We analyse your help desk, pick the tickets worth automating, build the agent and put it live in safe mode. You review the results.
Macha is a done-for-you AI customer support service. Our team analyses your past tickets, builds the knowledge base and the AI agent inside the help desk you already use (Zendesk, Freshdesk, Gorgias, Front, HubSpot, Intercom), and runs it in safe mode until your team approves the replies. Live in under a week. About $0.40 a ticket, from $299 a month for 750 tickets, with setup and a dedicated success manager included. No setup fee.
The free trial includes the same setup: $50 of free usage, about 125 tickets, no credit card.
Who does what
Signing in to your own tools is the one step we can't do for you. The rest of the work is ours.
Your team
The Macha team
How it works
Setup is included in your plan, and your first ticket category is live within a week of the call.
We learn how your support runs, the rules your team follows and which tickets you want off their plate.
We ask what you want off your team's plate, how you handle refunds and exceptions, and which tickets must always reach a person.
We come back with the ticket categories worth automating, and the ones that should stay with a person.
About a month of tickets, or two weeks at high volume. Every ticket is classified, the categories are ranked, and each one gets a clear call. You get it as a PDF.
We build its knowledge base from your help centre, website and past replies, connect the tools it needs, and test it on your past tickets.
The Knowledge Builder turns your help centre, a website crawl, your documents and past tickets into articles. Gaps for the first category are filled before go-live.
It writes internal notes inside your help desk. Your team decides what goes out to customers.
Drafts land as internal notes in your own help desk. Nothing reaches a customer until you say so.
We fix edge cases, tighten the rules and switch on automatic replies once you are comfortable.
When the drafts are right, that category switches to public replies and we start on the next one.
What the analysis looks like
Before we build anything, you get a breakdown of your ticket categories: how much of your volume each one is, which we would automate first, and which should stay with your team.
Help desk analysis
Damaged items need photos checked and a judgement call on each one, so we would leave them with a person.
Timeline
Live in under a week is the commitment. The day-by-day split below is typical, and after that the pace mostly depends on how quickly your team reviews drafts.
A 30-minute call, then about 15 minutes to sign in to your help desk and the tools answers come from.
We classify about a month of your tickets, rank the categories and agree the first one with you.
We fill the knowledge gaps for that category, write the instruction, connect the tools and test the agent on your past tickets.
The agent writes drafts as internal notes on real tickets. Your team reviews them, about 5 minutes a day.
When you're happy with the drafts, the category switches to public replies and we start on the next one.
Safe mode
Nothing goes to your customers until your team approves it.
Replies from your team, as usual. While a category is in safe mode, the agent doesn't write to customers at all.
A draft reply as an internal note on the ticket, written the way your team answers. Use it, edit it or ignore it.
When the drafts are right, you tell us. That category switches to public replies, and every other category stays in safe mode.
Customer: Hi, I ordered a jacket last week and haven't had a shipping email. Can you check?
Draft reply from Macha
Hi Sam, thanks for checking in. Your order left our warehouse on Tuesday and is with the carrier now, due on Friday. The tracking link is below so you can follow it.
Invented example. In safe mode, every draft waits for your team.
Continuous evaluation
Every ticket the agent handles is scored against the rules you gave us. Did it verify the account? Did it escalate when it should have? We group the misses by rule and fix them with you.
Learn about evaluationA dedicated success manager
One person on our team owns your account after launch. Tell them about a new category, a policy change or a new tool, and they update and test the agent. You don't manage the AI yourself.
Price
About $0.40 a ticket, on one plan priced on monthly ticket volume. Setup, monitoring and a dedicated success manager who handles your changes are included on every plan and on the free trial. Billing is monthly and you can cancel anytime.
Free trial: $50 of free usage, about 125 tickets, no credit card and no time limit. The trial includes the same done-for-you setup.
One ticket is one thread with one person, however many messages it takes. No overages: when the month's tickets are used, agents pause until the next billing date, or you move up a tier or add a top-up.
No migration and no new inbox. The agent works inside your help desk, and your team keeps working where it already does.
We connect to your Zendesk, build the agent's knowledge from your Help Center and past tickets, and keep it on internal notes until the drafts are right. Your agents also get the Macha Copilot app in the Zendesk sidebar, rated 5.0 on Zendesk Marketplace.
Macha on Zendesk
On Freshdesk, the agent answers tickets, adds private notes with context, and triages, routes and escalates tickets. Your team can also work with it in the Macha Chrome side panel next to Freshdesk.
Macha on Freshdesk
On Gorgias, the agent answers tickets, adds internal notes, and triages and routes them. For ecommerce teams we connect Shopify and your subscription platform, so answers about orders come from live data.
Macha on Gorgias
On Front, the agent works on conversations: it leaves drafts as internal comments, replies once a category is live, and triages, routes and escalates conversations.
Macha on Front
On Intercom, the agent replies, leaves private notes, and assigns, tags and closes conversations. It stays on private notes until the drafts are right.
Macha on Intercom
On HubSpot, the agent reads each ticket with the contact and their deals, replies, logs notes, and updates status, owner, priority or pipeline stage.
Macha on HubSpotEach route suits someone. They differ in who does the work, and who keeps the agent running after launch.
| Option | Who builds it | Time to live | Price published | Who runs it after launch | Commitment |
|---|---|---|---|---|---|
| Self-serve AI tools e.g. eesel AI, My AskAI, Chatbase | Your team, with the vendor's docs | Depends on your team's time | Yes | Your team | Monthly or annual plan |
| Help desk native AI e.g. Zendesk AI agents, Intercom Fin, Gorgias AI Agent | Your team configures it in the help desk. Intercom also sells Fin Deployment Services as a separate engagement. | Depends on your team's time. Intercom quotes enterprise rollouts in under 90 days. | Yes for the AI. Fin Deployment Services is price on request. | Your team | Your help desk plan plus AI usage |
| Enterprise AI vendors e.g. Sierra, Decagon, Ada | The vendor's own team | Not published | No, sales-led | The vendor's team, under contract | Annual contract after a sales process |
| Agencies, partners and freelancers e.g. chatbot agencies, help desk partners, Upwork freelancers | The agency, on another vendor's platform | Set per project | Quoted per project | Your team after handover, or the agency on a retainer | Project fee plus the platform's own plan |
| Macha | The Macha team | Under a week | Yes: about $0.40 a ticket, from $299 a month | A dedicated Macha success manager | Monthly, cancel anytime |
Some other AI vendors include onboarding in their plans too. When you compare prices, check what each one covers: setup, ongoing changes, or just the software.
Support leads on what changed once the repeat tickets stopped arriving.
The implementation didn’t feel like “work”.
Macha runs the front line of our candidate and reference support in Zendesk, a few thousand tickets a month. It triages everything that arrives, answers what it can in our own approved wording, and passes the rest to my team.
Nicole Garelick
Director of Support · Crosschq
No guessing, and it escalates the moment it isn’t certain.
Macha runs our Rewards claims support in Freshdesk, a few thousand a month. When a customer says their cashback is missing, the agent reads the whole thread, looks the purchase up in our own system through a custom integration they built against our API, and answers on what it actually finds.
Saad Hashim
COO · Sprive
They tuned each agent with us until it held up.
Macha runs the front line of our Zendesk across both our brands, around six thousand tickets a month in German, English, French and Dutch.
Yvonne Panarin
Customer Support Manager · myposter
Can't find what you're looking for? Talk to us
Not ready for a call?
Start with a free audit of your tickets. We tell you which categories are worth automating, and you keep the report either way.
Tell us which tickets your team answers over and over. We analyse them, build the agent, put it live in safe mode and keep it tuned as your tickets change.
Shopify
Stripe
Slack
Notion
Google Workspace
Confluence
