At Gorgias we recently switched our flask & celery apps from Google Cloud VMs provisioned with Fabric to using docker with kubernetes (k8s). This is a post about our experience doing this.

‍

Note: I'm assuming that you're somewhat familiar with Docker.

‍

Docker structure

The killer feature of Docker for us is that it allows us to make layered binary images of our app. What this means is that you can start with a minimal base image, then make a python image on top of that, then an app image on top of the python one, etc..

‍

Here's the hierarchy of our docker images:

• gorgias/base - we're using phusion/baseimage as a starting base image.
• gorgias/pgbouncer
• gorgias/rabbitmq
• gorgias/nginx - extends gorgias/base and installs NGINX
• gorgias/python - Installs pip, python3.5 - yes, using it in production.
• gorgias/app - This installs all the system dependencies: libpq, libxml, etc.. and then does pip install -r requirements.txt
• gorgias/web - this sets up uWSGI and runs our flask app
• gorgias/worker - Celery worker

‍

Piece of advice: If you used to run your app using supervisord before I would advise to avoid the temptation to do the same with docker, just let your container crash and let k8s handle it.

‍

Now we can run the above images using: docker-compose, docker-swarm, k8s, Mesos, etc...

‍

We chose Kubernetes too

There is an excellent post about the differences between container deployments which also settles for k8s.

‍

I'll also just assume that you already did your homework and you plan to use k8s. But just to put more data out there:

‍

Main reason: We are using Google Cloud already and it provides a ready to use Kubernetes cluster on their cloud.

‍

This is huge as we don't have to manage the k8s cluster and can focus on deploying our apps to production instead.

‍

Let's begin by making a list of what we need to run our app in production:

• Database (Postgres)
• Message queue (RabbitMQ)
• App servers (uWSGI running Flask)
• Web servers (NGINX proxies uWSGI and serves static files)
• Workers (celery)

‍

Why Kubernetes again?

We ran the above in a normal VM environment, why would we need k8s? To understand this, let's dig a bit into what k8s offers:

• A pod is a group of containers (docker, rtk, lxc...) that runs on a Node. It's a group because sometimes you want to run a few containers next to each other. For example we are running uWSGI and NGINX on the same pod (on the same VM and they share the same ip, ports, etc..).
• A Node is a machine (VM or metal) that runs a k8s daemon (minion) that runs the Pods.
• The nodes are managed by the k8s master (which in our case is managed by the container engine from Google).
• Replication Controller or for short rc tells k8s how many pods of a certain type to run. Note that you don't tell k8s where to run them, it's master's job to schedule them. They are also used to do rolling updates, and autoscaling. Pure awesome.
• Services take the exposed ports of your Pods and publishes them (usually to the Public). Now what's cool about a service that it can load-balance the connections to your pods, so you don't need to manage your HAProxy or NGINX. It uses labels to figure out what pods to include in it's pool.
• Labels: The CSS selectors of k8s - use them everywhere!
• ‍

There are more concepts like volumes, claims, secrets, but let's not worry about them for now.

‍

Postgres

We're using Postgres as our main storage and we are not running it using Kubernetes.

‍

Now we are running postgres in k8s (1 hot standby + pghoard), you can ignore the rest of this paragaph.

The reason here is that we wanted to run Postgres using provisioned SSD + high memory instances. We could have created a cluster just for postgres with these types of machines, but it seemed like an overkill.

The philosophy of k8s is that you should design your cluster with the thought that pods/nodes of your cluster are just gonna die randomly. I haven't figured our how to setup Postgres with this constraint in mind. So we're just running it replicated with a hot-standby and doing backups with wall-e for now. If you want to try it with k8s there is a guide here. And make sure you tell us about it.

‍

RabbitMQ

RabbitMQ (used as message broker for Celery) is running on k8s as it's easier (than Postgres) to make a cluster. Not gonna dive into the details. It's using a replication controller to run 3 pods containing rabbitmq instances. This guide helped: https://www.rabbitmq.com/clustering.html

‍

uWSGI & NGINX

As I mentioned before, we're using a replication controller to run 3 pods, each containing uWSGI & NGINX containers duo: gorgias/web & gorgias/nginx. Here's our replication controller web-rc.yaml config:

‍

apiVersion: v1
kind: ReplicationController
metadata:
 name: web
spec:
 replicas: 3 # how many copies of the template below we need to run
 selector:
   app: web
 template:
   metadata:
     labels:
       app: web
   spec:
     containers:
     - name: web
       image: gcr.io/your-project/web:latest # the image that you pushed to Google Container Registry using gcloud docker push
       ports: # these are the exposed ports of your Pods that are later used by the k8s Service
         - containerPort: 3033
           name: "uwsgi"
         - containerPort: 9099
           name: "stats"
     - name: nginx
       image: gcr.io/your-project/nginx:latest
       ports:
         - containerPort: 8000
           name: "http"
         - containerPort: 4430
           name: "https"
       volumeMounts: # this holds our SSL keys to be used with nginx. I haven't found a way to use the http load balancer of google with k8s.  
         - name: "secrets"
           mountPath: "/path/to/secrets"
           readOnly: true
     volumes:
       - name: "secrets"
         secret:
           secretName: "ssl-secret"
And now the web-service.yaml:apiVersion: v1
kind: Service
metadata:
 name: web
spec:
 ports:
 - port: 80
   targetPort: 8000
   name: "http"
   protocol: TCP
 - port: 443
   targetPort: 4430
   name: "https"
   protocol: TCP
 selector:
   app: web
 type: LoadBalancer

‍

That type: LoadBalancer at the end is super important because it tells k8s to request a public IP and route the network to the Pods with the selector=app:web.
If you're doing a rolling-update or just restarting your pods, you don't have to change the service. It will look for pods matching those labels.

‍

Celery

Also a replication controller that runs 4 pods containing a single container: gorgias/worker, but doesn't need a service as it only consumes stuff. Here's our worker-rc.yaml:

‍

apiVersion: v1
kind: ReplicationController
metadata:
 name: worker
spec:
 replicas: 2
 selector:
   app: worker
 template:
   metadata:
     labels:
       app: worker
   spec:
     containers:
     - name: worker
       image: gcr.io/your-project/worker:latest

‍

‍

Some tips

• Installing some python deps take a long time, for stuff like numpy, scipy, etc.. try to install them in your namespace/app container using pip and then do another pip install in the container that extends it, ex: namespace/web, this way you don't have to rebuild all the deps every time you update one package or just update your app.
• Spend some time playing with gcloud and kubectl. This will be the fastest way to learn of google cloud and k8s.
• Base image choice is important. I tried phusion/baseimage and ubuntu/core. Settled for phusion/baseimage because it seems to handle the init part better than ubuntu core. They still feel too heavy. phusion/baseimage is 188MB.

‍

‍

Conclusion

With Kubernetes, docker finally started to make sense to me. It's great because it provides great tools out of the box for doing web app deployment. Replication controllers, Services (with LoadBalancer included), Persistent Volumes, internal DNS. It should have all you need to make a resilient web app fast.

At Gorgias we're building a next generation helpdesk that allows responding 2x faster to common customer requests and having a fast and reliable infrastructure is crucial to achieve our goals.

If you're interested in working with this kind of stuff (especially to improve it): we're hiring!

We've released a new version of the Chrome Extension, with sharing features and a new navigation bar. We hope you'll love it!

‍

Share templates inside the extension

Before, the only way to share templates with your teammates was to login on Gorgias.io.

If you're on the startup plan, when you create a template, you can choose who has access to it: either only you, specific people, or your entire team.

‍

‍

The account management section is now available in the extension, under settings.

‍

New navigation

Tags are now available on the left. It's easier to manage hundreds of templates with them.
You can also navigate through your private & shared templates. Shared templates include templates shared with specific people or with everyone.

‍

‍

We hope you'll enjoy this new version of our Chrome Extension. As usual, your feedback & questions are welcome!

Today, we’re thrilled to announce that we’ve raised a $1.5 million Seed round led by Charles River Ventures and Amplify Partners, to help build our new helpdesk.

‍

We’re incredibly grateful to early users, customers, mentors we’ve met both at and Techstars.

‍

We started the journey with Alex at the beginning of 2015 with our Chrome extension, which helps write email faster using templates. We’ve been pleased all along with customers telling us about how helpful it was, especially for customer support.

‍

While building the extension, we’ve realized that a big inefficiency in support lies in the lack of integration between the helpdesk, the payment system, CRM and other tools support is using. As a result, agents need to do a lot of repetitive work to respond to customer requests, especially when the company is big.

‍

That’s why we’ve decided to build a new kind of helpdesk to enable customer support agents to respond 2x faster to customers. You can find out more and sign up for our private beta here.

‍

When a company has a lot of customers, support becomes repetitive. We want to provide support teams with tools to automate the way they treat simple repetitive requests. This way, they have more time for complex customer issues.

‍

We'll now focus on this helpdesk and on growing the team, oh, and if you'd like to join, we're hiring! We're super excited about this new helpdesk product. If you’re using the extension, don’t worry.

‍

Romain & Alex

We've been busy, but not deaf!

Last few months we got lots of feedback about our extension and found to our delight that most people are satisfied, but still a few recurrent issues came up:

• The HTML/WYSIWYG editor sucks.
• No support for Outlook.com.

‍

We listened and now we're presenting:

• A brand new editor
• Support for outlook.com
• More on the Rich-Text editor

‍

WYSIWYG editors for the web are notoriously buggy and are just difficult to develop.

‍

I have yet to see one that is bug free. There are few venerable editors that do a good job like TinyMCE, FKEditor or CKEditor.. but they are big and all have edge cases that break the intended formatting and add a lot of garbage html.

‍

There are newer good quality editors in town such as Redactor. The one that got my attention and finally landed in Gorgias is this wonderful editor called which is super lightweight, uses modern content-editable (no i-frames) and 'just works' most of the time. That's not to say it's perfect, but it's good enough and I'm satisfied with it's direction in terms of development.

‍

Enjoy it and as always send us bug-reports or feedback on: support@gorgias.com

You're juggling tickets across email, Instagram, live chat, and SMS, and customers still feel like they're being ignored. Every delayed response is a customer deciding whether to come back.

The right helpdesk gives your team one place to work from, cuts out the repetitive back-and-forth, and makes fast, helpful support actually achievable at scale. This guide breaks down the top options so you can find the one that fits where your store is today.

• Best for Shopify brands: Gorgias‍
• Best for enterprise teams: Zendesk‍
• Best for small teams on a budget: Freshdesk‍
• Best for chat campaigns: Intercom‍
• Best for marketplace sellers: eDesk‍
• Best for email-centric teams: Help Scout‍
• Best for self-service automation: Richpanel‍
• Best for social commerce brands: Re:amaze‍
• Best for luxury brands: Gladly‍
• Best for CRM-focused enterprise brands: Kustomer

How we evaluated the best ecommerce helpdesks

An ecommerce helpdesk is a software platform that manages all customer support conversations in one place. This means email, chat, social media, and phone calls all flow into a single inbox where your team can respond quickly and consistently.

We tested each platform with real stores to see how they handle the daily challenges ecommerce teams face. Our focus was on features that matter most to ecommerce brands, not generic helpdesk capabilities that work for any industry.

Here's what we looked for:

• Ecommerce platform connections: How well does it connect to Shopify, BigCommerce, and other store platforms?
• AI and automation quality: Can it resolve common questions without human help?
• Revenue-driving features: Does it help increase sales through upsells and recommendations?
• Setup and learning curve: How quickly can your team start using it?
• Transparent pricing: Are there hidden costs?
• Support during implementation: Do they help you succeed or leave you to figure it out on your own?

Comparison of the best ecommerce helpdesk software

The 10 best ecommerce helpdesk platforms for online stores

Choosing the right helpdesk shapes how your customers experience your brand. The wrong choice creates friction and missed sales opportunities. The right one turns every conversation into a chance to build loyalty and drive revenue.

1. Gorgias

Gorgias is a conversational commerce platform built specifically for ecommerce brands. As Shopify's only Premium CX partner, this means it's designed from the ground up to handle the unique needs of online stores, and powered by conversational AI.

What sets Gorgias apart is its dual focus on customer support and revenue generation. While other platforms just help you answer questions faster, Gorgias helps you turn those conversations into sales. Its AI Agent can resolve up to 60% of common tickets while maintaining your brand voice and suggesting relevant products to shoppers.

The Shopify integration runs deeper than any competitor. You can view orders, process refunds, apply discounts, and update shipping addresses all without leaving your helpdesk. Your team saves time and customers get faster resolutions.

Main features:

• Unified inbox for email, chat, SMS, voice, and social media
• Self-service Help Center and article generation
• Advanced automation Rules, Macros, and dynamic Shopify variables
• In-depth reporting with revenue attribution, support performance metrics, and AI statistics

AI features:

• AI Agent handles common questions, from WISMO to returns
• Trained on your brand's knowledge base and policies — not generic chatbot data
• Adjustable tone of voice
• Native Shopify integration for in-app order management
• Revenue tools like Shopping Assistant provide tailored product recommendations

Best for:

• Shopify and Shopify Plus stores
• Brands that want support to drive revenue
• Teams handling 50+ tickets daily
• Stores planning to scale quickly

Pricing:

• Starter: $10/month (50 tickets)
• Basic: $60/month (300 tickets)
• Pro: $360/month (2,000 tickets)
• Advanced: $900/month (5,000 tickets)
• Enterprise: Custom pricing

2. Zendesk

Best for: Large enterprises with dedicated IT teams who need extensive customization

Zendesk is one of the most well-known helpdesk companies out there. It serves every industry, from airlines to banks, which gives it powerful customization options but might also feel unintuitive for ecommerce brands.

While the platform can be configured to do almost anything, achieving ecommerce-specific workflows requires plenty of setup time and third-party apps. Most online stores find themselves paying for enterprise-level complexity they don't need while missing ecommerce features that should be the default.

AI features:

• Copilot surfaces insights and assists agents with relevant replies
• Create procedures for every customer support scenario with the help of agentic AI
• View the AI's reasoning and refine its actions

Pricing:

• Suite Team: $55/agent/month
• Suite Growth: $89/agent/month
• Suite Professional: $115/agent/month

3. Freshdesk

Best for: Startups and small businesses with limited budgets

Freshdesk is an affordable entry point for ecommerce stores. It provides solid multichannel support and a free plan that works for small teams just starting out.

The platform handles basic helpdesk functions well but lacks the ecommerce-specific automation features that growing stores need. As your business scales, you'll likely outgrow its automation capabilities and need to migrate to a more specialized platform.

AI features:

• Freddy AI resolves customer inquiries from email, chat, and other messaging apps
• Freddy AI Copilot helps summarize conversations, compose replies, and and translate messages

Pricing:

• Free: Up to 10 agents
• Growth: $15/agent/month
• Pro: $49/agent/month
• Enterprise: $79/agent/month

4. Intercom

Best for: SaaS companies and brands focused on proactive customer engagement

Intercom is widely praised for its intuitive interface and live chat experience. Its strength lies in engaging website visitors through targeted campaigns and automated conversations.

Intercom's AI agent, Fin, can handle a strong volume of straightforward queries, though it can struggle with more complex issues that require human intervention. Teams that prioritize structured ticket management may find its conversational-first approach at odds with the detailed, workflow-driven support operations they rely on daily.

AI features:

• Fin can connect to any existing helpdesk and integrations
• Fin executes actions based on Procedures or instructions based on your brand guidelines
• Test Fin's responses with Simulations before going live

Pricing:

• Essential: $39/seat/month
• Advanced: $99/seat/month
• Expert: $139/seat/month

5. eDesk

Best for: Marketplace sellers managing multiple sales channels

eDesk specializes in marketplace management. Its core strength is consolidating messages from Amazon, eBay, Walmart, and other marketplaces alongside your Shopify store into one inbox.

This unified approach saves significant time for brands selling across multiple channels. However, its features for direct-to-consumer websites lag behind competitors, making it less ideal for brands focused on growing their own storefront.

AI features:

• eDesk's AI Agent identifies customer intent across tickets
• AI Assist is an add-on that summarizes tickets and generates responses
• AI Translations is an add-on that enables translation of most major languages

Pricing:

• Essential: $39/month
• Growth: $119/month
• Professional: $119/month
• Enterprise: Custom pricing

6. Help Scout

Best for: Small teams that prioritize simplicity over advanced features

Help Scout keeps things simple with a shared inbox approach that feels like an upgraded email client. Teams can collaborate on customer emails without the complexity of traditional ticketing systems.

This simplicity is both a strength and limitation. While easy to use, Help Scout lacks the automation and ecommerce integrations that most growing stores need to handle increasing ticket volume efficiently.

AI features:

• AI Answers pulls from your help content and external sources to respond to customer requests instantly
• Tone settings let you configure responses to match your brand voice
• Replies are supported in 50+ languages without manual translation

Pricing:

• Standard: $25/user/month
• Plus: $45/user/month
• Pro: $75/user/month

7. Richpanel

Best for: Teams that want to maximize self-service automation

Richpanel focuses heavily on self-service automation. Its visual workflow builder lets you create sophisticated automated resolution paths that help customers solve their own problems without contacting support.

The platform offers competitive pricing and strong automation capabilities. However, the agent-facing interface is less polished than competitors, and it lacks advanced features like voice support and comprehensive social media management.

AI features:

• Sidekick drafts reply suggestions by referencing past conversations and FAQs
• Agents can prompt Sidekick with a short instruction to generate a reply on the spot

Pricing:

• Starter: Free (100 tickets/month)
• Pro: $69/agent/month
• Pro Max: $99/agent/month
• Enterprise: Custom

8. Re:amaze

Best for: Small businesses with strong social media presence

Re:amaze provides a solid all-in-one helpdesk with particular strength in chat and social commerce. Its chat widget can embed a full FAQ section, letting customers find answers without starting a conversation.

The platform offers good value for small to medium businesses but lacks the advanced automation and AI capabilities of market leaders. The interface also feels dated compared to more modern alternatives.

AI features:

• Suggested replies based on past conversations
• Agents can ask AI to summarize long conversation threads
• Generate FAQ content and response templates from a short description

Pricing:

• Basic: $29/team member/month
• Pro: $49/team member/month
• Plus: $69/team member/month

9. Gladly

Best for: Luxury brands and high-touch service models

Gladly organizes all customer communication into lifelong conversation threads. This gives agents complete context about each customer's history and supports high-touch, relationship-focused service.

This approach works well for luxury brands and high-consideration purchases but comes at a premium price. The focus on human agents means automation and AI capabilities lag behind more modern platforms.

AI features:

• Handles routine questions across all channels and routes complex issues to agents
• Conversations and orders are consolidated into a single customer profile
• Voice AI handles phone calls end-to-end then hands off to an agent when needed

Pricing:

• Gladly does not list its pricing plans

10. Kustomer

Best for: Large enterprises that need CRM and helpdesk in one platform

Kustomer operates as a customer relationship management (CRM) platform with helpdesk features. Its timeline view consolidates all customer data and interactions into a comprehensive profile.

Owned by Meta, Kustomer has strong WhatsApp and Facebook Messenger integrations. However, its enterprise focus brings complexity and cost that may be overkill for most ecommerce stores.

AI features:

• AI works across email, chat, SMS, and WhatsApp
• Agents can handoff interactions back to AI to deliver resolutions
• View AI reasoning, decisions, and knowledge used

Pricing:

• Enterprise: $89/agent/month
• Ultimate: $139/agent/month

What features to look for in ecommerce helpdesk software

Not all helpdesk features matter equally for ecommerce stores. Focus on capabilities that directly impact your ability to resolve customer issues quickly and drive additional revenue from support conversations.

Essential features every ecommerce store needs:

• Multichannel inbox: All customer messages in one place regardless of where they came from
• Ecommerce platform integration: Direct connection to view and edit orders
• Basic automation: Auto-responses and ticket routing to handle volume
• Customer context: Order history and past conversations visible to agents
• Mobile access: Ability to respond to urgent issues from anywhere

Advanced features for scaling brands:

• AI-powered responses: Automated resolution of repetitive questions
• Revenue tracking: Measure how support impacts sales and customer lifetime value
• Self-service tools: Help Center and chatbots that deflect tickets
• Advanced routing: Send tickets to specialists based on skills or customer value
• Voice support: Integrated phone system for complex issues
• Custom workflows: API access for unique business processes

The key is starting with essentials and adding complexity as your team grows. Overbuying features you won't use for months wastes money and creates unnecessary confusion during implementation.

Why ecommerce customer service software matters for online growth

Customer service software isn't just about solving problems. When done right, it becomes a revenue driver that directly impacts your bottom line through increased sales, higher customer retention, and improved operational efficiency.

Revenue impact you can measure:

• Pre-purchase support: Answer product questions that prevent cart abandonment
• Upselling during support: Recommend complementary products when customers contact you
• Cart recovery: Re-engage customers who left items behind
• Retention improvement: Resolve issues before customers switch to competitors

Operational benefits that scale your business:

• Faster response times: Automation handles simple questions instantly
• Lower cost per ticket: AI deflection reduces workload on human agents
• Better agent experience: Less repetitive work means higher job satisfaction
• Scalable growth: Handle more customers without proportional staff increases

The best ecommerce helpdesks turn customer service from a cost center into a profit center. Every conversation becomes an opportunity to strengthen relationships and drive additional revenue.

How to choose the right ecommerce helpdesk for your store

The right helpdesk depends on your specific situation, not just feature lists. Match the platform's capabilities to your current needs and growth plans to avoid overpaying for unused features or outgrowing your choice too quickly.

Start by answering these questions about your business:

• How many support tickets do you handle monthly?
• Which channels do your customers use most (email, chat, social media)?
• How many team members need access to the platform?
• What's your primary ecommerce platform?
• Do you need advanced AI now or can it wait?

Common mistakes that waste time and money:

• Choosing based only on price: Hidden setup and training costs often exceed monthly fees
• Buying too many features upfront: Start simple and add complexity as you grow
• Ignoring migration complexity: Factor in time to move data and retrain your team
• Skipping the trial: Always test with real tickets before making a decision

The goal is finding a platform that solves your current problems while providing room to grow. The best choice balances immediate needs with future scalability.

Ready to see how the right ecommerce helpdesk can transform your customer service and drive revenue?

‍Book a demo to explore how Gorgias turns every customer conversation into a growth opportunity.

{{lead-magnet-2}}

TL;DR:

• Chat is growing 2.5x faster than email. The shift toward real-time, conversational commerce pushed a full redesign to match how people actually want to shop.
• The new Chat is designed to drive action, not just answer questions. Clickable replies, contextual prompts, and built-in shopping features guide shoppers from discovery to checkout faster.
• 36% more customers click on products shown in Chat. Shoppable product cards make browsing feel natural and keep shoppers engaged in the conversation.
• 2.25x more shoppers add products to cart from Chat. Removing external links and keeping the journey in one place significantly increases buying intent.
• 7.3% more shoppers engage with Chat overall. Cleaner design and contextual entry points encourage more visitors to start conversations earlier.

In 2025, chat’s growth outpaced email by 2.5x quarter over quarter. Chat has become our most powerful customer experience tool for how shoppers discover products, ask questions, and decide to buy. 

We knew it needed an upgrade, so we reimagined the entire experience from the ground up.

The result is 36% more engagement with product recommendations, nearly 2.25x more shoppers add-to-cart, and 7.3% more customer engagement.

In this post, we'll walk you through our thinking, what’s new in Chat, and how brands are already seeing big gains.

Why the legacy experience needed a makeover

Chat has outpaced email support. Today’s shoppers prefer the speed of quick chat conversations over email. And when shoppers make a new move, we watch, listen, and move with them. 

This behavioral shift isn’t happening in isolation. It aligns with the rise of conversational commerce and proves a universal move toward real-time conversations in ecommerce.

In fact, the signals were already there. Two years of building AI Agent showed us just how much design shapes behavior. The interface is the experience, and we knew that pushing chat experiences to closely resemble human interactions would transform how shoppers engage.

Our new and updated chat brings that vision to life. We believe that shopping is moving from static pages to conversations. This new update is built for how people actually want to shop.

What the new Chat can do

The new design turns live chat into an interactive shopping surface made for modern shoppers. We've brought together multiple ways for shoppers to jump into chat, added clickable replies instead of typing, browsable product cards right in the conversation, and quick cart access.

Let's walk through what's new.

A cleaner visual experience

Chat now comes in a softer color palette that adapts to your store’s branding. We removed message bubbles in favor of an airy design that brings in the familiarity of speaking to your favorite conversational AI assistant. Every interaction now has the breathing room for deeper conversation and personalization.

One-click replies that move shoppers forward

It’s now easier for shoppers to get an answer with quick reply buttons and suggested questions in Chat. This replaces the tree-based flows of the previous Chat, removing the need to follow a fixed path. Shoppers can find answers faster without typing text-heavy explanations.

Shoppable product cards in messages

Browsing and buying within Chat is now possible. Previously, it only supported product links that would open in a new page. With the upgrade, you can view item details without leaving the conversation. Shoppers can browse, compare products, and add to cart in one place.

Product detail pages that open in chat

We’re keeping the context by removing the external redirects. The new interface lets shoppers browse product recommendations right in chat. View key product details, images, descriptions, variants, and pricing without opening a new tab.

Product page questions that remove hesitation

Chat adds clickable questions on product pages — like “Is this true to size?” or “What’s the difference between shades?” — designed to match what a shopper is likely wondering in the moment. These context-aware prompts help remove buying hesitation before shoppers even think to ask.

Instant access to cart and order status

Chat adds instant access to shopper actions, like a cart button and an orders button for returning customers. Shoppers can jump straight to their cart or check on an existing order without waiting for an agent to give them a status update.

How our redesigned chat improves your bottom line

Every update in Chat drives performance. We didn’t simply give it a makeover, we also fine-tuned its underlying mechanics. 

36% more customers click on products shown in Chat

When product suggestions are easy to browse, shoppers interact with them more. The new product cards make shopping feel natural, allowing customers to explore items at their own pace. That convenience led to a 36% increase in engagement with recommended products.

2.25x more shoppers add products to cart from Chat

Chat keeps the entire shopping journey inside the conversation, from browsing and asking questions, to adding to cart and checking out. This new layout removes the usual tab-switching between chat and the website. Less friction has led to more than double add-to-cart actions than before the redesign.

7.3% more shoppers engage with Chat

Chat's cleaner design and contextual entry points make it easier for shoppers to start a conversation. With suggested questions on product pages and quick reply buttons, more visitors are choosing to engage earlier in their journey. This has resulted in a 7.3% lift in chat engagement.

Your store, now in every conversation

Conversational commerce has moved from concept to reality. Chat makes it part of the everyday shopping experience, letting shoppers browse, ask questions, compare products, and check out in one interaction. It brings the ease of the in-person shopping experience into the digital world.

We built Chat to redefine the shopping experience. We hope you see it reflected in your customers’ journeys. 

Book a demo to see what's possible with the new experience.

TL;DR:

• Train your AI on your brand voice. A clear voice guide that covers tone, style, and formality helps your AI sound more natural and aligned with your brand.
• Add short delays before AI responds. A one- or two-second pause can make AI responses seem more thoughtful.
• Avoid generic phrases. Swap out formal responses for on-brand language that sounds like a real person on your team.
• Mention customer context in replies. Referencing order history or previous conversations makes AI sound more human and builds trust.
• Balance automation with human support. Let customers know when they are speaking to AI and escalate to a human when needed to avoid frustration.

Your AI sounds like a robot, and your customers can tell.

Sure, the answer is right, but something feels off. The tone of voice is stiff. The phrases are predictable and generic. At most, it sounds copy-pasted. This may not be a big deal from your side of support. In reality, it’s costing you more than you think.

Recent data shows that 45% of U.S. adults find customer service chatbots unfavorable, up from 43% in 2022. As awareness of chatbots has increased, so have negative opinions of them. Only 19% of people say chatbots are helpful or beneficial in addressing their queries. The gap isn't just about capability. It's about trust. When AI sounds impersonal, customers disengage or leave frustrated.

Luckily, you don't need to choose between automation and the human touch. 

In this guide, we'll show you six practical ways to train your AI to sound natural, build trust, and deliver the kind of support your customers actually like.

1. Train your AI on your brand voice

The fastest way to make your AI sound more human is to teach it to sound like you. AI is only as good as the input you give it, so the more detailed your brand voice training, the more natural and on-brand your responses will be.

Start by building a brand voice guide. It doesn't need to be complicated, but it should clearly define how your brand communicates with customers. At minimum, include:

• Tone: Is your brand warm and empathetic? Confident and cheeky? Straightforward and helpful?‍
• Style: How does your brand write? What is your personality? Short or long sentences, contractions or not, punctuation choices, and overall rhythm.‍
• Formality: Do you use slang? Emojis? Address customers as “you,” “y’all,” or something else?‍
• Friendliness: How personable should your AI sound? Is it playful, or should responses stay neutral and professional?

Think of your AI as a character. Samantha Gagliardi, Associate Director of Customer Experience at Rhoback, described their approach as building an AI persona:

"I kind of treat it like breaking down an actor. I used to sing and perform for a living — how would I break down the character of Rhoback? How does Rhoback speak? What age are they? What makes the most sense?" 

Next step

✅ Create a brand voice guide with tone, style, formality, and example phrases.

2. Delay responses to mimic human behavior

Humans associate short pauses with thinking, so when your AI responds too quickly, it instantly feels unnatural.

Adding small delays helps your AI feel more like a real teammate.

Where to add response delays:

• Before sharing info that would realistically take a moment to look up, e.g., order history
• Before confirming an action like issuing a refund or applying a discount
• Transitioning or escalating between steps or agents
• Emotional messages, like customer complaints and product quality issues

Even a one- to two-second pause can make a big difference in a robotic or human-sounding AI.

Next step

✅ Add instructions in your AI’s knowledge base to include short response delays during key moments.

3. Avoid generic phrasing and canned language

Generic phrases make your AI sound like... well, AI. Customers can spot a copy-pasted response immediately — especially when it's overly formal.

That doesn't mean you need to be extremely casual. It means being true to your brand. Whether your voice is professional or conversational, the goal is the same: sound like a real person on your team.

Here's how to replace robotic phrasing with more brand-aligned responses:

Next step

✅ Identify your five most common inquiries and give your AI a rewritten example response for each.

4. Use context to inform answers

One of the biggest tells that a response is AI-generated? It ignores what's already happened.

When your AI doesn't reference order history or past conversations, customers are forced to repeat themselves. Repetition can lead to frustration and can quickly turn a good customer experience into a bad one.

Great AI uses context to craft replies that feel personalized and genuinely helpful.

Here's what good context looks like in AI responses:

• Order awareness: The AI knows the customer placed an order yesterday and provides an accurate delivery estimate without asking for the order number again.
• ‍Conversation continuity: If the customer reached out earlier that week from a different support channel, the AI references that interaction or picks up where things left off.‍
• Customer type: First-time shopper? VIP? The AI adjusts tone and detail level accordingly.

Tools like Gorgias AI Agent automatically pull in customer and order data, so replies feel human and contextual without sacrificing speed.

Next step

✅ Add instructions that prompt your AI to reference order details and/or past conversations in its replies, so customers feel acknowledged.

5. Balance automation with human handoff

Customers just want help. They don't care whether it comes from a human or AI, as long as it's the right help. But if you try to trick them, it backfires fast. AI that pretend to be human often give customers the runaround, especially when the issue is complex or emotional.

A better approach is to be transparent. Solve what you can, and hand off anything else to an agent as needed.

When to disclose that the customer is talking to AI:

• You can disclose it at the start of the conversation, or include a disclaimer in your chat widget, contact page, or help center to let customers know AI may assist
• When the customer asks to speak to a human or expresses frustration
• If the AI cannot fulfill the request and needs to escalate
• Anytime the AI is making decisions, like issuing refunds or processing cancellations
• When transitioning from AI to a human agent

For more on this topic, check out our article: Should You Tell Customers They're Talking to AI?

Next step

✅ Set clear rules for when your AI should escalate to a human and include handoff messaging that sets expectations and preserves context.

6. Add intentional imperfections to sound human

We're giving you permission to break the rules a little bit. The most human-sounding AI doesn't follow perfect grammar or structure. It reflects the messiness of real dialogue.

People don't speak in flawless sentences every time. We pause, rephrase, cut ourselves off, and throw in the occasional emoji or "uh." When AI has an unpredictable cadence, it feels more relatable and, in turn, more human.

What an imperfect AI could look like: 

• Vary sentence length and structure. Some short and choppy, others long. 
• Add subtle grammatical “mistakes” like sentence fragments or informal punctuation. 
• Mix in casual phrasing or idioms where appropriate. 
• Avoid mechanical-sounding transitions. 
• Occasionally use filler phrases like "kinda," "just checking," or "I think."

These imperfections give your AI a more believable voice.

Next step

✅ Add instructions for your AI that permit variation in grammar, tone, and sentence structure to mimic real human speech.

Natural-sounding AI is easier to set up than you think

Human-sounding AI doesn’t require complex prompts or endless fine-tuning. With the right voice guidelines, small tone adjustments, and a few smart instructions, your AI can sound like a real part of your team.

Book a demo of Gorgias AI Agent and see for yourself.

{{lead-magnet-2}}

TL;DR:

• If your AI is giving wrong answers or getting stuck, it’s likely due to missing or conflicting knowledge. Ensure your AI is trained with up-to-date documents and add guardrails to prevent off-topic replies.
• Loops and escalations usually mean your escalation rules aren’t specific enough. Define when AI should step in, when it should hand over, and create “escape phrases” that trigger human takeover.
• Customers still want human help. Always offer a path to a real person and make sure your agents get full conversation context when a handoff happens.
• Inconsistent tone between AI and agents can make disjointed experiences. Align your brand voice across all support channels and choose tools that let you customize AI tone.
• AI works best when its role is clearly defined. Decide which topics it can handle, train it using real conversations, and review performance regularly to fine-tune your setup.

You’ve chosen your AI tool and turned it on, hoping you won’t have to answer another WISMO question. But now you’re here. Why is AI going in circles? Why isn’t it answering simple questions? Why does it hand off every conversation to a human agent?

Conversational AI and chatbots thrive on proper training and data. Like any other team member on your customer support team, AI needs guidance. This includes knowledge documents, policies, brand voice guidelines, and escalation rules. So, if your AI has gone rogue, you may have skipped a step.

In this article, we’ll show you the top seven AI issues, why they happen, how to fix them, and the best practices for AI setup. 

{{lead-magnet-1}}

1. AI sends the wrong answer — with confidence

AI can only be as accurate as the information you feed it. If your AI is confidently giving customers incorrect answers, it likely has a gap in its knowledge or a lack of guardrails.

Insufficient knowledge can cause AI to pull context from similar topics to create an answer, while the lack of guardrails gives it the green light to compose an answer, correct or not.

How to fix it: 

• Update the AI knowledge base. Create a new document that covers the affected topic in its entirety. To ensure AI follows every step, write your instructions in a when/if/then format.
• Define topics that AI should not handle. As a preventive measure, specify the topics the AI should skip and hand over to a human agent. For example, add words such as ‘disappointed’, ‘bad’, and ‘unacceptable’ to your AI off-limit list, so that human agents automatically handle negative-intent tickets.

2. Customer is stuck in an AI loop 

This is one of the most frustrating customer service issues out there. Left unfixed, you risk losing 29% of customers. 

If your AI is putting customers through a never-ending loop, it’s time to review your knowledge docs and escalation rules.

How to fix it:

• Double-check for conflicts in knowledge. You may have provided multiple resolutions for the same issue across different knowledge sources, such as uploaded documents, website pages, and in-app instructions.
• Add “escape routes”. Choose a set of phrases that automatically escalate conversations from AI to your support team. For example, “it’s not working” or “I already tried that”.
• Set a max number of failed interactions before escalation. Opt for a one-fail-and-escalate approach for every conversation, or specify the number of failed interactions for certain topics.

3. AI escalates too quickly, even for easy questions

It can be frustrating when AI can’t do the bare minimum, like automate WISMO tickets. This issue is likely due to missing knowledge or overly broad escalation rules.

How to fix it:

• Train AI on your FAQs and common issues. Which customer questions do you repeatedly receive? Create a document that lists out every question and its answer.
• Update vague escalation rules. AI works best with specificity. For example, if you told it to escalate conversations about “returns,” it may even escalate frequently asked questions about return eligibility.

4. Customers can’t find a way to reach a human

One in two customers still prefer talking to a human to an AI, according to Katana. Limiting them to AI-only support could risk a sale or their relationship. 

The top live chat apps clearly display options to speak with AI or a human agent. If your tool doesn’t have this, refine your AI-to-human escalation rules.

How to fix it:

• Set phrases to trigger escalation. In your knowledge docs, define which phrases should tell AI to hand a conversation over to your support team. For example, “I want to talk to someone” or “Can I talk to a human?”
• Add a visible option to connect with a human. This can be a button in your chat widget, a note in your contact page, or even a link in your website footer. At minimum, give customers an easy-to-find way to reach a real person.

5. Handoff happens — but the agent gets no context

If your agents are asking customers to repeat themselves, you’ve already lost momentum. One of the fastest ways to break trust is by making someone explain their issue twice. This happens when AI escalates without passing the conversation history, customer profile, or even a summary of what’s already been attempted.

How to fix it:

• Use rules to auto-tag conversations based on AI activity. Set up logic to tag tickets when certain conditions are met — like when AI attempted a specific action, couldn't resolve the issue, or triggered escalation.
• Audit your escalated tickets. Look for patterns where context is missing, and adjust the AI-to-human transition logic accordingly.
• Use an AI platform that provides automated ticket summaries. Choose a tool like Gorgias that provides a quick overview of every ticket.

6. The tone between AI and agent is jarring

Sure, conversational AI has near-perfect grammar, but if its tone is entirely different from your agents’, customers can be put off.

This mismatch usually comes from not settling on an official customer support tone of voice. AI might be pulling from marketing copy. Agents might be winging it. Either way, inconsistency breaks the flow.

How to fix it:

• Create shared brand voice guidelines. Align tone, formality, and language rules across both AI scripts and agent responses.
• Define emojis and punctuation use. A consistent visual style helps conversations feel smoother and more human.
• Use AI tools that allow tone control. Choose platforms that let you customize the voice and personality of your AI to match your brand.
• Train your agents with examples of ideal tone. Give your team brand voice examples of how conversations should continue when handed off.

7. You haven’t defined what AI should actually handle

When AI is underperforming, the problem isn’t always the tool. Many teams launch AI without ever mapping out what it's actually supposed to do. So it tries to do everything (and fails), or it does nothing at all.

It’s important to remember that support automation isn’t “set it and forget it.” It needs to know its playing field and boundaries.

How to fix it:

How to set up AI that actually works

Once you’ve addressed the obvious issues, it’s important to build a setup that works reliably. These best practices will help your AI deliver consistently helpful support.

1. Define clear AI boundaries

Start by deciding what AI should and shouldn’t handle. Let it take care of repetitive tasks like order tracking, return policies, and product questions. Anything complex or emotionally sensitive should go straight to your team.

2. Train it using real customer conversations

Use examples from actual tickets and messages your team handles every day. Help center articles are a good start, but real interactions are what help AI learn how customers actually ask questions.

3. Set up fallback triggers

Create rules that tell your AI when to escalate. These might include customer frustration, low confidence in the answer, or specific phrases like “talk to a person.” The goal is to avoid infinite loops and to hand things off before the experience breaks down.

4. Make sure agents receive full context

When a handoff happens, your agents should see everything the AI did. That includes the full conversation, relevant customer data, and any actions it has already attempted. This helps your team respond quickly and avoid repeating what the customer just went through. 

An easy way to keep order history, customer data, and conversation history in one place is by using a conversational commerce tool like Gorgias.

5. Keep tone and voice consistent

A jarring shift in tone between AI and agent makes the experience feel disconnected. Align aspects such as formality, punctuation, and language style so the transition from AI to human feels natural.

6. Review handoffs regularly

Look at recent escalations each week. Identify where the AI struggled or handed off too early or too late. Use those insights to improve training, adjust boundaries, and strengthen your automation flows.

If your AI chatbot isn’t working the way you expected, it’s probably not because the technology is broken. It’s because it hasn’t been given the right rules.

AI that works your way and knows when to escalate

When you set AI up with clear responsibilities, it becomes a powerful extension of your team.

Want to see what it looks like when AI is set up the right way?

Try Gorgias AI Agent. It’s conversational AI built with smart automation, clean escalations, and ecommerce data in its core — so your customers get faster answers and your agents stay focused.

Get started with Gorgias AI Agent →