Introducing the AI Agent Builder: Describe It, and Macha Builds It

On April 3, 2026 we shipped the Macha AI Agent Builder to collapse that, and this post is the proper write-up of what it does. You describe the agent you want in plain English — "triage incoming Zendesk tickets, tag the billing ones, and draft a reply for everything else" — and Macha builds it: the instructions, the tools wired to your actual connected integrations, the triggers, any sub-agents, and the model. You get a real, fully configured agent you can run, inspect, and edit — not a stub you have to finish by hand. It's live now, and it's available on all plans.

What we shipped

The AI Agent Builder is a conversation that ends in a configured agent. The launch is deliberately plain about what it does: describe what you want in plain language and the AI creates a fully configured agent with the right tools, instructions, triggers, and sub-agents. A follow-up refinement added the last piece it sets for you automatically — model selection — so the agent that lands isn't a half-built draft; it's ready to test.

Three things make this more than a fancy text box:

• It's context-aware. The Builder already knows which integrations your org has connected — your Zendesk, your Notion, your Stripe, your custom API tools — and it suggests configurations that use those tools, not a generic catalogue you don't have. Hover a suggestion pill and it previews the exact prompt it will run.
• It builds the whole agent. Instructions, tools, triggers, sub-agents, and model — all in one pass. It can even assign sub-agents when it creates an agent, with automatic circular-dependency checks so you can't accidentally wire an infinite loop.
• The output is real and clickable. Created agents, triggers, and tools appear as interactive artifact cards in the chat. Click an agent card and you land directly on its configuration page, where every field the AI filled in is yours to keep, change, or throw away.

How it works

You start by telling the Builder what you want, in your own words. There's no schema to learn and no prompt-engineering ritual — you write the way you'd brief a new teammate.

Macha reads the request against your account, drafts the agent, and streams the result back as artifact cards. Because the Builder knows your connected stack, a request like "refund triage agent" reaches for the connectors you actually have — your helpdesk for reading and replying to tickets, your commerce or billing tool for the refund logic, your knowledge sources for policy — instead of inventing capabilities you'd then have to go set up.

From there you open the agent and review it like any other. Nothing is locked. The Builder's job is to get you from a blank screen to a sensible first draft in one message; tuning, testing on a real ticket, and shipping are still yours to do — and they're a lot faster from a populated config than an empty one.

What a generated agent actually looks like

To make this concrete: type "build me a refund-triage agent for Zendesk that processes straightforward refunds in Stripe and replies on the ticket" into the Builder with Zendesk and Stripe already connected, and the agent that lands is fully populated, not a stub. Here is the config it produces, field by field:

Every one of those fields is editable. If you'd rather the agent never refund autonomously and only ever draft, you delete the Create Refund tool and tighten the instructions — by hand on the form, or by asking the AI editor to "make this draft-only." The point of the Builder is that you start from this filled-in config instead of a blank one. For the end-to-end build, test, and ship-it walkthrough of an agent like this, see the deep-dive below.

Editing by conversation, too

The same conversational interface works on agents you already have. Open the AI editor from any agent's configuration page and you can modify any part of it — tighten the instructions, add a tool, set up a trigger, wire in a sub-agent — by asking for the change instead of clicking through the form. The builder and the editor are the same idea pointed at two moments: standing one up, and evolving it later.

Why a support-native builder is different

Natural-language agent building is the defining product trend of 2026. Salesforce's Agentforce Builder lets you "describe what you want an agent to do and AI will help generate subagents, instructions, and actions"; ServiceNow and Salesforce have been racing each other to ship agent studios, and Talkdesk and Decagon have their own describe-the-agent flows — while horizontal tools like Lindy, Airtable's Omni, and Glean do it for general workflows. The idea is good. The question is what the builder starts from.

Most of those tools are one of two things: a horizontal workflow canvas that gives you a blank graph and a thousand possible integrations, or a platform-locked suite that only builds inside its own walled garden. Macha is neither. It's an AI agent layer that sits on top of the helpdesk you already use — Zendesk, Freshdesk, Gorgias, or Front — and connects to your commerce, knowledge, and comms tools alongside it.

That changes what the first draft looks like. A horizontal builder can't know that your helpdesk is Zendesk, that your refund logic lives in Stripe, and that you already indexed your policy docs in Notion — so its first guess is generic and you spend the next hour mapping it to reality. Macha's Builder starts from your connected account, so its first draft is already shaped to your stack. You're editing something real, not assembling something from scratch.

When you'd still build by hand

The Builder is a head start, not a replacement for judgment. A few honest caveats:

• It drafts; you own the result. Review what it wired up before you turn an agent loose — especially anything that writes back to customers or takes an action. The AI is good at a sensible first pass; you're accountable for the final config.
• It can only reach what you've connected. Ask for an agent that uses a tool you haven't set up and it can't conjure the integration. Connect the integrations you need first, then describe the agent — the Builder will pick them up.
• For surgical, multi-step changes, the form is still there. If you know the exact field you want to change, editing the config directly can be faster than describing it. The Builder shines most going from zero to a working draft.
• Like everything in Macha, it runs on credits. Building and editing by AI uses credits per action, the same model as the agents themselves — 0.5–9 credits by model, default GPT-5.4 Mini = 1. It's a small cost for a big shortcut, but it isn't free. See pricing for the details.

Go deeper

This post is the announcement. If you want the full step-by-step — what a generated agent's instructions, tools, triggers, and sub-agents actually look like, with more screenshots and a worked example — read the deep-dive: Build an AI Support Agent Just by Describing It. The docs cover the builder and editor in reference detail.

FAQ

What is the Macha AI Agent Builder? A conversational way to create support agents. You describe the agent you want in plain English and Macha generates a fully configured agent — instructions, tools wired to your connected integrations, triggers, sub-agents, and model. It launched on April 3, 2026.

Which plans include it? The AI Agent Builder is available on all plans. See the pricing page for what each tier includes.

Does it work with my helpdesk? Yes. Macha is a layer on top of your existing helpdesk — Zendesk, Freshdesk, Gorgias, or Front — and the Builder uses the integrations you've already connected when it drafts an agent.

Can I edit what it builds? Always. The generated agent is a normal Macha agent — every field is yours to change by hand, or you can keep using the conversational AI editor from the agent's config page.

Is there a separate tool builder? Yes — a companion AI Tool Builder lets you describe an API, paste your credentials, and have Macha discover endpoints, test them, and create the tools automatically. Those tools then show up for the Agent Builder to use.

Try it

Start a 7-day free trial, no credit card required, connect your helpdesk, and tell the Builder what you want your first agent to do. You'll have a working draft before you'd have finished filling in the old config screen.

Written by Abbas (Customer Support & AI, Macha) · Reviewed by Ankeet Guha (Co-founder & CTO) · Published 2026-06-24.