Extract lead details during chatbot conversations

When a new lead is captured in chat via help247.ai, automatically run the conversation text through Token Metrics to classify intent and extract key contact metadata.

Try:

See all help247.ai + Token Metrics integrations or talk to a human

Trusted by teams already building on Knit·

4.9/5 on G2·

Google for Startups Accelerator

How Knit builds this workflow

The Agent researches both APIs and wires the trigger on one side to the action on the other — no pre-built connector required. Here is the vocabulary it has to work with.

help247.ai Explore help247.ai →

Triggers

New conversation started

Fires when a new chat or conversation begins in help247.ai.

Lead captured in chat

Fires when help247.ai captures a lead during a conversation.

Conversation handed off

Fires when help247.ai escalates a conversation to a human.

Actions

Send a message

Sends a message to a user through help247.ai.

Generate an answer

Asks help247.ai a question against its knowledge base and returns the answer.

Summarize a conversation

Uses help247.ai to summarize a chat transcript.

Create a ticket from a chat

Opens a support ticket from an help247.ai conversation.

Token Metrics Explore Token Metrics →

Triggers

New completion generated

Fires when Token Metrics generates a response to a prompt.

Model run failed

Fires when a request to Token Metrics errors or times out.

Fine-tune job completed

Fires when a fine-tuning job in Token Metrics finishes.

Actions

Generate a completion

Sends a prompt to Token Metrics and returns the model's response.

Summarize text

Uses Token Metrics to summarize a block of text.

Classify or extract data

Uses Token Metrics to classify or extract structured data from text.

Send custom completions back to chat visitors When a conversation starts in help247.ai, generate a completion in Token Metrics and send a tailored message directly back to the visitor. See details

Alert support agents when model fine-tuning completes When a fine-tune job completes in Token Metrics, automatically send a message through help247.ai to notify AI administrators that the updated model is ready. See details

See all help247.ai + Token Metrics integrations → · Browse the full workflow library →

Enterprise-grade security

Visit our Security Center Review the DPA

FAQ

Common questions

Can Knit build “Extract lead details during chatbot conversations” between help247.ai and Token Metrics?

Yes — describe it in the box above and Knit's Integrations Agent researches help247.ai and Token Metrics's public API docs (or your own uploaded docs) and builds a working workflow, whether or not either app already has a pre-built connector.

How long does it take to build?

Minutes to a first working version, not weeks — you test it against real data before it goes anywhere near production.

How does connecting help247.ai to Token Metrics expand chatbot capabilities?

Connecting help247.ai to Token Metrics allows your chatbot to tap into advanced AI models for deeper context, sentiment classification, and sophisticated text generation beyond standard scripted responses.

Can help247.ai notify operators if a backend model process encounters an issue in Token Metrics?

Yes, when a model run fails in Token Metrics, you can send an automated message or alert through help247.ai to notify system administrators.