Integration
Connect Braintrust and Reply
When New Event fires in Braintrust, your agent runs Send Test Webhook Event in Reply, or New Email Opened in Reply to Add project in Braintrust. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Braintrust and Reply to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Braintrust and Reply can do together
From Braintrust to Reply
When New Event in Braintrust
then Send Test Webhook Event in Reply
From Reply to Braintrust
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Braintrust and Reply
Triggers and actions 9 triggers · 33 actions
- New Event
Triggers when an automation creates a new event.
- New Project
Triggers when a new project is created.
- Add dataset
Create a new Braintrust dataset.
- Add experiment
Create a new Braintrust experiment.
- Add project
Create a new Braintrust project.
- Add prompt
Create a new Braintrust prompt.
- Delete project
Delete a Braintrust project.
- Get dataset
Retrieve a Braintrust dataset by id.
- Get experiment
Retrieve a Braintrust experiment by id.
- Get project
Retrieve a Braintrust project by id.
- Get prompt
Retrieve a Braintrust prompt by id.
- Insert dataset events
Insert one or more rows/events into a Braintrust dataset.
- Insert experiment events
Insert one or more events (spans/rows) into a Braintrust experiment.
- Insert project logs events
Insert one or more log events into a Braintrust project's logs.
- List datasets
List Braintrust datasets.
- List experiments
List Braintrust experiments.
- List projects
List all Braintrust projects.
- List prompts
List Braintrust prompts.
- Update project
Partially update a Braintrust project.
- Inbox Category Set for Reply
Triggers when an email reply in Reply is given an inbox category, automatically or by a user.
- New Email Opened
Triggers when a contact opens a tracked email sent from Reply.
- New Emails Sent
Triggers when Reply sends an email from a sequence step.
- New Link Clicked
Triggers when a recipient clicks a tracked link in an email sent from Reply.
- New Person Bounce
Triggers when an email sent from Reply bounces or is rejected by the recipient's mail server.
- New Person Opt Out
Triggers when a contact opts out of outreach in Reply (unsubscribe link, manual opt-out, or marked Do Not Contact).
- Prospect Finished
Triggers when a contact's participation in a Reply sequence ends — completed, replied, bounced, opted out, or finished manually.
- Add contact list
Creates a new contact list in Reply, optionally shared with your team.
- Add note to contact
Adds a note to a contact's timeline in Reply.
- Add sequence
Creates a new sequence in Reply with its steps, schedule, sending accounts and settings.
- Create\Update Person
Creates a Reply contact, or updates the existing contact with the same email address.
- Delete contact
Deletes a contact from your Reply account.
- Find contacts by criteria
Returns the contacts that match a search term and/or field rules, optionally scoped to a contact list, sequence or sequence step.
- Get contact
Returns one Reply contact by its id, including profile details, owner, opt-out, call and meeting status, stage and custom fields.
- Get sequence
Returns one sequence in full: name, status, owner, schedule, settings, connected email and LinkedIn accounts, and its steps.
- List contact lists
Returns the contact lists you own plus those shared with your team, optionally filtered by name.
- List contacts
Returns your Reply contacts, optionally narrowed to one email address or LinkedIn profile URL.
- List inbox categories
Returns the inbox categories you can file conversations under.
- List Sequence Contacts
Returns the contacts enrolled in a sequence, with each contact's status, current step, added date, opt-out and call status.
- List sequences
Returns the sequences in your Reply account, optionally filtered by status, owner, folder, archive state or name.
- Mark as Finished
Marks one or more contacts as finished in every sequence they are in, so they receive no further sequence steps.
- Remove Person From Campaign
Removes a contact from a sequence so they stop progressing through it. The contact and their history stay in your Reply account.
- Send Test Webhook Event
Sends a test event from an existing Reply webhook subscription to its configured URL.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Braintrust
Braintrust to LinkedInLinkedIn is a professional networking platform enabling job seekers, companies, and thought leaders to...
Braintrust to Webscraper IoCloud web scraping platform with a REST API for extracting data from websites, including JS-rendered pages...
Braintrust to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Braintrust to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Braintrust to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Braintrust to Google SheetsGoogle Sheets
More into Reply
Gmail to ReplyGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to ReplyGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Google Drive to ReplyGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
Mailchimp to ReplyMailchimp marketing automation and email platform.
Questions
Braintrust and Reply, answered
What can start an automation from Braintrust?
Any of Braintrust's 2 triggers in the catalog, including New Event and New Project. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Reply when something happens in Braintrust?
Any of Reply's 16 actions, including Create\Update Person, Send Test Webhook Event, Add contact list and Add note to contact. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Reply to Braintrust?
Yes. When something happens in Reply, your agent can act in Braintrust too. This page covers both directions: Reply's triggers and Braintrust's actions are listed here as well.
Do I have to build a connector for Braintrust or Reply?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.