--- title: "How TravelJoy hit 80% AI resolution, saving 193 hrs/month" description: "TravelJoy's Zendesk AI resolved 24% of tickets. They switched to My AskAI. Now it's 80%. Same knowledge base, very different result." url: https://myaskai.com/blog/my-askai-traveljoy-case-study-2026 --- # How TravelJoy hit 80% AI resolution, saving 193 hrs/month TravelJoy went from 24% resolution with Zendesk AI to 76% on day one with My AskAI — now at 80%, saving 193 hours a month. TravelJoy had a problem. They needed a way to manage customer service for their ever-growing customer base, 24/7, across the world, without hiring more people. Their [Zendesk](https://myaskai.com/blog/zendesk-ai-agent-complete-guide-2026) account rep got in touch and offered a trial of their new [Zendesk Advanced AI](https://www.zendesk.co.uk/service/ai/). After trying it for a few months, they didn’t see the impact they had hoped for and so turned to My AskAI. Since integrating their My AskAI customer service agent into their Zendesk Ticketing and Messaging platforms it has resolved over 24,500 support tickets and is currently [deflecting 80% of their tickets](https://myaskai.com/blog/ai-resolution-rate-benchmarks), saving their team 193 hours every month. Now you’re probably asking yourself: “how does TravelJoy do this?!” and “how can I do this for my [SaaS](https://myaskai.com/industry-use-cases/saas)?”. Let’s take you through their setup and show you how. ## TravelJoy AI customer service results on Zendesk at a glance | Fact | TravelJoy | | --- | --- | | Website | [TravelJoy](https://www.traveljoy.com/) | | Industry | SaaS, travel advisor platform (CRM, itineraries, payments) | | Helpdesk | Zendesk (Ticketing and Messaging) | | Support volume | ~2,500 to 2,700 tickets/month | | AI resolution rate | 80% (76% at go-live) | | AI CSAT | 86% | | Time saved | 193 hours/month | | Key features used | Zendesk Ticket and Messaging apps, Custom Answers, Communication & Style Guidance, Handover Guidance, AI Tagging, Copilot note-drafting | | Knowledge sources | Website sync, internal Notion workspace | | Previously used | Zendesk Advanced AI, trialled for a few months | | Go-live mode | Direct replies in Zendesk Messaging from day 1, Copilot notes on email tickets | ## What does TravelJoy do? First, we should probably explain a little about who [TravelJoy](https://traveljoy.com/) are and what they do… TravelJoy is an all-in-one platform for travel advisors that combines CRM, itinerary building, client messaging, and integrated payments to streamline trip planning from lead to booking. It’s built for ease of use and time-saving workflows, helps advisors stay organized, automate routine tasks, and deliver professional, shareable itineraries to clients. It is used by thousands of [travel](https://myaskai.com/industry-use-cases/travel-hospitality) entrepreneurs and has facilitated over $1bn in annual spend. A screenshot of TravelJoy’s homepage. ## Which helpdesk does TravelJoy use? First off, their helpdesk - TravelJoy uses [Zendesk](https://www.zendesk.com/) as their helpdesk platform. More specifically, They use [Zendesk’s Ticketing](https://www.zendesk.co.uk/service/ticketing-system/) and [Messaging](https://www.zendesk.com/service/messaging/) features when providing support over email and chat and had previously looked at [Zendesk’s own AI solutions](https://www.zendesk.co.uk/service/ai/ai-agents/) but weren’t impressed ([see our comparison here](https://myaskai.com/blog/my-askai-zendesk-ai-agent-comparison-2026)). So they installed [My AskAI’s approved Zendesk Ticket app](https://www.zendesk.co.uk/marketplace/apps/support/1058614/ai-customer-service-agent-by-my-askai/) and [Zendesk Messaging app](https://myaskai.com/ai-agent-integration/zendesk-messaging). [Play video](https://www.youtube.com/watch?v=7hWPHnP1GNk) The results were instant. Case study card: Alan Pugh, Head of Customer Service at TravelJoy (B2B SaaS, replaced Zendesk AI): "You're beating Zendesk's AI agent 76% to 24% on AI deflection. Huge." ## How did they train their AI customer service agent? TravelJoy started off by [just connecting website](https://support.myaskai.com/features/sitesync-adding-and-syncing-your-website-content) to give their AI agent a base knowledge of their common FAQs. They supplemented this with further knowledge by connecting to their internal Notion workspace. A screenshot of TravelJoy’s knowledge page in their dashboard showing their site connection. ## When did they decide to turn on ‘direct replies’ to customers? They decided pretty much from day 1 that the fastest way for them to learn how their new agent would perform in their Zendesk Messaging would be to put it in front of their users and start gathering feedback. In the worst case scenario, there figured there were always [lots of ways the users could request to speak to someone](https://support.myaskai.com/features/human-handover#when-will-it-be-handed-over-to-a-human) and hopefully in some cases it would give a number of users faster answers. They were pleasantly surprised to see that from go-live, due to their extensive collection of articles and tutorials, that they were able to see a ~76% resolution rate, beating the 24% they previously achieved with Zendesk’s AI agent comfortably. Alan Pugh, their Head of Customer Service, put the switch like this: "In comparison to Zendesk's AI agent, we're now achieving an impressive 76% AI resolution rate, versus just 24% before. The dramatic improvement has elevated the overall level of service." As well as having their AI agent reply directly, they also have it drafting notes to tickets received via email. A screenshot showing TravelJoy’s active integrations with Zendesk Tickets (note reply) and Messaging (direct reply) Due to the nature of queries received via email, they decided it made the most sense to use My AskAI as a copilot there instead, giving their agents quick response on first contact using our “[reply to only the first message](https://support.myaskai.com/features/channels/zendesk/zendesk-tickets#how-to-connect-your-ai-agent-to-zendesk-tickets)” feature. ## What was the biggest thing they did to improve their AI agent’s resolution? But TravelJoy didn’t want to stop at 76%, they wanted to see how much further they could take their AI customer service agent. So they regularly checked in on their [Insights](https://support.myaskai.com/features/insights) to see what people were asking, [reviewed and fixed their knowledge gaps](https://support.myaskai.com/features/improve/knowledge-gaps) and [created custom answers](https://support.myaskai.com/features/improve/custom-answers) to make sure their agent had all the knowledge it could to answer questions. A screenshot showing TravelJoy’s use of custom answers in their dashboard. Through this continual improvement process, they have managed to increase their average AI resolution to where it sits today, at around 80%. A screenshot from TravelJoy’s dashboard showing their long term AI resolution rate of 80% over the last 365 days, with an AI CSAT of 77%, 24,525 conversations processed and 2,300 hrs saved (at 5 mins per conversation). ## How do they customize their AI agent setup to work for their business? Every business manages support in their own way and needs a solution to flex to their needs. Here are a couple of ways TravelJoy make My AskAI work for them: ### Controlling their communication style TravelJoy use our [Communication style guidance](https://support.myaskai.com/features/improve/guidance#communication-style) feature to make sure that their AI agent responds in exactly the way they want, following their reply structures and using their brand tone of voice. They also use [Handover guidance](https://support.myaskai.com/features/improve/guidance#handover-and-escalation) to ensure conversations are handed over when they need to be. A screenshot showing TravelJoy’s Communication & Style guidance set up within Improve in the My AskAI dashboard. ### Using AI to auto-tag and categorize their tickets Previously TravelJoy were manually assigning reasons for contact to each ticket. Now they use our [AI Tagging Zendesk app](https://support.myaskai.com/features/channels/zendesk/zendesk-tagging) to auto-classify tickets on receipt saving their team the monotonous job of (inconsistently) categorizing each month. A screenshot of TravelJoy’s tagging set up within the My AskAI Dashboard. ## What impact is their AI customer service agent having now? Good question. As a result of TravelJoy’s continual efforts and focus on improving their AI customer service agent, their AI agent is currently: - Resolving 80% of tickets automatically each month across over 2,500 tickets (that’s over 2,000 chats per month their team doesn’t have to deal with directly). - Saving their customer service team 205 hours per month (assuming a 5 minute per ticket handle time). - Achieving a 86% [AI CSAT](https://support.myaskai.com/features/insights#ai-csat) score across those 2,700 tickets. A screenshot of Traveljoy’s Insights for the last 30 days at 10 Dec 2025, with 79% AI resolved rate, 86% AI CSAT and 2,704 conversations. ## Where do they go from here? TravelJoy are keen to increase their AI resolution still further, with a focus on auto-resolving tasks that currently take time out of their (human) team’s day. Things like, sharing more information on card decline reasons and extending free trials. They’re now looking at how our [tools](https://support.myaskai.com/features/ai-actions-tools) and [tasks](https://support.myaskai.com/features/tasks) features can help them do just this, automating both simple and complex actions. Watch this space! [View all case studies](https://myaskai.com/reviews-and-case-studies) or [get started with My AskAI](https://myaskai.com/pricing). [Learn more about building an AI-first support operation in our complete guide](https://myaskai.com/blog/ai-first-customer-service-guide-2026). - HubSpot ### [Zinc: Using My AskAI to reduce support tickets by 68%, overnight](https://myaskai.com/blog/my-askai-zinc-case-study-2026) Zinc went live with AI support in minutes — not weeks. Now 68% of queries resolve automatically with 97% CSAT. They didn't need to hire a replacement. 27 Feb 2024 4 min read - HubSpot ### [Zeffy: How My AskAI helps Zeffy Keep Their Ticket Volume Down and Fundraising Free](https://myaskai.com/blog/my-askai-zeffy-case-study-2026) Zeffy tested 8 AI vendors with 200+ questions. Only one passed. Now they deflect 84% of tickets with a 7-person support team. Here's how. 6 Jul 2024 4 min read - Case Study ### [Swytch: How My AskAI helps deflect over 4,050 support queries every month](https://myaskai.com/blog/my-askai-swytch-case-study-2026) Swytch sells e-bike kits and deflects 4,050+ support tickets a month with AI. Their secret? Treating the AI like a new hire that never stops learning. 27 Nov 2024 4 min read - Intercom ### [Freecash: How My AskAI resolves over 70k support queries every month](https://myaskai.com/blog/my-askai-freecash-case-study-2026) 70,000 tickets a month. 82% resolved by AI. Freecash tested Intercom Fin first — then switched. The cost difference was... significant. 6 Aug 2024 3 min read - Alternatives ### [My AskAI vs Zendesk AI agent: Features, Pricing, and Results (2026)](https://myaskai.com/blog/my-askai-zendesk-ai-agent-comparison-2026) Zendesk's AI agent bills $1.50 to $2.00 per automated resolution. My AskAI plugs into your existing Zendesk and resolves tickets for a fraction of the cost. 8 Sept 2025 31 min read - Intercom ### [How Kriptomat achieves 62% AI resolution, saving 172 hrs each month](https://myaskai.com/blog/my-askai-kriptomat-case-study-2026) Kriptomat started at 50% AI resolution and thought that was good. Turns out reviewing knowledge gaps weekly got them to 62% — and counting. 14 Oct 2025 5 min read ## Start using AI customer service in your business today Set up an AI agent on your helpdesk in minutes. Pay only for the tickets it resolves. [Create AI customer service agent (opens in a new tab)](https://myaskai.com/create-account) [Book a demo (opens in a new tab)](https://myaskai.com/book-a-demo) My AskAI