It reads every email that hits support@, looks up the customer before it writes a word, replies in the thread within minutes, and holds the ones that are yours.
It lives in your support inbox. It looks up the customer before it writes, replies in the thread in their language, files every ticket to the CRM, and holds only the emails your rules say are yours.
A customer writes to support@ at 7am, and the ticket ages until someone opens the inbox. Email is still where most support happens, and AI chat widgets skip it.
Fasrad's email support agent lives in that inbox. When a message arrives it reads the whole thread and pulls up the sender's orders, plan and last contact. Then it answers in the same thread, from the same address, usually within a minute. The reply carries the tracking number, the reissued invoice or the refund already done.
Pick the mode that fits you. With a dedicated support address it answers on its own, inside limits you set. On your own inbox it drafts every reply in your voice and sends only when you tap approve, so nothing leaves your address without your say-so. Both modes read your mail without touching it: nothing gets marked read, moved or deleted. Customers write in Spanish, German, or Japanese, and it replies in kind.
Rules you write once, applied to every email:
Every email becomes a record. The sender goes into the built-in CRM as a contact, and the ticket gets a category and a one-line summary. The agent remembers what it learns, like the late delivery in May that earned this customer a credit, or their preference for short replies.
When it needs you, it asks on Telegram or in chat with the draft attached and buttons to tap. It also keeps a searchable copy of the mailbox, so it can answer 'how many people complained about the linen shirt this month?' in seconds, searching by meaning across the whole message.
Buyers usually compare these adjacent jobs before choosing an AI agent.
Your choice, per inbox. On a dedicated support address it replies on its own within the rules you set: refund limits, topics that always come to you, phrases it must never use. On your own inbox it drafts in your voice and sends only when you tap approve. Many teams run both, with the agent answering support@ and drafting the sensitive ones for you.
In the thread, always, with proper reply headers, a 'Re:' subject, and the same address the customer wrote to. To the customer it looks like a person answered their email, because one effectively did.
It looks them up before it writes. Orders, plans, and past tickets can live in its built-in records, in a sheet you keep, or behind your own API, and it reads all three. It remembers what it learns across emails, so the credit you issued in May comes up when the same customer writes in September.
It replies in the language they wrote in, with no rules to set and no separate templates. Your instructions stay in your language, and the customer gets theirs.
No. It reads mail read-only. Nothing gets marked read, moved, or deleted, and it files something only when a rule you wrote says to. Look at the inbox after it answers a ticket and the original email is exactly where it was.
They come to you untouched, with context attached: who the sender is, what they've asked before, and a draft if you want one. You define 'shouldn't' in plain English, such as legal threats, chargebacks, press, or anyone on a list of accounts. It tells the customer who has it and when they'll hear back, so every email gets a response.
Start with a 7-day free trial. Full access, no card needed. Then $49 per month. That covers the inbox, the CRM, the searchable mail history, and the rules, for unlimited emails with no per-ticket or per-resolution fee. It's in public beta and takes about four minutes to connect.
One support agent that resolves tickets on email, web chat and inside your product. Plain-English rules decide what asks you first.