

A few things to know before you connect Gorgias MCP:
Ask your helpdesk anything, and get a real answer from your actual data in seconds.
Gorgias MCP connects your Gorgias account directly to Claude, ChatGPT, Cursor, or any other MCP-compatible AI tool. No more exporting data or re-explaining context every time you need a different angle on your tickets. Ask a question, follow up, and execute, all in the same conversation.
This guide covers what Gorgias MCP is, how to connect it, and six specific workflows you can run in your first session.
The Model Context Protocol (MCP) enables AI systems to link directly with other tools.
The Gorgias MCP provides a first-party bridge, giving you a secure, direct connection between your chosen AI assistant and your Gorgias account.
Once connected, your LLM of choice can:
Setup takes about five minutes. Here is what you need and how to do it.
What you need:
Steps:
The exact steps vary slightly depending on which AI tool you use.
Read more: The Gorgias MCP setup guide specifically walks through Claude, ChatGPT, and Cursor.
Each workflow below includes the exact prompt to copy. Adjust the specifics to match your store, and run it in your first session.
CSAT dips are easy to spot in your dashboard. The cause is harder. Figuring it out usually means opening tickets one by one, building a custom filter, and reading through results one by one.
The prompt:
What you get: A grouped breakdown of the patterns behind your low scores, based on what customers wrote.
Follow-up prompts:
Handoff reports tell you how many tickets AI Agent escalated to your team. They rarely tell you why. Diagnosing the root cause and writing new guidance to fix it are usually two separate tasks that happen days apart, if at all.
With Gorgias MCP, you can do both in the same conversation.
The prompt:
Then, without starting a new chat:
What you get: A diagnosis of where AI Agent is struggling and a ready-to-review draft guidance to address the top gap. You apply it manually in Gorgias, but the thinking is done.
Follow-up prompts:
This is one of the most powerful early use cases customers have found. By connecting Gorgias MCP with the Shopify MCP, you can link what customers complain about in tickets to the product pages where that friction lives.
To use this workflow, connect both Gorgias MCP and Shopify MCP oto your AI tool first.
The prompt:
What you get: A prioritized list of friction points tied to specific content gaps on your product pages, ready to hand off to your product or merchandising team.
Follow-up prompts:
Gorgias's built-in reports cover the core metrics well. But when you need a specific cut, ticket volume by intent for a particular channel, or resolution time broken down by tag, getting there requires an export and a spreadsheet.
Ask for exactly what you need instead.
The prompt:
What you get: A custom breakdown you can copy directly into a slide or share with your team, built from a single question.
Follow-up prompts:
Every support inbox has repeat questions that agents are still answering manually. Some of those topics may already have a macro, but others show up again and again without consistent macro usage. This workflow helps surface the best candidates to standardize next.
The prompt:
What you get: A ranked list of frequent support topics that appear to be handled manually most of the time, helping your team prioritize where a new or better macro could save the most effort.
Follow-up prompts:
Tag libraries tend to grow organically. Over time, teams end up with overlapping labels like “return,” “returns,” and “return-request,” along with tags that are rarely used and naming patterns that make reporting harder to trust. This workflow helps identify cleanup opportunities based on how tags are actually used on tickets.
The prompt:
What you get: A list of likely tag issues grouped by type — duplicates, low-use tags, and inconsistent naming — based on actual ticket usage, with consolidation suggestions your team can act on.
Follow-up prompts:
Everything in the workflows above is already sitting in your Gorgias account. Gorgias MCP just makes it conversational.
Not sure where to start? Try workflow 1 (CSAT drop report) or workflow 6 (tag cleanup) first. Both deliver results quickly and work regardless of how your account is configured.
Gorgias MCP is currently in open beta and available to all paid plan customers.
TL;DR:
Getting more out of your Zendesk AI Agent comes down to better configuration. The problem is that auditing your own setup requires time you don't have.
Gaia for Zendesk is a free Chrome extension from Gorgias that clears that backlog in minutes. It connects to your Zendesk account, reads your tickets, and generates the components your AI Agent needs to resolve more conversations without escalation.
Below, you'll find everything you need to get started: how to install Gaia, what it can do, and the use cases teams are already putting it to work for.
Jump to:
Zendesk Suite admins and agents who want to set up or improve their Zendesk AI Agent (and, optionally, Zendesk Copilot).
Throughout this article, "AI Agent" refers to Zendesk's own AI Agent feature, not Gorgias's product. Gaia is the Gorgias-built Chrome extension that helps you configure it.
Gaia for Zendesk is a free Chrome extension built by Gorgias that connects to your Zendesk account and analyzes your real ticket history.
It autonomously transforms that data into the core components your Zendesk AI Agent needs to resolve more tickets without human intervention: guidances, instructions, voice-of-customer insights, and Copilot procedures.
Gaia opens automatically as a side panel on any .zendesk.com page. You choose a workflow, Gaia runs the analysis and generates structured drafts, and you review and approve what should be applied to your Zendesk workspace.
What Gaia can do:
Good to know: Gaia is autonomous in how it analyzes your data and generates recommendations, but nothing is applied without your approval.
How well your AI Agent performs comes down to how well it is configured. Clear instructions, well-defined intents, and up-to-date procedures are what separate an AI Agent that resolves tickets from one that escalates them — and building that foundation manually takes time most teams do not have.
Gaia removes that constraint by turning your existing support data into structured, ready-to-review outputs:
Tip: Teams that define five or more strong guidances typically see a meaningful lift in the share of tickets their AI Agent resolves without escalation. Gaia is designed to help you reach and expand beyond that baseline quickly.
Installation takes about five minutes. You'll need admin access to your Zendesk account to generate an API token.
Make sure you're using Google Chrome or another Chromium-based browser (such as Edge or Brave). Gaia is not available for Safari or Firefox at launch.
Follow these steps:
1. Install the Gaia for Zendesk extension. Go to the Chrome Web Store listing for Gaia for Zendesk by Gorgias and click Add to Chrome. Confirm the permissions to complete installation.
2. Generate a Zendesk API token. In Zendesk, navigate to Admin Center › Apps and integrations › Zendesk API. Enable Token access if needed, then click Add API token. Copy and store the token securely (it will not be visible again).
3. Open the Gaia extension and add your credentials. Click the Gaia icon in your Chrome toolbar, then open Settings. Enter:
4. Click Save. Gaia will validate the connection.
5. Open any Zendesk page. Navigate to any page in your Zendesk account. Gaia will appear as a side panel where you can select a workflow and begin.
Here are the four most common ways teams use Gaia for Zendesk.
Best for: Teams already using Zendesk AI Agent or Answer Bot but not reaching their automation goals
Select Improve my AI Agent. Gaia analyzes escalated tickets against your current guidances to identify missing intents, unclear instructions, and outdated logic, then proposes prioritized improvements.
Best for: Teams starting without an established AI configuration
Select Create my first instructions. Gaia generates a foundational set of 15 instructions covering common ecommerce scenarios (order status, refunds, cancellations, shipping, returns).
Best for: Support, CX, and operations teams planning improvements or reporting on performance
Select Analyze my tickets. Gaia summarizes ticket volume, top intents, and escalation drivers to highlight where automation or process improvements will have the greatest impact.
Best for: Teams using Zendesk Copilot who want consistent, scalable agent workflows
Requires the Copilot add-on in Zendesk. Select Create my first procedures. Gaia converts real agent behavior into structured WHEN/IF/THEN procedures that standardize how common scenarios are handled.
Gaia connects to your Zendesk account, reads your ticket history, and shows you exactly where your setup is falling short. Install the free Chrome extension and run your first analysis in under a minute.
The best in CX and ecommerce, right to your inbox

TL;DR:
Your ticket volume number is probably wrong. If customers are reaching you through email forwards, Slack DMs, or channels that bypass your helpdesk, those tickets aren't being counted, and your SLA reporting is built on incomplete data. This guide covers how to get an accurate count, break it down by channel and category, and use your vertical benchmark to figure out whether your volume is actually a problem or just normal for your industry.
Ticket volume is the total number of customer inquiries your support team receives across all channels — email, live chat, phone, social media, and contact forms — within a specific time period. It is the most direct measure of your team's workload.
Do not confuse it with contact rate. Contact rate = tickets ÷ orders (or customers). That normalized number is more useful for benchmarking and planning because it accounts for business growth. Raw ticket volume tells you how busy your team is. Contact rate tells you whether support demand is outpacing your business.
Start by looking at the last 30 days of customer conversations, no matter where they currently live.
Pull these four numbers:
Here’s how to pull that data depending on your setup:
Open your inbox or Sent folder and filter by the last 30 days. Count how many customer conversations came in during that period. You can also copy subject lines into ChatGPT or Claude to group conversations by topic.
Go to Inbox > Conversations and review your recent conversations. Count how many messages you received and look for repeated themes or questions.
Most helpdesks have ticket reporting or exports built in. Search “export tickets” or “ticket report” in your platform’s help center. From there, you can pull:
If a large portion of customer questions are still happening in untracked places like Slack DMs, personal inboxes, or Instagram comments, your reporting is incomplete. Before optimizing support operations, route customer conversations into one shared system so you can accurately measure volume, response times, and recurring issues.
A raw ticket count tells you how busy your team is. The breakdown tells you what to fix.
|
Category |
What high volume signals |
What to do |
|
"Where is my order?" |
No proactive shipping updates; poor tracking page |
Automate WISMO with AI Agent; add tracking link to order confirmation |
|
Returns and exchanges |
Confusing return policy; no self-serve portal |
Add a clear returns page; enable self-serve exchange flows |
|
Sizing and product questions |
Weak product page content |
Add size guides, FAQs, and fit notes directly on product pages |
|
Account and subscription issues |
Customers can't self-serve basic account changes |
Build or improve your Help Center; enable self-serve account management |
|
Payment and billing |
Checkout friction or unclear pricing |
Fix at the source — this is rarely a support problem |
Run this categorization for your last 30 days. Your top two or three categories are your highest-leverage targets.
Ticket volume only tells part of the story. Track it alongside:
Once you know what is driving your volume, address each category at the source. The goal is to eliminate unnecessary tickets.
Automate the highest-volume, lowest-complexity tickets first. WISMO inquiries, order status checks, and basic return initiations require no agent judgment. An AI Agent connected to your ecommerce platform can handle these end-to-end without a human stepping in. When a question is too complex, the AI escalates it with full context attached.
Build self-service content around your top categories. A Help Center that directly addresses your most common ticket types is the highest-leverage tool for sustained volume reduction. Start with your top five categories. Write one article per category. Surface those articles on relevant product pages, in checkout, and in post-purchase emails — before customers need to search.
Send proactive messages at the moments that generate the most tickets. Post-purchase is the single highest-value touchpoint: an order confirmation that includes a tracking link, estimated delivery window, and a clear link to your return policy eliminates a large share of inbound questions before they are ever submitted.
Measure deflection, not just volume. Deflection rate, the percentage of issues resolved through self-service or automation, is the metric that tells you whether your volume reduction efforts are actually working. Track it weekly alongside CSAT for automated interactions to make sure quality is holding.
The all-industry average is not your benchmark. Ticket volume per 100 orders varies 2.4x across verticals, so comparing yourself to a cross-industry number will either make you complacent or create false urgency.
According to Gorgias platform data from March 2026 across 14 verticals at the $10M GMV band, here is what tickets per 100 orders actually looks like by vertical:
|
Vertical |
Tickets per 100 orders |
|
Electronics |
46 |
|
Vehicles & Parts |
46 |
|
Hardware |
41 |
|
Luggage & Bags |
32 |
|
Home & Garden |
32 |
|
Sporting Goods |
32 |
|
Baby & Toddler |
24 |
|
Business & Industrial |
25 |
|
Animals & Pet Supplies |
25 |
|
Apparel & Accessories |
22 |
|
Health & Beauty |
21 |
|
Arts & Entertainment |
21 |
|
Food & Beverages |
20 |
|
Toys & Games |
19 |
Source: Gorgias Ecom Lab, March 2026
High ticket volume is not always a sign of poor CX — it often reflects product complexity. Electronics brands generate nearly one ticket per two orders because customers have more pre- and post-purchase questions about technical products. Food and Beverage brands generate about one in five. That gap is not a performance difference; it is a category difference.
The right question is not "are we below 10 tickets per 100 orders?" It is "are we above or below our vertical peers?" Find your row. That is your baseline. Then use the reduction tactics above to move below it.
If your ticketing tool uses usage-based pricing, where your bill scales with ticket volume rather than agent headcount, forecasting volume directly affects your budget.
The core formula is simple:
Projected tickets = projected orders × (tickets per 100 orders ÷ 100)
So if you expect 2,000 orders next month and your vertical median is 22 tickets per 100 orders, your forecast is approximately 440 tickets.
But a flat monthly estimate misses the real risk: peak seasons. A volume spike during BFCM that triples your order volume will also triple your ticket count — and your bill — unless you have guardrails in place.
To build a more accurate forecast:
Before signing any usage-based contract, ask two questions: What counts as a billable ticket? And is there a hard cap on monthly charges? Variable billing only works in your favor if you have clear definitions of what triggers a charge and a ceiling on how high costs can go during an unexpected spike.
If your platform bills per ticket resolved by a human agent (not AI), your deflection rate becomes a financial metric, not just an operational one. Every percentage point of additional deflection directly reduces your bill.
Begin by identifying your top ticket categories, then work backward to find the root cause of each one.
From there, layer in self-service content, automation, and proactive messaging to address those root causes directly. The result is a support operation that handles more customers and a team that spends its time on the work that actually requires human judgment.
Book a demo to see how Gorgias helps ecommerce brands reduce ticket volume and improve customer experience at the same time.
{{lead-magnet-2}}

TL;DR:
If you're wondering what it costs to add AI Agent to your Helpdesk, you're in the right place. This article walks through how pricing works, what counts as a billable interaction, and how to think about the investment before talking to anyone on our team.
The good news: there are no seat fees, no per-message charges, and no token-based billing. You pay for conversations your AI actually resolves. If you've looked into other AI tools for customer support and found the pricing models confusing or hard to predict, Gorgias AI Agent works differently.
A billable interaction is counted when the AI resolves a customer conversation entirely on its own. The customer asks something, the AI handles it, the conversation closes. That's one interaction.
If the AI can't fully resolve a conversation and hands it to a human agent, that ticket shifts over to your regular Helpdesk plan. It becomes a standard resolved ticket. You're not charged for both.
A few things that don't count as billable interactions:
This matters most for brands coming from seat-based tools. With Gorgias, your whole team can work in the platform. Agent seats are unlimited. Pricing scales with what your AI is actually doing, not with how many people have access.
Understand the difference between seat-based vs. usage-based pricing.
AI Agent is an add-on to your Gorgias Helpdesk plan. The two are priced separately but work together. Your Helpdesk plan covers all the conversations your human agents resolve. Your AI Agent plan covers the interactions the AI resolves on its own.
When you choose a plan, you select how many automated interactions you want included per month. Depending on your plan, that ranges from 90 to 2,500+ interactions, with custom interaction numbers available for enterprise. You can see the full breakdown on the Gorgias pricing page.
Each resolved conversation costs $0.90 on most plans. Starter plans begin at $1 per resolved conversation. You only pay for fully automated interactions, meaning conversations the AI handles from start to finish without a human stepping in.
The main input is your average monthly ticket volume. From there, you estimate how many of those conversations AI could realistically handle on its own.
Order status updates, return requests, and shipping questions tend to be the highest-volume ticket types AI resolves well. AI Agent actions shows the full range of what it can handle, which makes it easier to estimate your starting number.
Your actual automation rate, meaning the share of total tickets the AI ends up resolving, emerges from usage over time. Most brands start with their most repetitive ticket types and expand from there as they see results.
Related: Which Gorgias plan should you choose?
You're charged an overage fee for each additional automated interaction if you exceed your plan's baseline in a given month. The exact rate depends on your plan tier and whether you're on a monthly or annual subscription.
Generally, the higher your plan tier, the lower your overage rate. Annual plans also carry lower overage rates than monthly plans. So if you're regularly going over, upgrading to a higher tier or switching to annual often works out cheaper than paying overage fees month after month.
If you're on a Support + Shopping Assistant plan, the overage rate is $1.50 per interaction across all paid tiers. If you're on a Support-only plan, rates range from $1.00 to $2.00 per interaction on monthly plans, and $0.83 to $1.67 on annual plans, depending on your tier.
For seasonal businesses, forecasting your customer service volume before peak periods is the best way to choose the right plan size and avoid unexpected fees.
At $0.90 per resolved interaction on most plans, each AI resolution costs less than a human agent handling the same ticket. Once you know what a human-resolved ticket costs your business, the comparison becomes straightforward.
For brands building an internal case for the investment, how to pitch AI Agent to your boss covers the ROI framing in detail.
To see what results look like in practice, how 10 brands transformed customer support into revenue has real ecommerce examples.
AI Agent comes with everything you need to set it up, customize it, and improve it over time:
Learn more: Gorgias AI Agent guardrails: What they are and how to configure them
The best way to get a sense of what AI Agent will cost is to look at your own ticket volume and the types of questions your customers ask most. From there, the right plan becomes much clearer.
If you want to talk through the numbers with someone from our team, book a demo and we'll walk through it with you.
If you'd rather keep exploring first, here are a few good next reads:
{{lead-magnet-2}}

TL;DR:
Helpdesk 2.0 starts with the people who use it most: the agents.
We spent time understanding customer support from the agent's seat. What do they reach for constantly? What slows them down? What does a better workday look like?
Everything we found is in this brand-new update.
Conversational commerce is the new standard.
In customer support, this means customers expect context to remain intact wherever they reach out, whether a conversation starts on social, moves to email, or ends on a call.
This new approach to support has also changed the agent's role. Recurring tickets, like order status checks, shipping updates, and returns, are now handled by AI. What lands in the agent inbox are edge cases that require human judgment and troubleshooting, or tickets that require the full picture.
However, the original Helpdesk was built for a different era of support.
Context was separated across views rather than built into the conversation itself. It's something one in five Gorgias customers flagged, through support tickets, NPS surveys, and conversations with our team. So, we got to work.
Helpdesk 2.0 is the result.
Here's a look at everything that changed.
Conversations have a natural rhythm, one that’s already found in every messaging tool we use. We brought that same layout into the helpdesk.
Say goodbye to the 2000s email interface and hello to chat bubbles. This updated design changes how quickly you can orient yourself and resolve the ticket in one go.

Chats with customers now look like real conversations, using the speech bubble style you’re familiar with on popular messaging apps.
Checking a customer's history used to mean leaving the conversation, an extra step that interrupted what should have been a smooth workflow.
Now, past conversations open in a sidebar next to the active conversation. You can view a customer’s full history, search through their timeline, and open prior tickets without going to a new page.

Check past conversations, orders, and customer details in the brand-new Customer Timeline.
Order information is easier to reference than ever. Open a ticket, and you instantly see the customer's recent orders, marked with product images and invoice details at a glance. Need to dig deeper? Click on an order, and the expanded information appears in the same panel.
For teams using custom integrations, apps are fixed in a quick-access integration menu on the right.

See order details, product images, and totals at a glance on the right panel, without leaving the conversation.
You shouldn't have to dig through a thread to figure out what AI already tried. Now you don't have to.
When AI Agent escalates a conversation, it includes a concise handover summary that mentions the issue, what actions were taken, and why it was passed to your team.

Escalated tickets include a brief AI-generated handover summary, marked in yellow, for quick reference.
We restructured and simplified the navigation. The left sidebar organizes everything into clear categories: Inbox, AI Agent, Marketing, and Analytics, so anyone on your team knows exactly where to go.
To quickly update your knowledge base or adjust a workflow, both now live right in the sidebar. For teams managing multiple stores, switching between them is just as straightforward, accessible from the sidebar, so agents can move between inboxes without breaking their flow.

Agents can switch between stores and their corresponding inboxes directly from the left menu.
Support comes down to the person on the other end of the conversation. We built Helpdesk 2.0 is to make sure they have everything they need to show up for that moment.
The best way to see the difference is to work in it. Start a free trial today.

At Gorgias we've been very fortunate to work with some amazing people who did their internship with us:
Amit Poonia
Astrid Parmentier
Emilie Drouin
Hadrien de Lamotte
Ram Goli
Thank you all for your work!
Their contributions big and small make an indispensable part of what Gorgias is today and what it will be in the future. We are very grateful for their hard work, and we want to continue working with them after they finish their studies. To make returning more attractive for them, we've decided to take into account their stock option vesting period if they ever decide to return as full-time employees.
Interns that decide to return to Gorgias within a limited amount of time and choose to take our stock options offer upon the start of their full-time employment will have an accelerated schedule of their stock option vesting period. The offer will be judged case by case with our board's approval.
Let's take the example from our friends at Cockroach Labs (which this decision was inspired from):
For example, our standard option vesting schedule is that 25% of the stock options vests after 12 months of service from an employee’s start date (the “cliff”), and the remaining option vests in equal installments over the following 36 months of continuous service. However, if an intern spent four months with us, on their hire date, they would only have eight months until they hit their one-year cliff date and vest 25%.
We hope that by doing so, we're showing that we're taking their time seriously and we show our intention to work with them beyond their internship.

Recharge is the most popular subscription app in the Shopify app store and is the preferred solution for Shopify Plus stores. Over 10,000 Shopify merchants chose ReCharge to help sell products on a recurring basis, including stores like Dr. Axe, Hubble Contacts, and 5 Hour Energy.
The challenge is, when a customer has an issue with their subscription, the support team needs to jump between their helpdesk, Shopify and the ReCharge platform to fix the problem. This negatively impacts response time. Agents end up wasting hours per week going to ReCharge to skip a box for a customer, edit a subscription, etc. One of the key advantages of using Gorgias is to manage all your customer support in one place. A few months ago, our customer Darn Good Yarn asked us to build an integration with ReCharge. They no longer wanted to switch between ReCharge, Shopify and their helpdesk. This was completely aligned with our vision, so we decided to build it.
Today, we're excited to announce we've partnered with ReCharge to launch this integration.
Here are the key benefits:
“Gorgias gives us a holistic view of our customers. This way we can provide them with fast and personalized help”
Nicole Snow, DarnGoodYarn
Let’s take the example of Averill John. She wants to cancel her subscription to the Yummy Box and has just sent an email to your support.
Here is how your helpdesk looks like:

You can see that Astrid has been assigned to this ticket and that this ticket is tagged “Ambassador”. It means that Averill is one of your super loyal customers.
On the right, you can see the ReCharge account data of Averill. Here, Averill has a monthly subscription to the Yummy Box and will be charged on the 15th of October.
Astrid can skip the October charge in one-click on the “Skip charge on subscription” button. It will immediately set the action within ReCharge. Response time? Less than 1 minute!
If you're already a Gorgias customer, head to your account and go to Integrations to connect ReCharge. If not, you can create an account here and get started in a few minutes.

One of the key advantages of using Gorgias is to provide a unified support experience to your customers across all channels. A few months ago, some of our customers asked us to build a phone integration. Traditional helpdesk integrations simply log calls as tickets. We wanted to go one step further and associate the phone call with the right customer.
Today, we're excited to announce we've partnered with Aircall to build this integration.
Aircall arms small-to-medium sized business (SMBs) with a phone system built for modern business. With zero hardware to manage, dozens of integration options to explore, and the ability to add local numbers in more than 40 countries, support teams can easily provide phone support in minutes.

Here are the benefits of this new integration:
If you're already a Gorgias customer, head to your account and go to Integrations to connect Aircall. If not, you can create an account here and get started in a few minutes.

Today, we’re thrilled to announce we’re joining the Shopify Plus Technology partner program.
Over the past few months, we’ve worked with some incredible Shopify Plus merchants like Darn Good Yarn, Fjallraven and Frichti, who serve tens of thousands of customers every month. What they all had in common was a shared commitment to maximizing the efficiency of the customer service team to keep delivering high-quality support as they grow.
We’ve worked with other technology partners, like LoyaltyLion, in order to provide merchants with a holistic view of their customers when they respond to them in an effort to continue delivering best-in-class support interactions. We’ve also worked with the Plus team to leverage the latest features of the Shopify Plus API, to allow agents to create customized solutions for their customers, For example, creating personalized gift cards based on support conversations. Also, check out the guide we wrote comparing Shopify and Shopify Plus for an idea of the additional functionality and benefits ecommerce business owners get when they upgrade to Shopify Plus.
Using our technology, we’re proud to announce that our Shopify Plus customers have managed to improve their support request treatment time by 30%.
By joining the Technology Partner Program, we’re excited to take our collaboration with Shopify Plus and Shopify Plus merchants to the next level, by further enabling more customers to improve their customer service.
"We are glad to welcome Gorgias to the Shopify Plus Technology Partner Program. We’re particularly excited about how they’re helping our merchants provide efficient & personalized customer support, and hope they can help more of them."
Jamie Sutton, Head of Technology Partnerships, Shopify Plus

Great news! Today, we're announcing a new integration with LoyaltyLion. LoyaltyLion is a digital loyalty framework that gives ecommerce stores innovative ways to engage and retain customers.
Our mutual customer Darn Good Yarn uses it to successfully increase customer retention. When they switched from Freshdesk to Gorgias to manage customer support, they wanted to leverage their loyalty program for customer support.
We used their feedback to build the integration with LoyaltyLion, which they have been using for a couple months in beta. Today, we're excited to make it available to all our users.
Here are some of the benefits of this integration:

Overall, this allows your team to use your loyalty program for customer service.
"We love being able to issue our customers loyalty points directly from Gorgias! It's a great way to boost efficiency and also customer retention."
Chloe Kesler, Customer Support manager at Darn Good Yarn
The integration is immediately available on your Gorgias account. If you don't have an account, you can create one here. Then, follow the instructions in our documentation and you can get started!
.avif)
Most customers are loyal to brands because they know what level of service they can expect. As a result, providing an above-average customer experience is key to increase repeat in sales.
It’s relatively easy to provide great support when you get started with your store: your team gets a few dozens of support requests a day, and they respond to them almost instantly. The thing is, this level of service is very hard to maintain as you scale. Response time usually drops, and most brands start using standardized macros to keep up with the pace, which is a poor customer experience.
Your sales have increased, good. Now, you need to get your customer support up to speed

Source: Gorgias customers during the Thanksgiving peak
At Gorgias, we’ve been chatting with 400 stores over the past year, and we’ve seen a lot of them working on crossing this “chasm”.
This post shares learning on how you can build a customer support organization that will scale with your business, and provide best-in-class customer service, which will drive customer retention.
A good place to start is to list the most common reasons customers are contacting you about. Go ahead and manually classify 200 tickets from your support inbox. This should take you about an hour. You can build categories from scratch, or use this spreadsheet of the most common requests for e-commerce companies we built.

Now, you should be able to understand what problems are causing the most pain to customers.
If a specific type of request is above 10% of requests, then it’s a good candidate for optimization. For instance, if you’re getting a lot of “where is my order” questions, here are a few things you can do to deflect those:
Now that you have a good understanding of the reasons customers are contacting you for, you can map the customer journey, and identify what actions your agents need to take to respond to tickets.
Later, you can use this for training purposes, and to identify optimization opportunities.
At Piper, we basically studied the whole customer journey and tried to identify all reasons why someone could contact us (based on previous history). This helped us quickly identify where customers were "blocked"
Finally, let’s analyze the efficiency of your team. Of course, every business is different, but you can use this table to figure out how efficient your agents are compared to other stores. A good metric to track it is ticket closed per month. Just make sure that satisfaction remains consistent.

Related: Learn more about the impact of live chat on sales. And see how Gorgias live chat can help you turn more browsers into buyers with chat campaigns.
Now, let’s work on creating “wow moments” for your customers. If you manage to exceed customers expectations when they contact you, you’re most likely to increase their loyalty and have them refer your store to their friends.
Here are a few ways you can create “wow moments”.
You should be where your customers are. For example, if you have a Facebook page with a large audience, consider it as a real customer support channel. The point is, you should provide the same level of assistance across all support channels that your customer will use.
Also, don't be afraid to contact customers first, especially when they have items in their shopping cart. Offering help or a discount code at the right time could make the difference between a sale and an abandoned cart.
Example: providing high quality support on Facebook
70% of customers consider Facebook as a live chat support. To maximize customer satisfaction, your response time should be no more than 1 min. You’ll then be listed as a very responsive page, which will encourage your customers to respond.

You can also leverage public posts to build relationship with your customers. Another easy way to facilitate customer communication is to remove the need for customers to repeat themselves. On your support platform, make sure your merge Facebook conversations with email tickets. This way, if the customer switches channel, your team will have access to the context of what the customer said before.
Related: Check out our trends and best practices for customer support.
You should leverage every data point you have about the customer to personalize the way you communicate with them:
For how long they have been a customer
Their order preference
Their location
The days of the “we value your business” are over.
Always go an extra mile for your customers. If the customer asks for the status of their order, don’t respond only with the tracking number. Go get the order status on UPS so the customer doesn’t have to do it themselves when they’ll receive your email in the subway with poor network connection.

Another good thing to do is to use a specific tone with your customer, that matches the brand image you want to convey.
If you’re into gifs, you can use them to build a brand tone your own set of gifs, designed for your own brand, and use them in your support emails. You can hire an illustrator on Upwork for that, or build them yourself.
Related: Tips to respond to angry customer emails.
Now that you know the level of support you aim at giving your customers, and you know what actions your agents need to take to get the delivery info, create an RMAs, etc., you can start optimizing the process for them.
To personalize messages, your agents need to have access to customer data. You can leverage the standard Shopify integration from your help desk as a starting point.
Though, it can be relevant to connect other data points to your help desk:
If you’re on Zendesk, enabling the Shopify integration is a good start: it shows how much the customer has spent, and the past orders.
Some Gorgias customers have pretty advanced widgets that display data from Shopify, Stitch & Shipstation. This way, all the customer information is available.
You can create custom widgets for your help desk, so that your agents can trigger actions from your help desk. Here are the most helpful actions:
This is a bit more tricky to implement. You need to build a custom app with buttons that will trigger actions - there are some good tutorials for Zendesk, Freshdesk & Help Scout. At Gorgias, we’ve built integrations with Stitch, Shipstation to embed these actions in the product, and enable you to add your own.
Other 3rd party apps like Chargedesk enable you to refund customers in one click.

Our goal here is to improve the customer experience to drive sales. A good way to track the efficiency of your support work is to compare the behavior of customers that have been in contact with customer support from those who have not.
Shopify helps you easily to this. You can create an integration between your help desk and Shopify to tag customers who reach out to support, using the Shopify API. Say you add a “customer_support” tag to them.

Then, you can use Shopify statistics to monitor how the cohort of customers who have been in touch with your support team behaves, and assess the impact of your efforts with customer support.

Another way to proceed is to tag orders that generated a support tickets. This way, if you work on improving delivery notifications, you can monitor the impact.
Building a scalable support team that provides an amazing customer experience takes time.
Try to test different “wow moments”, iterate on the way you personalize messages, on the tone you’re using, and always track your progress. Among the teams we surveyed, several mentioned they managed to increase sales repeat by 30% after implementing these tactics.
Want to learn more about how customer support can improve your conversion rate and lead to more purchases? Check out our guides to ecommerce upselling and Shopify abandoned cart recovery.

Celery just released their API on Github, currently in beta. Here are some of the cool stuff you can do with it in Gorgias.
When you receive an email from a customer, you can connect your Celery account and see customer information (orders, shipping address, etc.). Here’s what it looks like:

To configure it, grab your Celery access_token, head to integrations, and add an HTTP integration using this URL:
https://api.trycelery.com/v2/orders?buyer.email={ticket.requester.email}
Then you can customize the sidebar to only show the Celery data you need to respond to customers. Click the cog and simply drag and drop elements you want to show.

Celery’s API enables you to perform a few actions from your favorite helpdesk:
Here’s an example of how you can cancel an order from Gorgias itself. Say you already have a macro to cancel an order. Add an HTTP action to it, in this case:
https://api.trycelery.com/v2/orders/{ticket.requester.customer.data[0].number}/order_cancel
Then, when you use this macro and send it to the customer, it will automatically cancel the last order at the same time:

We hope this integration with Celery can save you time. If you'd like to try Celery with Gorgias, shoot us a note! At support@gorgias.com.

TLDR: https://github.com/xarg/pghoard-k8s
This is a small tutorial on how to do incremental backups using pghoard for your PostgreSQL (I assume you’re running everything in Kubernetes). This is intended to help people to get started faster and not waste time finding the right dependencies, etc..
pghoard is a PostgreSQL backup daemon that incrementally backups your files on a object storage (S3, Google Cloud Storage, etc..).
For this tutorial what we’re trying to achieve is to upload our PostgreSQL to S3.
First, let’s create our docker image (we’re using the alpine:3.4 image cause it’s small):
FROM alpine:3.4
ENV REPLICA_USER "replica"
ENV REPLICA_PASSWORD "replica"
RUN apk add --no-cache \
bash \
build-base \
python3 \
python3-dev \
ca-certificates \
postgresql \
postgresql-dev \
libffi-dev \
snappy-dev
RUN python3 -m ensurepip && \
rm -r /usr/lib/python*/ensurepip && \
pip3 install --upgrade pip setuptools && \
rm -r /root/.cache && \
pip3 install boto pghoard
COPY pghoard.json /pghoard.json.template
COPY pghoard.sh /
CMD /pghoard.sh
REPLICA_USER and REPLICA_PASSWORD env vars will be replaced later in your Kubernetes conf by whatever your config is in production, I use those values to test locally using docker-compose.
The config pghoard.json which tells where to get your data from and where to upload it and how:
{
"backup_location": "/data",
"backup_sites": {
"default": {
"active_backup_mode": "pg_receivexlog",
"basebackup_count": 2,
"basebackup_interval_hours": 24,
"nodes": [
{
"host": "YOUR-PG-HOST",
"port": 5432,
"user": "replica",
"password": "replica",
"application_name": "pghoard"
}
],
"object_storage": {
"aws_access_key_id": "REPLACE",
"aws_secret_access_key": "REPLACE",
"bucket_name": "REPLACE",
"region": "us-east-1",
"storage_type": "s3"
},
"pg_bin_directory": "/usr/bin"
}
},
"http_address": "127.0.0.1",
"http_port": 16000,
"log_level": "INFO",
"syslog": false,
"syslog_address": "/dev/log",
"syslog_facility": "local2"
}
Obviously replace the values above with your own. And read pghoard docs for more config explanation.
Note: Make sure you have enough space in your /data; use a Google Persistent Volume if you DB is very big.
Launch script which does 2 things:
#!/usr/bin/env bash
set -e
if [ -n "$TESTING" ]; then
echo "Not running backup when testing"
exit 0
fi
cat /pghoard.json.template | sed "s/\"password\": \"replica\"/\"password\": \"${REPLICA_PASSWORD}\"/" | sed "s/\"user\": \"replica\"/\"password\": \"${REPLICA_USER}\"/" > /pghoard.json
pghoard --config /pghoard.json
Once you build and upload your image to gcr.io you’ll need a replication controller to start your pghoard daemon pod:
apiVersion: v1
kind: ReplicationController
metadata:
name: pghoard
spec:
replicas: 1
selector:
app: pghoard
template:
metadata:
labels:
app: pghoard
spec:
containers:
- name: pghoard
env:
- name: REPLICA_USER
value: "replicant"
- name: REPLICA_PASSWORD
value: "The tortoise lays on its back, its belly baking in the hot sun, beating its legs trying to turn itself over. But it can't. Not with out your help. But you're not helping."
image: gcr.io/your-project/pghoard:latest
The reason I use a replication controller is because I want the pod to restart if it fails, if a simple pod is used it will stay dead and you’ll not have backups.
Future to do:
Hope it helps, stay safe and sleep well at night.
Again, repo with the above: https://github.com/xarg/pghoard-k8s


