Platform
Solutions
Integrations
Case studies
Resources
Pricing Start free Request a demo Log in
API and AI agents

Headless conversation analytics. Your AI agent can ask it anything.

Ender Turing is headless conversation analytics for contact centers, built for AI agents. Through a REST API and a public guide, your agent, your BI tool or your CRM gets the analyzed conversations your managers see: quality scores, summaries and EnderGPT's answers. Each gets only what its account's role allows.

REST API Public guide for AI agents 4.8/5 on G2
SetupThree steps
  1. Create an account for the agent

    An administrator invites a user with the predefined Session API role, or a role of your own, and ticks System/Technical User. That account decides everything the agent can see. API access ↗

  2. Hand your agent the guide

    One plain-text page tells an AI agent how to send its token, write filters, ask EnderGPT and upload conversations. Give it the address and a token of that account. Guide for AI agents ↗

  3. Ask for last week

    A first request lists last week's conversations. From there the agent counts them by any filter, gets their scores and summaries, or asks EnderGPT why customers cancel. Conversations ↗

What it does

What your AI agent or your own system can do.

Every item below is in the guide for AI agents or in the Help Center's API Access article. The links on each card are the sources.

1

Find and count conversations

List conversations by date, agent, topic, direction, type or length, or with any other filter of the Conversations screen: the filters are the same. Count them, or total their length, for any filter.

2

Scores and summaries for any conversation

For one conversation: its details, every quality score point by point with its scorecard and reviewer, and its summaries.

3

Ask EnderGPT about a whole week

For a question about many conversations, such as "why do customers cancel?", the agent asks EnderGPT, waits for the answer and follows up in the same chat. A scheduled chat asks the same question every day, week or month.

4

Send conversations in

Upload a call recording (MP3, WAV, OPUS or M4A), or a chat, an email thread or a ticket as messages. Analysis starts once the upload is accepted; the scores and summaries follow.

5

Set up topics, keywords and automations

With a role that allows it, the agent creates topics and keywords, and Enders: rules that act on new conversations, scores or summaries, webhooks included.

6

Your BI tool, warehouse and CRM

Feed conversation and quality data into a BI tool or a data warehouse, enrich CRM records with insights from conversations, and add your own data to any conversation.

What the API leaves out: Transcript text is not part of it. A conversation comes with its details, its summaries and its quality scores, and an agent asks EnderGPT for what was said. Which plans include API access is in the plan comparison.

Access

Your roles decide what the agent sees.

An agent or a system works through an account you create. Nothing reaches it that the account's role does not allow.

  • Its own account — an administrator invites it like any user, with the predefined Session API role or a role of your own, and marks it System/Technical User, which keeps it out of dispute assignment, mentions and training plans.
  • The same view as the web interface — a role limited to one team, or to the account's own conversations, returns only those through the API.
  • A permission on every call — each endpoint checks its own permission. The Session API role covers conversation data and quality scores and cannot change your settings.
  • Careful by instruction — the guide tells an agent to create, change or delete nothing unless you asked for exactly that, to keep a copy before it changes an item, and to offer archiving in place of deleting.
  • Off when you say so — deactivate the account and its access ends.

API access, in the Help Center ↗ · Roles and permissions ↗ · Guide for AI agents ↗

API FAQ

What teams ask before they connect an agent.

Is Ender Turing headless?

Yes. Ender Turing is headless conversation analytics for contact centers, built for AI agents: an agent or your own system finds conversations, gets quality scores and summaries, asks EnderGPT, sends conversations in and creates topics, keywords and automations through the API, without the web interface. The web interface stays for the people who want it.

Does Ender Turing have an API?

Yes. Through Ender Turing's REST API, other systems get and send much of the same data people work with in the web interface: conversations and their metadata, summaries and quality scores. The Help Center's API Access article explains accounts, roles, filters and limits, and the interactive API reference inside the product lists every endpoint for the roles your administrator allows.

Can an AI agent such as Claude or ChatGPT work with Ender Turing?

Yes, when it can send web requests. Ender Turing publishes a plain-text API guide written for AI agents. With a token, an agent finds conversations, gets their quality scores and summaries, asks EnderGPT questions about many conversations and uploads new ones. It gets only what the token's account may see.

Can an AI agent run our weekly quality review?

The API gives an agent what a weekly review is made of. It lists last week's conversations by agent or topic, counts them for any filter, gets every quality score and summary, and asks EnderGPT a question about all of them, such as why customers cancel. A scheduled chat asks the same question every day, week or month.

Can Ender Turing be set up through the API instead of the web interface?

The guide for AI agents covers this much: an agent creates topics, keywords and automations (Enders), uploads conversations and adds its own data to them, when its role allows it, and it looks up scorecards, the summaries that are set up and the connected apps. For any other call it opens the full API reference, which signed-in accounts with the right role can open.

What can the agent see?

Only what its account may see. Every endpoint checks its own permission, and a role limited to one team or to its own conversations returns only those, as in the web interface. The predefined Session API role covers conversation data and quality scores and cannot change your settings.

Does the API return transcripts?

No. Transcript text is not part of the API. A conversation comes with its details, its summaries and its quality scores; for what was said, an agent gets the summaries or asks EnderGPT.

Can Ender Turing send results to our systems by itself?

Yes, through Enders. An Ender is an automation that acts on a new conversation, score or summary: it can call your webhook, send a notification or add the conversation to a reviewer's to-do list.

Where is the API documented?

In three places. The Help Center's API Access article covers accounts, roles, filters and limits. The guide for AI agents is one public plain-text page. The interactive API reference, with every endpoint, opens inside the product from Help, API Documentation, for the roles your administrator allows.

Is it secure?

Ender Turing is SOC 2 Type II audited and handles data in a GDPR-compliant way on every plan. API access follows your roles: an agent or a system works through its own account, and deactivating that account ends its access.

Which plans include the API?

The plan comparison on the pricing page lists API access for each plan.

Security, hosting regions, sub-processors and response times are documented on the Data Security page; SOC 2 Type II audited, the latest report available under NDA.

Ender Turing also connects to Genesys Cloud, Five9, NICE CXone, Talkdesk, Amazon Connect, Twilio, RingCentral, Zendesk, Fireflies.ai, HubSpot, Pipedrive, Attio, GoHighLevel and the browser call recorder; every option is on the integrations page.

API and AI agents

Put your agent to work on your own conversations.

Book a demo and bring the question you want your agent to answer every week, or the data your BI tool or your CRM should get.