Integration · Help desk
AI agents for Re:amaze
Find conversations and contacts, read messages, reply to customers, add internal notes, open conversations, and change status, assignee and tags in a Re:amaze brand.
- Actions
- 13
- Read
- 7
- Write
- 6
Actions
What your agents can do in Re:amaze
13 actions. Each one is a tool your agents can call and a step your workflows can run.
Read 7
Look things up. Nothing changes.
Find conversations
Lists the brand's conversations, 30 a page, newest first by default (sort updated or changed for recent activity).
Get a conversation
Reads one conversation by its slug.
List messages in a conversation
Reads a conversation's messages, newest first, 30 a page, optionally only staff or only customer messages.
Find contacts
Lists the account's contacts, 30 a page, sorted by name (or newest first), or those whose name or email matches the search.
List a contact's notes
Reads every note on a contact, by their email or phone number.
List staff
Lists the account's staff users, 30 a page.
List channels
Lists the brand's channels, optionally of one type.
Write 6
Create, change or send.
Reply to a conversation
Posts a reply (Markdown allowed) as the connected staff user, which Re:amaze sends to the customer through the conversation's channel.
Add an internal note
Adds an internal note (Markdown allowed) to a conversation as the connected staff user; customers never see it and no one is emailed.
Create a conversation
Opens a conversation in a channel on behalf of a customer (found by email, or created), with a subject and first message, as if they had written in, like a support form.
Update a conversation
Changes a conversation's status (0 open, 1 responded, 2 done, 3 spam, 4 archived, 5 on hold), its tags (the list replaces the current tags, so include the ones to keep), its assignee.
Create a contact
Adds a contact with a name and an email or mobile number (E.164, like +14155550100), and optionally your own ID for them, notes and custom data.
Add a note to a contact
Adds a note to a contact (by email or phone), visible to staff on the customer's profile, credited to the connected user or another staff email.
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.
Enter the API credentials from your Re:amaze account.
What you enter
- Login email
- API token
Settings
- Brand
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 Re:amaze data
Ask a question in plain words. The agent can find conversations, get a conversation or list messages in a conversation in Re:amaze, then answers with what it found.
- 02
Let an agent update Re:amaze
Have the agent reply to a conversation or add an internal note in Re:amaze as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent Re:amaze and Slack: it can find conversations in Re:amaze and post a summary to a Slack channel in the same run.
FAQ
Re:amaze and MyDeepAgents
Can MyDeepAgents connect to Re:amaze?
Yes. The Re:amaze connector has 13 actions: 7 read and 6 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Re:amaze?
Enter the API credentials from your Re:amaze account. You'll need: Login email and API token. The connection also asks for: Brand. 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 Re:amaze 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 Re:amaze in workflows as well as agents?
Yes. Every Re:amaze action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Re:amaze to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.