Frequently Asked Questions

Yuma is a customer service automation platform made for e-commerce brands. It's purpose-built to work with top ecommerce platforms such as Shopify, WooCommerce, Magento, etc. It automates support tickets by connecting with helpdesks such as Gorgias, Zendesk, Gladly, etc. Yuma resolves tickets end-to-end by taking real actions across platforms, just like human support agents. It's known for high accuracy thanks to its built-in guardrails. Brands only pay for tickets fully resolved by AI, and setup is handled by a dedicated account team at no extra cost. Yuma has successfully automated up to 89% of customer support for its top customers.

Yuma also offers three other products: Sales AI, Social AI, and Chat AI to automate 360-degree ecommerce interactions for brands.

Guillaume Luccisano is the Founder and CEO of Yuma AI. He's a three-time Y Combinator backed founder: first with Socialcam (acquired by Autodesk for $60M), then Triplebyte (valued at $135M, acquired by Karat), and now Yuma. Guillaume started his career as a software engineer at Justin.tv (which became Twitch) and has since angel invested in 60+ startups. Yuma started by accident when he released a prototype in December 2022 and got flooded with demo requests from Shopify merchants. He turned it into a company, and it's now backed by Alt Capital, Google's Gradient Ventures, Y Combinator, and investors behind Twitch, Docker, and Cruise.

Yuma AI is headquartered in Cambridge, MA, United States, with a European office in Barcelona, Spain.

Yes, Yuma is a US registered legitimate software company that's Y Combinator-backed and founded by Guillaume Luccisano, a three-time founder whose previous startups include Socialcam (acquired by Autodesk for $60M) and Triplebyte (valued at $135M, acquired by Karat). The platform serves several global paying e-commerce brands. Yuma was featured in a16z's AI x Online Shopping Market Map, and has been covered by TechCrunch. The company is headquartered in Cambridge, MA with a European office in Barcelona, Spain.

Yuma publishes full case studies with named customers, real metrics, and direct quotes. Here's what a few of them report:

Glossier saw 91% accuracy on complex shipping tickets and an 87% drop in response times. Amy Kemp, Director of CX said: "We barely had to think about the technical side. Yuma just worked, right out of the box."

Clove hit 70% automation and 3x ROI within three months, after switching from a previous AI partner that lacked guardrails. Gabe Walker, CS Manager said: "It's refreshing to have a partner that's just really trying to make our experience with the product as successful as possible."

Javvy Coffee went from 24-hour response times to 12 minutes, with CSAT climbing from 3.5 to 4.2. Shannon White, Head of CX said: "Going into this holiday season versus last year's, I had the peace of mind knowing that no matter what, the inbox was going to be fine."

EvryJewels reached 89% automation and cut cost per ticket from $5.50 to $2 while processing over 150,000 tickets.

All case studies are available at yuma.ai/case-studies

Yuma is used to automate ecommerce customer service. The most common use cases include shipping status inquiries, returns and exchanges, order cancellations and modifications, subscription management, refunds, and product questions. These ticket types typically make up 40 to 70% of a brand's total support volume.

For example, Glossier uses Yuma to parse global tracking links and process time-sensitive order changes. Petlibro uses it for product troubleshooting and subscription management across numerous SKUs. Javvy Coffee automates subscription cancellations, refunds, and payment issues. In each case, Yuma resolves tickets end-to-end by taking real actions in external systems, not just answering questions.

Yuma plugs directly into your existing helpdesk (Gorgias, Zendesk, Salesforce, and others) and works alongside your team. When a ticket arrives, Yuma reads the message, identifies the customer's intent, and routes it to the right AI agent: process-driven agents for tasks like returns and order changes, or knowledge-based agents for product and policy questions. Each agent follows your SOPs and brand voice, then takes real actions across your tools (Shopify, Recharge, Loop, shipping carriers) to resolve the ticket end-to-end. Every response passes through built-in quality control before it reaches the customer. If a ticket is too complex or sensitive, Yuma escalates to a human agent with full context instead of guessing. See how Yuma compares to other AI tools in our complete market guide, or our focused guide for Gorgias users.

Yuma connects to your helpdesk and ecommerce platform, then a dedicated account manager configures your AI agents based on your existing processes, brand voice, and support policies. There's no DIY setup: Yuma's team handles it at no extra cost. Once configured, Yuma starts with a gradual rollout, processing only 5 to 10% of eligible tickets so your team can review quality before scaling up. As confidence builds, the rollout increases until the AI handles the full volume. Your agents still see every ticket in the helpdesk, and anything the AI can't resolve gets escalated to a human with full context attached.

No. Yuma requires zero engineering work to set up. A dedicated account manager from Yuma configures your AI automations, writes your automation processes, and connects Yuma to your helpdesk and ecommerce tools. This is included at no extra cost, and there's no package without it.

Yes. Yuma offers a 30-day trial period where you can test the AI on live ecommerce customer service tickets with your real data, your helpdesk, and your customers. The trial is typically kicked-off with an agreed potential automation rate, so both sides have a clear success metric upfront. During the trial, Yuma's team handles the full setup and configuration (same white-glove onboarding as paying customers), and deployment starts gradually at 5 to 10% of ticket volume so you can review quality before scaling.

To book a live demo, just fill up the form here - https://yuma.ai/contact-us

Pricing is scoped around ticket volume, workflows, channel mix, and the implementation depth needed for your team rather than around generic seat counts alone.

Yes. Yuma offers a free 30-day trial so teams can validate automation coverage, operational fit, and business impact before expanding the rollout.

Security and governance reviews are part of the buying process, but they are handled as part of the rollout scope rather than hidden as a separate upsell line item.

Bring expected ticket volume, current helpdesk and commerce stack details, the channels you want to automate first, and the KPIs that matter most to your team.

Yes. Yuma's Chat AI is a live chat widget you can add to your website or store by copy-pasting just a few lines of code. It runs on the same AI that handles your helpdesk tickets, so it follows your brand voice, takes real actions (tracking orders, processing returns), and escalates to a human agent with full context when needed. It works 24/7 across multiple languages.

Yuma covers 25+ support channels: email, live chat, SMS, WhatsApp, contact forms, Instagram DMs, Instagram comments (including ad comments), Facebook Messenger, Facebook comments, Twitter/X DMs, TikTok Shop, and review platforms (Trustpilot, Yotpo, Okendo, Judge.me, Avis Vérifiés). Each channel runs on the same core AI with the same accuracy, but you can configure different brand voices per channel (e.g. shorter on chat, more detailed on email). Yuma also offers a native Chat AI widget for your website and Social AI for automating social media customer support.

Yuma supports 180+ languages. It auto-detects each customer's language and responds in that language, including regional dialects and right-to-left scripts. Your brand voice and policies stay consistent regardless of the language. So a French customer gets the same quality and accuracy as an English one. This means you can support international customers without hiring multilingual agents, which is especially useful during seasonal spikes when finding language-specific temporary coverage is nearly impossible.

Yes. Yuma's Social AI connects to your Facebook and Instagram pages in one click, classifies every comment by intent and sentiment in real time, and takes action based on rules you define: reply, like, flag, or skip. You configure the agent's tone, verbosity, and brand guidelines so replies sound like your team wrote them. A dashboard tracks automation coverage, sentiment distribution, negative exposure rate, and unanswered rate across both platforms.

Support AI doesn't just draft a reply — it executes the full resolution. For a return, the AI checks eligibility against your policies, determines the return type, creates a return label through your returns provider, sends instructions to the customer, then follows up days later to confirm shipment and process the refund. For WISMO, it pulls live carrier data, reads shipment exceptions, and gives the customer a real tracking update. Yuma has over 100 ready-to-use actions for support automation, from issuing refunds to updating subscriptions.

Support AI ramps up like training a new hire. It starts at 0% of tickets, then moves to 1%, 10%, 30%, 50%, and 100%. At each stage, you review a batch of AI-handled conversations and approve or roll back. The AI earns trust ticket by ticket — typically through 25+ human reviews before reaching full autonomy. For stores with lower ticket volume, the system can replay historical tickets so you can validate before going live.

Multiple layers. Every reply is scored for accuracy before sending — low-confidence responses are escalated to a human instead of sent. The AI uses structured workflows (Flows) for policy-sensitive processes so it can't skip steps or invent outcomes. Knowledge answers come from real-time search of your actual documentation, not from the model's training data. And if the AI doesn't know the answer, it knows when to stop and hand off to your team.

Yuma learns your voice from sample responses you provide — tone, length, structure, personality. You can configure different voices for different channels (email vs. Instagram DM vs. chat), and every AI response is rewritten to match your persona before it's sent. Yuma even adapts regional spelling automatically, so your British customers see "colour" and "favourite" while your American customers see "color" and "favorite".

Yuma works with multiple AI providers as backup, including OpenAI, Anthropic, and Google. If one provider has issues, the system switches automatically — often before anyone notices. There's always a path to a response, so your customers never see downtime.

Sales AI is a live chat widget on your storefront that answers pre-purchase questions in real time — sizing, compatibility, availability, shipping estimates, ingredient details. It pulls answers from your product catalog and knowledge base using semantic search, so responses are accurate and specific. It can also recommend products, surface promotions, and qualify purchase intent to help convert browsers into buyers.

None at all. You add a small snippet to your store and Sales AI is live. There's no training step, no FAQ list to build, no rules to write. The widget reads your product images, descriptions, and metadata on its own, so it immediately understands your catalog and starts answering shopper questions accurately. Most merchants see useful conversations from day one, with zero configuration.

Copy and paste a few lines of code into your store's theme. No development work required — the widget loads independently and connects to your Yuma account. It works on Shopify, BigCommerce, and any platform that supports custom scripts.

Yes. When the conversation requires human judgment — a custom order request, a complex compatibility question, or when the customer explicitly asks — Sales AI escalates with full context to your helpdesk. The human agent sees the entire conversation history so the customer never has to repeat themselves.

Social AI handles Instagram DMs, Facebook Messenger, Instagram comments (including ad comments and mentions), and Facebook comments. The AI adapts its tone and format to each channel automatically.

Yes. When someone comments on a post or ad with purchase intent — "Is this available in my size?" or "How much?" — Social AI can respond publicly and simultaneously open a private DM to continue the conversation, qualify the lead, and drive the sale without cluttering your comment section.

Social AI uses channel-aware brand voices. A public Instagram comment reply is concise and on-brand. A follow-up DM is warmer and more detailed. An email response is more formal. You configure each voice separately, and the AI applies the right one based on the channel.

Generic chatbots can only answer from a static FAQ list. Chat AI runs on the same AI engine as Yuma's ticket automation — it can search your product catalog and knowledge base in real time, track orders, check subscription status, initiate returns, and take real actions inside your helpdesk and ecommerce platform. It follows your brand voice and escalates to a human agent with full context when needed.

Chat AI searches your knowledge base, product catalog, and help center documentation in real time. It can also pull live data from your ERP, CRM, or any custom API when needed. It doesn't rely on what was in the AI model's training data — it finds and references your actual, current content. You can update your knowledge base at any time and the AI reflects the changes immediately.

Yes. You control the widget's colors, position, greeting message, and avatar to match your brand. You can also define which types of questions should be handled by AI vs. escalated to your team.

Yes. One Yuma account can manage multiple stores or brands from a single helpdesk. Yuma automatically routes each conversation to the right store, applies the correct policies, and pulls the right order data. Everything works seamlessly even when all your stores share the same support inbox.

Yuma is known for being highly accurate. For example, FINN, Europe’s leading car subscription platform, chose Yuma after quality A/B testing because it needed human-level accuracy for B2B support workflows like invoices, paperwork, billing questions, and address changes. Yuma ensures high accuracy by making sure that each ticket passes through multiple quality control checks (policy verification, intent matching, response validation) before reaching the customer. If any check flags uncertainty, Yuma escalates to a human agent instead of guessing. You can track accuracy, confidence scores, and error rates in real time through your dashboard.

Yes. Yuma natively supports multiple brands and storefronts from one platform and account. Each store keeps its own brand voice, policies, and analytics separate, while your team can share automations across domains.

Yes, this is core to how Yuma works. When the AI detects low confidence, customer frustration, or a topic outside its scope, it escalates to a human agent with full conversation context, so customers never have to repeat themselves. You control the escalation rules: by topic, sentiment, VIP status, or custom triggers.

Yes. Yuma's AI agents can open and analyze images, videos, and PDFs directly within a support ticket or chat conversation. It recognizes broken parts, model numbers, barcodes, and product defects from customer photos, and extracts text from screenshots or receipts. This is where automated customer service gets practical: a customer sends a photo of a damaged item, and the AI processes the warranty claim without a human needing to look at it first.

Yes, across every channel. Yuma's AI pulls from your customer knowledge base, product catalog, and past tickets to answer sizing, ingredients, compatibility, and other product questions in support tickets, live chat, and social DMs. Yuma also offers a Sales AI widget that sits on your product pages as an AI shopping assistant, answering pre-sales questions before they become support tickets. Users of Sales AI report up to 6% higher conversion rates.

Yes, Yuma offers a feature called Flows that allows users to build automations with a workflow builder style UI and ensure strict step by step instructions for automations.

Yes. Yuma's Process Builder lets you write automations in plain English: describe how a ticket type should be handled, and the AI follows those instructions. No code, no decision trees, no dev resources. For workflows that need stricter logic, Yuma also offers Flows, a visual drag-and-drop builder that works alongside natural-language processes. Your account manager helps configure both as part of Yuma's automated customer service setup, so your team doesn't carry the implementation burden.

Yes, you can fully control what Yuma AI says and doesn't say. Yuma gives you three layers of control over your ecommerce customer service AI. Guidelines let you embed brand tone, legal phrases, and explicit do-not-say lists directly into the AI's reasoning. Hard Limits set non-negotiable boundaries: refund caps, restricted topics, discount ceilings. And lastly, Yuma runs every response through multilayer checks for accuracy, policy compliance, and tone before it reaches a customer.

Yes. Yuma's Support AI runs 15 to 20 quality checks per ticket (accuracy, policy compliance, tone) and still delivers responses in seconds. The real proof is in customer service response time data: Clove went from day-long waits to under 3 minutes, and CABAIA now replies in under 2 minutes. Speed matters, but Yuma treats accuracy as the higher priority.

Yes, in two ways. First, Yuma learns from your agents: when a human edits or overrides an AI draft, Yuma absorbs that correction into future replies. Second, Yuma's engineering team ships model improvements and new features weekly, so your automated customer service keeps pace with the latest AI advances.

Any AI can make mistakes, and anyone who tells you otherwise is selling you a lie. Yuma's approach is to make errors extremely rare and catch them before they reach customers. That’s why we run every response through multilayer checks for accuracy, policy compliance, and tone. Yuma also comes with built-in guardrails specifically designed for ecommerce customer service. That’s why a top customer, Glossier saw 91% accuracy on shipping tickets from day one, and that number climbs as the AI learns.

It depends on your ticket mix, but most Yuma customers land between 40% up to 89% automated customer service. Real numbers from Yuma customers: EvryJewels reached 89%, Petlibro hit 79%, and Clove reached 70% in three months.

Yes. Yuma is built to connect to any knowledge base imaginable. Our knowledge base hub connects your help-center articles, policy docs, and external wikis so the AI always pulls from information you trust. Fact Snippets store immutable details (warranty periods, sizing charts, ingredient lists) that get inserted verbatim into replies. Yuma also offers Quick Q&As that lets you build a curated vault of approved answers for your most common questions. The AI draws from all three when responding.

Yuma's Support AI learns from multiple sources to handle your ecommerce customer support accurately. You can feed it past tickets, help-center articles, policy documents, excel sheets, google docs, PDFs, basically anything type of knowledge source imaginable. Beyond knowledge, you also train the AI on brand voice (tone, emoji rules, channel-specific formality), Guidelines (do-not-say lists, legal language), Hard Limits (refund caps, restricted topics), and custom processes written in plain English.

Yes, Yuma is trained on your whole website and store including the whole product catalog, once integrated.

Yes. Once you connect Yuma to your helpdesk, it begins building a custom knowledge base from your existing ticket data in the background. The AI also learns from how your agents handle tickets over time, absorbing corrections into future replies. On each new ticket, Yuma pulls the customer's previous conversations and order history to personalize its response. You can test new automations against historical tickets in Playground before anything reaches customers. Your past conversations become training data that keeps improving ecommerce customer support accuracy over time.

Yuma drives revenue in two ways. First, Yuma's Sales AI product sits directly on your product pages, auto-generates product FAQs using AI, and answers shopper questions in real time before they bounce. Sales AI users report up to 18% higher revenue per visitor and a 6% lift in conversion rate. Second, by automating repetitive support tickets, Yuma frees your agents to focus on high-value conversations like retention, upsells, and complex pre-sales inquiries. Faster response times, thanks to AI also directly reduce churn from potential sales: Javvy Coffee went from 24-hour response times to 12 minutes, while CSAT climbed from 3.5 to 4.2.

Yuma often delivers 3X to 4X ROI for it’s customers. Here are some of the real results that yuma drove for top brands:

Clove achieved 3x ROI and 25% cost savings in 90 days.

EvryJewels cut cost per ticket from $5.50 to $2, a 63% reduction.

MyVariations reported 4x ROI and 33% lower monthly customer service costs.

CABAIA dropped cost per ticket from €3.75 to €1.

Petlibro saved 20% annually and avoided hiring additional human agents.

Javvy Coffee reclaimed 4 months of agent time while improving CSAT from 3.5 to 4.2.

ROI usually comes from three places: lower cost per ticket through automated customer service, fewer hires needed to handle volume, and faster response times that improve sales and retention.

Brands using Yuma typically see anywhere from 45% to 89% of customer support automated, 60-87% faster response times, and substantial cost savings within the first 90 days. Specific examples: Clove hit 3x ROI and 25% cost reduction in 3 months. EvryJewels cut cost per ticket from $5.50 to $2. Javvy Coffee went from 24-hour response times to 12 minutes and raised CSAT from 3.5 to 4.2.

Yes. Yuma publishes detailed case studies with real metrics, timelines, and customer stories. Here’s a list of top case studies you can read:

Glossier (87% faster response time, 91% accuracy, 16 hours saved per ticket resolution)

EvryJewels (89% automation, 63% cost reduction, cost per ticket from $5.50 to $2, 150K+ tickets processed)

Petlibro (79% automation, 20% annual savings, 30% faster resolution, eliminated additional hires)

Clove (70% automation, 3x ROI, 25% cost savings, FRT from 1 day to 3 minutes, all in 3 months)

CABAIA (74% cost reduction, halted CX recruitment, €2.75 savings per ticket)

Javvy Coffee (70% automation, 99% FRT reduction, response time from 24 hours to 12 minutes, CSAT from 3.5 to 4.2)

MFI Medical (64% automation, 87% FRT reduction, $30K annual savings, Google rating from 3.5 to 4.4)

MyVariations (62% automation, 70% FRT reduction, Trustpilot score maintained at 4.8/5)

Omnie (BPO partner, 50% automation for clients, FRT from 7 hours to 1 hour, serving 12 e-commerce businesses)

Four things separate Yuma from generic AI tools for ecommerce and helpdesk add-ons.

First, it's built exclusively for ecommerce customer service, with pre-built actions for order tracking, returns, exchanges, and subscriptions that plug into your existing helpdesk (Gorgias, Zendesk, Kustomer, etc). No re-platforming required.

Second, Yuma is highly customizable and takes real action across tools and platform just like human agents - making it highly capable for complex cases and real life support scenarios.

Third, every response runs through several quality control checks before reaching a customer; ensuring high accuracy for all support processes.

Fourth, you only pay for tickets Yuma resolves.

Every Yuma customer gets a dedicated account manager who handles setup, configuration, and ongoing optimization at no extra cost. Clove's support team reported support turnaround is less than an hour. Glossier's Director of CX said: "We'll come up with an idea, and by the next day, Yuma's support team has added the feature or found a workaround." That level of responsiveness is standard, not premium. Yuma treats ecommerce customer service automation as a partnership, not a software license.

Yes. Yuma AI is fully SOC 2® compliant.

Yuma is purpose-built for ecommerce. The most common verticals are fashion and apparel (Glossier, Clove), beauty and personal care, accessories and jewelry (EvryJewels), consumer electronics (Petlibro), and home and lifestyle brands.

Ecommerce, DTC, and retail brands use Yuma because it's purpose-built for commerce and consistently ranks as the most accurate AI for ecommerce customer service. Top companies include:

Glossier (beauty, 87% faster response times)

Clove (footwear, 70% automation)

EvryJewels (jewelry, 89% automation)

Petlibro (consumer electronics, 79% automation)

CABAIA (fashion, 74% cost reduction)

Javvy Coffee (food and beverage, 70% automation)

MFI Medical (medical supplies, 64% automation)

Yuma connects to 50+ platforms. Helpdesks: Gorgias, Zendesk, Kustomer, Front, Salesforce Service Cloud, Gladly, Re:amaze, Sprinklr, Zoho Desk. Ecommerce: Shopify, BigCommerce, WooCommerce, Magento 2, Adobe Commerce. Subscriptions: Recharge, Skio, Seal Subscriptions, Loop Subscriptions, Subscribfy, Stripe, Stay AI, Checkout Champ. Returns: Loop Returns, ReturnGO, AfterShip Returns, Baback, Redo, Shippingbo, iF Returns. Shipping: ShipStation, ShipBob, ParcelLab, Fulfill Engine, Shipmonk, Brightpearl, Bigblue, Shippingbo, Shipup, AfterShip, Parcel Panel. Carriers: DHL, USPS, Chronopost, Mondial Relay, Colis Privé. Loyalty: Yotpo Loyalty, Smile.io, Rivo. Reviews: Avis Vérifiés, Okendo, Trustpilot. Marketing: Klaviyo, Yotpo, Attentive, Postscript. Knowledge bases: Guru. Social: Facebook, Instagram.