Let your AI agents
run the inbox.

Your agent triages, drafts, and files bugs in Fernand. Each key only does what you allow, so the hard conversations still come to you.

Start for free R
Works with
  • Claude Code
  • OpenAI Codex
  • Amp
  • OpenCode
  • Cursor
and anything that speaks HTTP

Every key only does
what you allow.

Give an agent read access and drafts, and it can’t message a customer. Need more? Turn on one permission. Give each agent its own key, and revoke it in one click.

Try it: flip a permission.

triage-agentsk_live_1337•••••F3RN
  • Read conversations
  • Write drafts and notes
  • Tag and assign
  • Reply to customers
  • Edit the help center
What the agent tries
GET/conversations20014 conversations403Not allowed
POST/conversations/8231/drafts200Draft saved403Not allowed
POST/conversations/8244/tags200Tagged billing403Not allowed
POST/conversations/8231/reply200Sent to Monica403Not allowed
PATCH/knowledge/articles/112200Article updated403Not allowed
Everything is in the API

Conversations, drafts, notes, tags, contacts, rules, the help center, AI training, Linear, GitHub, and reporting. If you can do it in the app, your agent can too.

Docs written for agents

An llms.txt and an OpenAPI spec. Your agent reads them before its first call, so you don’t have to.

No per-call pricing

The API is free to use. Let your agent check the inbox every five minutes. Nobody bills you for it.

Jobs to hand to your agent

Copy a prompt, or open it straight in your agent. Each job lists the permissions its key needs.

Every 15 minutes

Triage the inbox

Tags every new conversation, marks spam, and snoozes what is waiting on the customer.

Read conversationsTagsStatus

You keep deciding what the tags mean.

Every day at 8:00

Draft replies every morning

Leaves a draft on every conversation waiting on you. You review and send.

Read conversationsDrafts

You keep hitting send.

Every hour

Answer the easy ones

Replies when a help article fully covers the question. Drafts the rest.

Read conversationsHelp centerReplyDrafts

You keep anything the help center doesn’t cover.

Every 15 minutes

Escalate to the right person

Sends refunds, outages, and cancellations to the right teammate, with a summary note.

Read conversationsAssignNotes

You keep the conversation itself.

Every hour

Turn bug reports into issues

Finds bug reports, checks Linear for duplicates, then files or attaches the issue.

Read conversationsLinearNotes

You keep fixing the bug.

When a fix ships

Tell people it’s fixed

Finds everyone who reported the bug, tells them it’s fixed, and closes the thread.

Read conversationsReplyStatus

You keep anything else they asked about.

Which AI agents work with Fernand?
Claude Code, OpenAI Codex, Amp, OpenCode, Cursor, or anything that can send an HTTP request with an API key, including n8n and plain scripts. Point your agent at https://developers.getfernand.com/llms.txt and it learns the API on its own.
How is this different from Fernand AI?
Fernand AI answers customers in the widget and drafts replies in the inbox. This page is about your own agents working in Fernand from the outside, through the API. You can use both.
How do I keep an agent from messaging customers?
Don’t give its key the reply permission. Drafts and private notes never reach the customer. Give each agent its own key, and revoke it in one click.
Is everything really in the API?
Yes. Conversations, replies, drafts, notes, contacts, tags, rules, assignment, the knowledge base, AI training, Linear, GitHub, and reporting. If you can do it in the app, your agent can do it through the API.
Are there rate limits?
Yes. By default, 20 requests per minute on reads and 5 per minute on writes. Every response includes X-RateLimit-Remaining, X-RateLimit-Limit, and X-RateLimit-Reset, so agents can pace themselves.
Does the API cost extra?
No. The API is free to use. We don’t charge per API call, per agent action, or per AI resolution.