Customer Support

Hazel for Gorgias: the AI coworker that separates real agent performance from AI Agent autoresolutions

Hazel reads your full Gorgias helpdesk (tickets, messages, tags, channels, satisfaction scores, response times, agent performance) and answers business questions in plain English. No dashboards to build.

May 23, 2026

Hazel is an AI coworker that connects to your Gorgias helpdesk and answers business questions about your support data the way an analyst would. Once installed, Hazel ingests your full ticket history, message threads, tags, ticket fields, CSAT responses, response and resolution times, agent activity, and every channel you run (email, chat, social, phone) then refreshes every few hours. Ask Hazel which products are driving the most tickets, what the top cancellation reasons are inside a specific ticket field, how WISMO volume tracks against order volume, or when ticket volume is likely to spike around Mother's Day, and you get an answer with the numbers behind it. Hazel separates automated AI Agent replies from human agent work so your performance metrics reflect real team output. For consumer brands running on Gorgias, Hazel replaces the work of digging through ticket fields, exporting CSVs, and stitching support data against orders by hand, and it pairs Gorgias with Shopify, your ad platforms, email, subscriptions, and reviews so cross-source questions are a single prompt.

What Hazel does

Hazel reads the Gorgias data that matters for running a consumer-brand CX team and lets you query it conversationally:

  • Tickets and ticket fields: volume by channel, by tag, by intent, by ticket field value; segment any analysis by the categorization your team already uses
  • Messages and conversations: full thread content, so Hazel can summarize cancellation reasons, product complaints, or shipping themes without you opening tickets one by one
  • Tags and intents: WISMO, returns, subscription changes, product questions; cohort any analysis by your tagging conventions
  • CSAT and satisfaction: scores by agent, by channel, by topic, with the caveat that only customers who respond to the survey show up
  • Response times and resolution times: first response time, full resolution time, one-touch ticket rate, by agent and by channel
  • Agent performance: ticket counts, response speed, CSAT, with automated AI Agent replies separated from human work
  • Channels: email, chat, social, phone, all pulled simultaneously so cross-channel volume comparisons are one prompt

Hazel keeps the full historical record, so year-over-year ticket volume comparisons and seasonal projections (Mother's Day, BFCM, summer peak) work out of the box.

Real questions, real answers

These are real questions Hazel customers ask about their Gorgias data:

"Has there been an increase in tickets coming into Gorgias this week vs. last week and the week prior?"

"Can you pull CSAT trends from Gorgias for the month of March?"

"What hours of the day do we receive the highest number of customer phone calls in Gorgias?"

"Our top reasons are only 36% of ticket volume. What is the other 64% about?"

"Summarize the top reasons customers gave for cancellation under the ticket fields Subscription - Cancel - Active order and Subscription - Cancel - No active order."

"Based on data from 2025, what will be the busiest days and times of day for customer support tickets from April through August 2026?"

"Average WISMO tickets per day by period, normalized by daily order volume."

"For Gorgias, what's the most common country people ask if we ship to?"

How your data flows
How it works

How Hazel connects to Gorgias.

Connect from the Hazel app using your Gorgias account subdomain plus an admin login. One-time setup; once Hazel has admin read access, all channels and ticket fields are picked up automatically.

What syncs.

Full historical tickets, message threads, tags, ticket fields, CSAT responses, first response time, resolution time, agent activity, and every support channel (email, chat, social, phone). No cap on lookback. Hazel pulls your whole helpdesk history.

How often.

Roughly every 6 hours, automatically.

How agent metrics work.

Hazel separates Gorgias AI Agent autoreplies from human agent messages, so first response time, resolution time, one-touch rate, and CSAT-by-agent reflect actual team performance rather than being inflated by Gorgias Automate activity.

CSAT coverage.

Satisfaction scores only exist for tickets where the customer responded to the CSAT survey. Hazel reports CSAT against the responded-to sample, not against all tickets, so the number is real, and you can ask Hazel for the response rate alongside the score.

Auth.

Admin login plus your Gorgias subdomain. Hazel only reads your helpdesk; it never writes tickets, replies, or tag changes back to Gorgias.

MCP access

Looking for a Gorgias MCP for analytics?

A handful of vendors (Zapier, Composio, Improvado, Pipedream, MCPBundles) ship Gorgias MCP servers that let an LLM create tickets, update customers, tag conversations, or fetch ticket data on demand. Those are useful when you want an agent to *act* on Gorgias as part of a workflow.

Hazel takes a different approach.

Instead of giving an LLM raw API access to Gorgias on every prompt, Hazel pre-ingests your full helpdesk into an analytical store, separates Gorgias AI Agent activity from human work, and joins your support data with Shopify orders, ad spend, Klaviyo email, subscriptions (Recharge, Skio, Stay AI), and reviews (Yotpo, Okendo). Your team gets one conversational interface for the business questions a CX leader actually asks. Ticket volume trends, top contact drivers, products that generate the most tickets, seasonal projections, agent performance. No MCP setup, no per-prompt rate limits, no schema discovery, and the same analyst answers questions across every source you've connected.

If you specifically want MCP access to Hazel itself, that's available too. Ping us at https://calendly.com/clint-dunn/clint-hazel-intro.

Frequently asked questions

Does Hazel work with Gorgias?

Yes. Connect Hazel with your Gorgias subdomain and an admin login. Setup is one-time and Hazel picks up every channel and ticket field automatically.

How is Hazel different from Gorgias Statistics and Gorgias AI Agent reports?

Gorgias Statistics and the Gorgias AI Agent performance dashboard are great for live dashboards, AI Agent coverage and success rates, and standard support KPIs inside the helpdesk. Hazel goes deeper: it ingests your full ticket and message history into an analytical store, summarizes free-text conversations (cancellation reasons, product complaints, WISMO themes), joins your support data with Shopify orders, ad spend, Klaviyo email, subscriptions, and reviews, and answers ad-hoc business questions Gorgias Statistics isn't built for. Like "which products generate the most tickets per 1K orders" or "project ticket volume for the week before and after Mother's Day based on last year."

Gorgias is unifying its own analytics in 2026. Does Hazel still matter?

Yes. Gorgias is building a unified view across helpdesk, Gorgias Voice, and Gorgias AI Agent, and that's a good thing for support teams. Hazel extends that picture out to Shopify orders, Meta Ads and Google Ads, subscriptions (Recharge, Skio), and reviews (Yotpo). The questions that live outside Gorgias's data boundary. Gorgias tells you what's happening in the helpdesk; Hazel tells you why it's happening across the business.

How is Hazel different from eesel AI?

eesel AI is a Gorgias-specialized analytics and agent platform. If Gorgias is your only data source, eesel is purpose-built for it. Hazel is for brands that want one conversational analyst across Gorgias, Shopify, ad spend, subscriptions, email, and reviews, so questions that cross sources ("which products generate the most tickets per 1K orders and what's the return rate on those same SKUs?") get answered in one prompt. Gorgias ships its own Gorgias AI Agent ($0.90/resolution autoresolution) and third parties like eesel, Lindy, and Fleece ship agents that plug into Gorgias. Hazel is neither. Hazel is analytics on top of all of it.

How is Hazel different from Sentisum, MaestroQA, or other Gorgias analytics add-ons?

Those tools are Gorgias-focused and report-focused. You still pivot in a dashboard. Hazel is analyst-first and source-agnostic: ask any business question that touches CX, and Hazel answers in plain English, pulling Shopify, ads, subscriptions, or reviews into the same answer when the question crosses sources.

How does Hazel separate Gorgias AI Agent metrics from human agent metrics?

Hazel identifies which messages and resolutions came from Gorgias AI Agent versus your human team. That means first response time, resolution time, one-touch rate, and CSAT-by-agent reflect actual team performance rather than being inflated by Gorgias Automate autoreplies. You can ask Hazel for the split directly. "what percentage of tickets were fully resolved by Gorgias AI Agent vs. handled by a person?", or filter any metric to human-only or AI-only.

How does Hazel pricing compare to Gorgias AI Agent's per-resolution cost?

Different budget lines. Gorgias AI Agent is automation. It resolves tickets at $0.90/resolution. Hazel is analytics. It answers your business questions about CX data at a flat annual fee with unlimited seats and connectors. Most brands run both: Gorgias AI Agent handles the tickets, Hazel tells you what the ticket data means.

How often does Hazel pull data from Gorgias?

Roughly every 6 hours.

Will Hazel write data back to my Gorgias account?

No. Hazel only reads. We never create tickets, send replies, or modify tags in your helpdesk.

Does Hazel cover all my support channels?

Yes. Email, chat, social, and Gorgias Voice all pull simultaneously. You can ask Hazel for volume by channel, CSAT by channel, or response time by channel without any extra setup.

Why don't all my tickets have a CSAT score in Hazel?

Gorgias only records CSAT when a customer responds to the survey. Hazel reports against the responded-to sample, so the number is accurate, and you can ask Hazel for the CSAT response rate alongside the score.

Can Hazel summarize ticket content, not just count tickets?

Yes. Hazel reads message threads, so you can ask things like "what are the top reasons customers gave for canceling subscriptions" or "summarize the most common complaints in tickets tagged 'shipping' over the past 30 days" and get a real answer drawn from the actual conversation text.

Can Hazel join Gorgias data with Shopify?

Yes. Tickets per 1K orders, products driving the most tickets, WISMO volume vs. shipment volume, and cancellation reasons cross-referenced with subscription status are all one prompt. Connect Shopify and Gorgias and the join happens automatically.

How do I get started?

Book a call and we'll walk through your Gorgias setup, the CX questions you want answered, and what the rollout looks like.