Start free
Copilot

Every ticket opens with the work already started

The Copilot is the Aide panel inside Zendesk and Front, the Aide card in Gorgias, and the reply box in Aide's own inbox. The moment a ticket opens, the customer's orders and tracking are on screen next to the detected intent and a grounded draft. Handle time comes down, the tab-hopping stops, and the hardest tickets open with the most context.Grounded by the Customer Context Engine, learning through the Continuous Learning Engine. AI that keeps your team in the driver's seat.
Get a demoSee it in the helpdesk
On screen the moment the ticket opens
Context on openCited draftsIntent detectionThe hard queueLearning loopPath to automationContext on openCited draftsIntent detectionThe hard queueLearning loopPath to automationContext on openCited draftsIntent detectionThe hard queueLearning loopPath to automation
Populate ticket fieldsSuggest macrosWrite handoff summariesWrite the intent back to the ticketShow order and account dataShow what each draft is based onPopulate ticket fieldsSuggest macrosWrite handoff summariesWrite the intent back to the ticketShow order and account dataShow what each draft is based onPopulate ticket fieldsSuggest macrosWrite handoff summariesWrite the intent back to the ticketShow order and account dataShow what each draft is based on
10x
Faster responses
Context and a grounded draft on screen when the ticket opens
One panel
Instead of five tabs
Orders, tracking, the intent, and a draft in the helpdesk sidebar
24h
To first value
One click into Zendesk, Front, or Gorgias
Trusted by customers on
Zendesk logoZendesk★★★★★5.0 rating
Shopify logoShopify★★★★★5.0 rating
We currently use Zendesk and as such needed an AI solution that works with our existing CX platform and allows us to fully leverage our Shopify data to cut down support times and costs. Aide was a perfect fit as it integrates with both and seamlessly helped our agents get through tickets faster and automatically populates ticket fields on Zendesk!
Patchstore24Shopify
We have been working with Aide for some time now and they have been exceedingly responsive and helpful to our needs. Throughout the process, the Aide team has taken our feedback well and made this as smooth as possible.
Wicked ClothesShopify
Really great approach and strong answers out of the box. Ability to grow into your AI journey at your own pace starting with suggested responses, macro suggestions or precanned messages and then slowly automate once you're confident.
Zendesk Marketplace reviewZendesk
Inside the helpdesk

Review and insert, not research and compose

Open a ticket and the panel has already worked it: context gathered, intent detected, draft written and cited. Handle time falls on the simple tickets, and the hard ones open with the context that makes them workable. Every reply is a draft a person reviews and inserts.

The Customer Context Engine puts the detected intent, the customer's orders, and live tracking in the panel the moment a conversation opens, next to a draft and the macros that fit. No tab-hopping across the helpdesk, the store admin, and the docs: what those tabs hold is already in the ticket.

Every draft is grounded in your help center, the customer's live data, and the macros your team actually sends for this kind of ticket, and says what it was based on. The agent checks it, edits if needed, and inserts it in one click. Composing from scratch becomes reviewing what is already written, and handle time comes down ticket by ticket.

Every incoming conversation is classified by intent the moment it arrives. Aide writes the intent back to the ticket, procedures collect fields and apply tags, and your helpdesk's own rules route it before anyone has read it. The administrative minutes come off the ticket, and the agent's time goes to the customer.

As automation absorbs the simple volume, the tickets that reach your team get harder and more technical, and those are the ones where context matters most. When Aide hands a ticket to your team, it leaves a handoff summary of what the customer wants, what was tried, and what is needed next, with a draft to start from. The panel adds the macros your team sends for this kind of ticket, so a new hire works the hard queue the way your most experienced agent would.

Marking a detected intent right or wrong saves the message as an example on the right topic. Drafts learn which macros your team sends for which situations, and where your team keeps rewriting drafts, Superintelligence proposes a fix for you to approve. Your team's judgment is the signal, and nobody is bypassed.

Start small. Prove it works. Expand from there. When the drafts on an intent keep holding up, your team tests it in the Agent Simulator against your real past conversations, then switches it to full automation. One intent at a time, on the Gradual Automation Pathway, at your team's pace.
Aide is the AI platform for customer service, and the Copilot is where your team meets it. Copilot shows your team the detected intent, the customer's orders, and the draft, on every ticket. Amplifies, not replaces.
The Agent Governance Engine

The panel suggests. Your team decides.

The Copilot puts the work on screen. What leaves the helpdesk is still your team's call, on every ticket.
A person sends every replyThe panel drafts and suggests inside the ticket. Nothing reaches a customer until an agent has reviewed it and hit send.
Drafts only from approved knowledgeDrafts are built from your help center, the customer's live data, and the macros your team sends, never the open internet. Each draft says what it was based on.
Your team's corrections countA corrected intent becomes an example on the right topic, and drafts your team keeps rewriting become fixes Superintelligence proposes for your approval.
Automation is opt-in, per intentNo intent is automated until you say so. Test it in the Agent Simulator against real past conversations first, then flip the switch.
Getting started

Works with your existing stack

The panel installs in one click and lives inside the helpdesk you already run. No migration, no new tab, no engineering.

Zendesk logo
Zendesk

The Copilot panel in the ticket sidebar, updating as agents move between conversations.

Front logo
Front

The panel in the shared inbox sidebar: context, draft, and fitting macros per conversation.

Gorgias logo
Gorgias

The Aide card in the sidebar shows the draft, intent, and orders; one macro inserts the draft.

Shopify logo
Shopify

Order details, tracking, and product data in the panel the moment a ticket opens.

WooCommerce logo
WooCommerce

Live order data from your store, in the panel next to every conversation.

Salesforce logo
Salesforce

The CRM record alongside the ticket, so drafts reflect the account as it is right now.

Claude logo
Claude

Search knowledge, read conversations, and act from a Claude chat.

Aide integrates with your custom systems via API.

Frequently asked questions

In Zendesk and Front it is the Aide panel in the ticket sidebar, updating as agents move between conversations. In Gorgias it is the Aide card in the sidebar, with an "Aide: insert draft" macro that drops the draft into the reply box. In Aide's own inbox it is in the reply box. No separate tool, no extra window.

From both ends of the ticket. The research comes off the front: the customer's orders and tracking are on screen the moment the ticket opens, surfaced by the Customer Context Engine. The composition comes off the back: a grounded draft and the macros that fit are one click from inserted. Average handle time comes down because agents review and verify instead of research and compose. The size of the drop depends on your intent mix, which is why we show it on your own tickets in a demo instead of quoting a number.

Your help center articles, product information, custom instructions, and the customer's live data: the order or shipment as it is right now. Drafts also learn from the macros and replies your team sends for each situation, and say what they were based on so your agent can verify before sending.

No. In assist mode a person reviews and sends every response. Full automation is a separate, opt-in step your team takes per intent, after testing it in the Agent Simulator.

It would if the team were bypassed. Copilot works the other way: agents see the detected intent, the customer's orders, and what each draft was based on, on every ticket. New hires ramp with the Intent Map as a shared mental model of why customers write in, and the team's corrections become examples and fixes the team approves. The team builds product mastery through the process instead of watching a black box.

Marking a detected intent right or wrong saves the message as an example on the right topic, and drafts learn from the macros and replies your team sends. Where your team keeps rewriting drafts, Superintelligence proposes the smallest fix, and nothing changes until someone approves it.

Yes. With Shopify or WooCommerce connected, the Customer Context Engine displays order details, tracking, product data, and customer history alongside every conversation, and drafts are grounded in that live data.

On the Gradual Automation Pathway. Your team watches how drafts hold up on a given intent, tests it in the Agent Simulator against your real past conversations, and promotes it to full automation when the evidence is there, one intent at a time, at your pace.

Start free with 150 AI replies a month and no card. Paid plans start at $39 a month with a 7-day free trial, and you pay for AI replies, not seats. See aide.app/pricing for every plan.

Set it up

Bring handle time down. Keep your team in the driver's seat.

Context, a grounded draft, and the macros that fit on screen the moment the ticket opens, inside Zendesk, Front, or Gorgias. Automation comes later, one proven intent at a time, at your pace.

Start freeGet a demo
Not ready yet? Get product updates by email