What's New in Macha — June 2026: Studies Reports, Agent Evaluation, Gorgias & Front, and Cheaper Models

This is the operator's rundown — what changed, why it matters, and where the sharp edges are. As a reminder of where Macha sits: it's the AI agent layer on top of the helpdesk you already run (Zendesk, Freshdesk, and now Gorgias and Front), wired into your commerce, knowledge, and comms tools. None of what follows replaces your helpdesk; it makes the agents on top of it more capable and easier to trust.

Studies now has a Report view

Studies launched on May 30 as batch AI extraction: point it at a batch of Zendesk tickets, define the columns you want, and a model fills the grid — one row per ticket, one column per question. The June 5 release added the part that turns that grid into a decision: a Report view, available on every completed run.

Open the report from a run's toolbar and Studies aggregates each reportable column into a visual:

• Yes/No, single-choice, and multiple-choice columns become bar charts — each bar labelled with its bucket, count, and percentage. Click any bar to drill straight into the matching records in a modal that uses the same results table as the run page, so moving from a chart into the underlying rows feels continuous.
• Number columns become histograms with min / mean / median / max summary stats on top. With ten or fewer distinct values each gets its own bin; otherwise Macha bins automatically into roughly ten equal-width ranges.

There's also an Ask Sidekick bar at the top of the report, shipped as a disabled "coming soon" preview. Study-scoped query tools land soon — once they do, you'll ask free-form questions about a run's data and get answers grounded in that run's results. Until then it stays inert by design, so it can't return a confident-but-wrong answer over data it can't yet read.

Alongside the report, the Studies editor got a polish pass: tag-style pills for choice options, a credits-per-record badge next to the model selector (and again at the top of every run page), a run-confirmation modal that shows record count, estimated credits, and model before anything starts, and an Excel-like results table with click-to-sort headers and a live search filter.

Plan note, stated plainly: the Report view is Professional and Enterprise only. Trial and Starter plans see an upgrade card. The extraction grid itself runs on Professional and Enterprise.

Agent Evaluation: test before you ship

The harder problem with support agents isn't building one — it's trusting it. The most-cited barrier to putting agents in production is quality: LangChain's 2026 State of AI Agents report found that while 57% of organizations now run agents in production, quality is the number-one thing holding the rest back, named by roughly a third of respondents. Agents are non-deterministic — the same ticket can take a different path on two runs — so "it looked fine when I tested it once" is not a deployment standard.

Agent Evaluation is Macha's answer: run an agent against a set of cases and grade the results before it goes anywhere near a live customer. It follows the same disciplined pattern as Studies — build, estimate, run, report — so if you've used one, the other is immediately familiar.

The flow:

1. Build the evaluation — define the cases you want the agent to handle. You can draft these with AI assistance rather than hand-writing every row.
2. Estimate the cost — like Studies, an evaluation run is metered, so you see the projected credit cost before you commit. Nothing runs until you confirm.
3. Run and review — Macha runs the agent across the cases and returns a results grid, then a report that summarises how it did.

This is the missing half of the agent lifecycle. Studies tells you what's in your queue so you know which agent to build; Agent Evaluation tells you whether the agent you built actually handles it before it's live. It's the same instinct the broader eval ecosystem — LangSmith, Braintrust, and friends — has been formalizing this year, but kept inside the same tool where you build and run the agents, against your real helpdesk data, instead of a separate testing stack you have to wire up.

Watch-out: an evaluation is only as honest as its cases. A passing report on ten happy-path tickets tells you the agent handles ten happy-path tickets — not that it's safe on the angry refund edge case you forgot to include. Build the awkward cases in deliberately, and re-run after every instruction change.

Two new helpdesks: Gorgias and Front

Macha now connects to Gorgias and Front, joining Zendesk and Freshdesk. Both connect via API key and live under Connectors → Support, each with built-in agent templates to get moving fast.

Gorgias is the helpdesk built for Shopify-native ecommerce teams — order data sits right inside the helpdesk, which is exactly the context an agent needs to answer "where's my order?" or process a return without tab-switching. The connector ships 15 tools spanning tickets, messages, customers, macros, tags, and team assignment, plus custom-webhook triggers for ticket created, ticket updated, and message added. Pair it with Macha's Shopify integration and you've got an agent that reads the ticket and the order in one move.

Front is the shared-inbox, customer-operations platform — more common in B2B and ops-heavy teams. Its connector also ships 15 tools, covering conversations, contacts, custom fields, inboxes, and teammate routing. A nice touch: internal comments support @mentions, so an agent can loop in a specific human teammate inside a Front conversation rather than just dropping a note into the void.

If you're weighing the two as helpdesks, the trade is well understood: Gorgias is purpose-built for high-volume B2C ecommerce with deep Shopify order data, while Front shines for B2B and complex internal workflows on a seat-based model (eesel's Gorgias-vs-Front breakdown is a fair summary). Macha sits on top of either — you don't switch helpdesks to use it.

Cheaper models: GPT-5 and GPT-5.4 dropped in price

This one is pure margin back to you. On June 17, Macha cut the credit cost of its two most capable OpenAI models:

Because Macha credits are spent per AI action — not per ticket or per resolution — a lower per-response cost means more agent runs from the same balance. The changelog math: a Professional plan (10,000 credits a month) now gets roughly 67% more GPT-5 and GPT-5.4 responses than before, with no change to the plan. If you'd been defaulting agents to GPT-5.4 Mini purely to conserve credits, GPT-5 is now a much easier upgrade for the agents that need sharper reasoning.

A small related fix: changing the model from the top-right dropdown now shows a toast clarifying that the choice applies only to the current conversation, and pointing you to Settings if you meant to change the org-wide default. It's the kind of scoping confusion that quietly burns credits, now caught.

For the full credit-cost-by-model picture and what each plan includes, see the pricing page.

Operating at volume: the reliability releases

The headline features get the screenshots, but if you run agents in production these are the changes you'll actually feel day to day.

Sub-agent runs are now visible in chat

When an agent hands off to a sub-agent, you can finally see what the sub-agent did. Each invocation gets its own conversation record, surfaced as an expandable card under the delegated message — avatar, handle, model, connector logos, tool count, and a green "Handed off" badge. Expand it for the full nested run: system prompt, every tool call with arguments, every result, and the final reply, styled like the main chat.

It works automatically for every new sub-agent run, in both chat and autonomous (trigger-fired) flows, and the records stay out of your main conversation counter while remaining available for 45 days. For anyone debugging a multi-agent workflow, this turns a black box into a trace.

Soft-delete agents — 30-day trash with restore

Deleting an agent is now reversible. It moves to a Trash tab on the Agents page for 30 days; restore it any time in that window and its triggers, instructions, sub-agent links, and tool config all come back intact. Triggers are deactivated, not deleted, so they stop firing but keep their webhook secrets — restore brings the config back, and you re-enable when ready. The AI sidekick respects the same path, so "delete this agent" from the dashboard assistant is just as recoverable.

A long-standing Zendesk tagging bug, fixed

If you've ever had an agent report it tagged a ticket while the tag never appeared — that was a real bug, and June 10 fixed it. zendesk_update_ticket_tags now actually applies the tag across all Zendesk account configurations, preserves existing tags instead of wiping the set, and reports the verified final tag list back so the agent sees the truth rather than its own intent. If your routing or reporting leans on tags, this one matters.

Debounce on every event-driven trigger

Previously only messaging triggers could be debounced. Now any Zendesk or Freshdesk ticket event, Slack mention or DM, or messaging event can carry a debounce delay — useful when a flurry of rapid updates would otherwise fire your agent five times for one logical change. Safeguards force-fire a debounce bucket once it hits 25 events, or after 10× the window (capped at 2 minutes), so a malformed event source can't hold an agent hostage.

A friendlier first run

New orgs that finish onboarding with at least one connector now land in a welcome conversation instead of a static "you're all set" screen. Macha pulls a few real items from the tools you just connected — recent tickets, recent payments, recent conversations — and the first message streams in referencing what it actually found, with three tailored suggestion chips below. The whole chat is free (a "This chat costs no credits" badge sits by the model picker). One per organization.

There were also smaller wins: new Model / Tools & Triggers / Sub-agents columns on the Agents listing, a top-up balance chip on the Billing usage card, and subscription recovery so a successful retry after a declined card flips an org back to active automatically instead of getting stuck in past_due.

When these updates don't change anything for you

A roundup should be honest about scope:

• If you're on Trial or Starter, the Studies Report view and the extraction grid are gated to Professional/Enterprise — the June reporting work won't be visible to you yet.
• If you don't use sub-agents, the visible-sub-agent-runs feature is invisible (by design) — it only appears when delegation happens.
• The cheaper-model change only helps if you actually run GPT-5 or GPT-5.4. Agents already on GPT-5.4 Mini (the default, still 1 credit) see no change — though it does make stepping up to GPT-5 cheaper than before.
• Gorgias and Front don't replace your current helpdesk — they're additional connectors. If you're happily on Zendesk or Freshdesk, nothing here asks you to migrate.

FAQ

Where do I find the Studies Report view? On any completed Study run, open the Report from the run's toolbar. It's available on Professional and Enterprise plans; Trial and Starter see an upgrade card.

How is Agent Evaluation different from Studies? Studies analyses your existing tickets to tell you what's in your queue. Agent Evaluation runs an agent against a set of cases to tell you whether it handles them — before it goes live. Both follow the same build → estimate → run → report flow, and both are credit-metered with a confirmation gate.

Do Gorgias and Front replace Zendesk or Freshdesk? No. Macha is the AI agent layer on top of your helpdesk — Gorgias and Front are two more helpdesks it can sit on, alongside Zendesk and Freshdesk. Both connect via API key under Connectors → Support.

Did my agents get cheaper to run automatically? Yes, if they use GPT-5 (now 2 credits per response, down from 3) or GPT-5.4 (now 3, down from 5). GPT-5.4 Mini stays at 1 credit. No action needed — the new costs apply to existing agents.

Can I undo deleting an agent now? Yes. Deleted agents sit in a Trash tab for 30 days with one-click restore; their triggers, instructions, sub-agent links, and tools all return intact. After 30 days they're permanently removed.

Try it

If you've been waiting for a reason to look at Studies reporting or test an agent properly before shipping it, this is the month. Start a 7-day free trial, no credit card required, connect your helpdesk — Zendesk, Freshdesk, Gorgias, or Front — and run a Study or an evaluation. The full feature history lives in the changelog and the docs; the integrations directory lists every tool Macha connects to.

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