customers on WhatsApp using a large language model grounded in your own knowledge base, with handoff to a human when needed.

Does the AI answer from my own documents?

Yes — it uses retrieval-augmented generation (RAG) over a knowledge base you provide, so answers come from your content rather than general model knowledge.

Can I use my own OpenAI or LLM key?

Yes. The agent supports bring-your-own-key configurations alongside the allowance included with your plan.

Which plan do I need for the AI agent?

Platform AI starts on Growth (₹3,999). Free, Starter, and Pro do not include platform AI.

What happens when the AI cannot answer?

It hands the conversation off to a human agent in the shared inbox, carrying the full thread across so the customer does not repeat themselves.

Related