What's New in Macha — April 2026 (AI Builders, OAuth, Confluence & GDPR)

This is the full roundup of everything Macha shipped across the April 2, 3, 9, 17, and 23 releases, grouped by what it does rather than which day it landed, with a short why it matters on each. As always, Macha is the AI agent layer that sits on top of the helpdesk you already run — Zendesk, Freshdesk, Gorgias, Front — so most of these changes are about making the agents smarter and the connections to your stack sturdier. The canonical, dated log lives on the changelog page; this post is the narrated version.

The headline: the AI Agent Builder & Editor

The biggest change in April is that you no longer have to assemble an agent by hand. Build agents through conversation — describe what you need ("an agent that triages new Zendesk tickets, tags them by topic, and routes billing questions to the Billing group") and the builder creates a fully configured agent: instructions, tools, triggers, sub-agents, and model selection, all wired up. It's available on every plan, including Trial.

It works in both directions. Edit with AI opens the same conversational editor from any existing agent's configuration page, so you can change instructions, add a tool, set up a trigger, or wire in a sub-agent without hunting through the form. The builder is context-aware — it knows which integrations you've connected and suggests relevant configurations, and you can hover a suggestion pill to preview the prompt it will run. Everything it creates or modifies — agents, triggers, tools — shows up as interactive artifact cards in the chat; click an agent card to jump straight to its config.

By the April 9 iteration the builder could also assign sub-agents when creating new agents, with automatic circular-dependency checks so you can't accidentally build an infinite delegation loop.

Why it matters: the slowest part of adopting an agent platform is the blank-canvas problem — knowing which tools and triggers to combine. Describing the outcome and letting the builder draft the configuration turns a 30-minute setup into a 30-second one, and the artifact cards keep it auditable instead of magic.

New connector: Confluence (plus a way to connect anything)

Macha added a Confluence connector on April 9, bringing knowledge-base teams that live in Atlassian into the fold. It ships with seven tools: search pages, read content, list spaces, get child pages, create pages, update pages, and add comments. Write operations (create/update/comment) require confirmation, in line with how Macha gates every state-changing action. Connecting Confluence auto-creates a data source — the same behaviour as Google Workspace and Notion — so your space content is immediately searchable knowledge for agents, not just an API endpoint.

There's also token-expiry monitoring: you enter your Atlassian API token's expiration date, Macha emails you a reminder 30 days out, and it automatically deactivates the connector on a 401 so a silently-expired token never causes mystery failures. See the full Confluence integration page for the tool list, or the broader integrations directory.

Alongside Confluence, April carried the Custom API Tools & AI Tool Builder forward: define any REST endpoint (URL params, body templates, API-key / bearer / basic auth, credentials encrypted at rest), or just describe the API and paste credentials and the AI Tool Builder discovers endpoints, tests them, and creates tools automatically. Tools group under named connectors with custom icons and brand colors, so a homegrown internal API shows up next to Zendesk and Stripe like any first-class integration.

Why it matters: Confluence is where a lot of teams keep the real answers. Auto-creating a source means that knowledge is usable on day one, and the expiry monitoring removes the single most common cause of "the agent stopped answering" — a dead token nobody noticed.

Zendesk OAuth is now the default — and much harder to break

April was a big month for the Zendesk connection. On April 9, Zendesk approved Macha's global OAuth client, and OAuth became the default authentication method for new Zendesk connections, replacing API-key auth. Tokens now refresh proactively (and on a 401 fallback) with per-subdomain locking so they're renewed before they expire.

Then on April 23, the OAuth path got hardened after a real incident. A concurrent-refresh race — two webhooks racing on a single-process Node server — had caused an outage for one customer (Schmid Digital). That's now fixed with compare-before-write logic so two refreshes can't clobber each other's tokens. The release also added a Reconnect button in the connector modal: it re-authenticates in place — same connector ID, no tools stripped, no agents broken — and a new email template points customers to it when a reconnect is needed. The re-auth path now preserves existing credential fields (webhook IDs, signing secrets) instead of overwriting the whole blob.

Why it matters: API keys were the old friction point — generate, scope, paste, rotate. OAuth removes that, and the reconnect-in-place flow means a re-auth no longer detonates every agent attached to the connector. The compare-before-write fix is the unglamorous kind of reliability work that you only notice when it isn't there.

Agents can now see: image vision on Zendesk attachments

Shipped April 17: when an agent hits an image attachment on a Zendesk ticket — JPEG, PNG, GIF, or WebP — it downloads the image, encodes it, and sends it to the model for visual analysis. In practice that means an agent can describe a screenshot, read the text inside an image, identify a product, or parse a receipt — the things customers attach instead of typing.

Vision runs on the vision-capable models. As of this release, that's GPT-5.4 Mini, Claude Sonnet 4.5, and Claude Sonnet 4. (When vision first shipped on April 17, the now-retired GPT-5 Mini and GPT-4o Mini were vision-capable too — but both were retired in the April 23 model refresh covered below, so don't build new agents around them.) Groq models gracefully return a "not supported" message rather than failing. Under the hood it's a shared image utility (download + base64 encoding) that future connectors like Freshdesk and Slack can adopt with a single function call.

Why it matters: a huge share of support tickets are "here's a photo of the problem." An agent that can't read the attachment is stuck asking the customer to describe what they already showed you. Vision closes that gap for the most common attachment types.

Sharper Zendesk tools: custom fields, subjects, and routing

A cluster of Zendesk write/read tools landed across April 17 and the days around it:

• Get Ticket Custom Fields — returns every custom field on a ticket with its title resolved from the schema, so an agent reads Bestellnummer: 013724827106 instead of field_1900003089273: 013724827106. Field definitions are cached per connector for five minutes. This is what makes custom-field data actually usable in agent reasoning.
• Update Subject — change a ticket's subject line (validated 1–150 characters; requires confirmation in chat mode). Handy for normalizing messy inbound subjects before routing.
• Assign Ticket → groups — the assign tool now accepts a group, an agent, or both, so triage agents can route straight to a queue ("Billing", "Tier 2 Support") instead of always pinning a specific person.
• List Groups — a read tool that lists every active Zendesk group, so an agent can resolve a group name to its ID before routing.
• Update Ticket Type — set a ticket's type (problem, incident, question, or task) to categorize cleanly without touching custom fields.

There's also a safety layer around all of this: activation confirmation modals now appear when you toggle on high-impact tools (Add Public Reply, Update Ticket Status) or triggers (Every Customer Message, New Ticket), and enabled tools/triggers carry a persistent advisory card on the agent config page — a short, always-visible note on how to use them safely. You can wire a routing trigger into an agent from the same trigger picker shown below.

Why it matters: routing is where most triage agents prove their worth, and "resolve a group name to its ID" is exactly the kind of plumbing that previously forced you to hard-code IDs. Resolving custom-field labels turns raw schema noise into context the model can actually reason over.

A fresher model lineup (and lower cost on the workhorse)

The April 23 release reset the model menu:

GPT-5 Mini, GPT-4o Mini, and o4-mini were retired, and every agent running on them was auto-migrated to GPT-5.4 Mini — no manual action required. This is the practical face of Macha's pricing model: credits are charged per AI action, and the per-message cost varies by model (roughly 0.5–9 credits depending on the model, with GPT-5.4 Mini at 1 as the default workhorse). You pick the trade-off between capability and cost per agent, not per plan.

The April 23 release also restated plan pricing — Starter at $299/mo (3,000 credits) and Professional at $699/mo (10,000 credits). For the current, authoritative plan details, see the pricing page.

Why it matters: dropping the default mini model to 1 credit/message lowers the cost of high-volume automation across the board, and auto-migration means nobody got stranded on a retired model. The 1M-context options matter for agents that read long ticket threads or large knowledge sources in one pass.

GDPR, retention, and data controls

Quietly, April also shipped a serious data-governance layer (refined from the late-March privacy work):

• 30-day scheduled deletion for accounts and organizations, with cascade cleanup (Spaces files, MongoDB collections, org memberships).
• Data export — download a complete copy of your data as JSON, with credentials, embeddings, and other sensitive fields stripped.
• Cookie consent — accept/decline banner across all pages and layouts.
• Conversation TTL — conversations auto-delete after 45 days of inactivity; internal agent logs expire after 7 days.
• Credential encryption in logs — API keys and tokens that appear in internal agent log messages are encrypted with AES-256-GCM before storage.

Why it matters: these are the items a security review asks about. Having scheduled deletion, JSON export, and retention TTLs built in — rather than handled by support ticket — is what lets a regulated team say yes.

Under the hood: connector health and quieter alerts

A few reliability changes that you'll feel as fewer surprises:

• Connector health status — connectors now carry a state (connected / auth_failed). When auth breaks, affected agents are automatically deactivated and admins are emailed, so a broken connector fails loud and safe instead of silently mis-answering.
• Test connection — verify any connector's credentials with one click.
• Webhook rejection tracking — after a threshold of rejected webhooks on a broken connector, Macha returns 410 Gone to prompt the external system to stop sending.
• Credit-alert dedup — usage alerts (50% / 80% / 90%) are now tracked in the database, so you don't get duplicate emails after a deploy, and admin alerts fire once per threshold rather than once per admin in the org.
• Sub-agents can now perform write operations in autonomous mode (replies, updates) while staying read-only during interactive chat for safety.

Watch-outs and the honest caveats

A few things to keep in mind before you flip everything on:

• OAuth is now default, but existing API-key connections still work. If you connected Zendesk before April, you're not forced to migrate — though the new reconnect-in-place flow makes OAuth the lower-maintenance path going forward.
• Image vision only covers images, and only on supported models. PDFs and other documents go through the separate attachment-extraction path, and Groq-based agents won't do vision at all (they return a clean "not supported" rather than erroring). If reading screenshots matters, keep that agent on a vision-capable model.
• The retired-model migration is automatic — double-check your prompts. Auto-migration to GPT-5.4 Mini is convenient, but a model swap can subtly change behaviour. If you had instructions tuned for GPT-4o Mini, re-run a Test Run before trusting the migrated agent in autonomous mode.
• Retention TTLs delete data on a clock. Conversations expire after 45 days of inactivity and internal logs after 7. That's a feature for compliance, but if you relied on old conversations as a record, export what you need first.
• The AI Agent Builder drafts; you still own the review. It produces a real, runnable configuration — which means you should read the tools and triggers it wired up before enabling write actions, exactly as you would for a hand-built agent.

FAQ

Where's the official Macha changelog? The dated, canonical log is at /policies/changelog. This post is the narrated April 2026 summary with context on why each item shipped.

Is the AI Agent Builder available on my plan? Yes — building and editing agents through conversation is available on all plans, including the 7-day free trial, no credit card required.

Did April change how I connect Zendesk? For new connections, yes: OAuth is now the default (Zendesk approved Macha's global OAuth client on April 9). Existing API-key connections continue to work, and there's a Reconnect button that re-authenticates in place without breaking your agents.

Which models can read images? As of the April 23 lineup: GPT-5.4 Mini, Claude Sonnet 4.5, and Claude Sonnet 4. (GPT-5 Mini and GPT-4o Mini were also vision-capable when the feature shipped on April 17, but both were retired on April 23.) Groq models return a "not supported" message rather than failing the run.

What happened to the models I was using? GPT-5 Mini, GPT-4o Mini, and o4-mini were retired, and agents on them were automatically migrated to GPT-5.4 Mini (now 1 credit per message). New agents default to GPT-5.

How are credits charged? Per AI action — the per-message credit cost depends on the model you pick (roughly 0.5–9 credits, with the default GPT-5.4 Mini at 1). See the pricing page for plan details.

Try the April release

The fastest way to feel the difference is to build an agent by describing it. Start a 7-day free trial, no credit card required, connect Zendesk over OAuth, point a Confluence or Notion source at it, and ask the AI Agent Builder for a triage agent — then read the docs for the full configuration walkthrough. For the running list of what's next, keep an eye on the changelog and the blog.

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