Integration · Team chat
AI agents for Landbot
Work with Landbot chatbot conversations: find customers and read their full transcript, reply with text or an approved WhatsApp template, save values to customer fields.
- Actions
- 10
- Read
- 4
- Write
- 6
Actions
What your agents can do in Landbot
Work with Landbot chatbot conversations: find customers and read their full transcript, reply with text or an approved WhatsApp template, save values to customer fields, and hand a customer to a human agent or back to a bot flow.
Read 4
Look things up. Nothing changes.
List customers
Lists the workspace's customers (people who chatted with a bot), newest first, at customers[].
Get a customer
Reads one customer by ID: name, channel_id, assigned agent_id, archived, last_message and every custom field the bot collected.
Read a conversation
Reads a customer's whole transcript at messages[], in no guaranteed order (sort by message_datetime, formatted YYYY-MM-DD HH:MM:SS).
List WhatsApp templates
Lists the WhatsApp templates the workspace may send, at templates[]: each with id (for send_whatsapp_template), text and params_number (how many placeholders its body has).
Write 6
Create, change or send.
Send a text message
Sends a text message to a customer on their channel (web, WhatsApp, Messenger or API chat).
Send a WhatsApp template
Sends an approved WhatsApp template to a customer, which is how to write first or after the 24-hour window.
Create a customer field
Saves a new field on a customer, like an order number or a preference, with its type (string, integer, float, boolean, date as ISO 8601, datetime as a Unix time).
Update a customer field
Changes the value of a field the customer already has (404 when it was never created; then use create_field).
Hand to a human agent
Assigns a customer's conversation to a human agent in the workspace by the agent's ID (the bot stops answering).
Hand to a bot
Puts a customer into a bot's flow by the bot's ID, starting at its start node or at a node reference (right-click a node in the builder and copy its reference).
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Paste an API key from your Landbot account.
What you enter
- Agent token
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your Landbot data
Ask a question in plain words. The agent can list customers, get a customer or read a conversation in Landbot, then answers with what it found.
- 02
Let an agent update Landbot
Have the agent send a text message or send a WhatsApp template in Landbot as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Work from your CRM
Give one agent HubSpot and Landbot: it can search contacts in HubSpot and send a text message in Landbot in the same run.
Works well with
More Team chat tools
- Slack bot6 actionsPost and reply in any channel, read recent messages, list channels, find a person by email and add reactions, as a bot installed in a Slack workspace.
- Microsoft Teams6 actionsPost and reply in Teams channels and send chat messages as the signed-in person, and list their teams, channels and chats.
- Google Chat1 actionPost messages to a Google Chat space through an incoming webhook.
- Discord1 actionPost messages to a Discord channel through a channel webhook.
- Zoom4 actionsSchedule Zoom meetings, list a user's upcoming meetings, read a meeting's details and list cloud recordings, through the organization's own Server-to-Server OAuth app.
- Google Meet5 actionsCreate Google Meet meeting links, and see past meetings, who joined them and their transcripts, signed in with the person's own Google account.
FAQ
Landbot and MyDeepAgents
Can MyDeepAgents connect to Landbot?
Yes. The Landbot connector has 10 actions: 4 read and 6 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Landbot?
Paste an API key from your Landbot account. You'll need: Agent token. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in Landbot without asking?
Only if you let it. Each of the 6 actions that change data can be set to wait for a person's approval before it runs.
Can I use Landbot in workflows as well as agents?
Yes. Every Landbot action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Landbot to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.