We replaced Zendesk
by Liriel on 5/28/2026, 3:42:25 PM
https://tradecore.com/resources/blog/we-replaced-zendesk-in-48-hours
Comments
by: 827a
Companies that are brave enough to do this; or more importantly, those that have aligned their internal processes and infrastructure around an ability to do this; will own the future.
5/28/2026, 5:13:02 PM
by: firefoxd
From my understanding, they vibe coded a solution and for now it is working for them. I've worked with zendesk and several other platforms. I worked in customer service automation, so we had to deal with so many incompatibility with different platforms. This looks like a win for now, but the part we won't see is what happens at 72 hours.<p>I'm all for sticking it to zendesk, but as I tell every single person who were thinking to roll their own solution, have you thought about Integration? That's zendesk's moat. They have an integration with almost every single platform you can think of. It works with all e-commerce, but also ebay and amazon. It can communicate via WhatsApp, imessage, signal, and everything in between. Then connects to salesforce and netsuite.<p>I know this is a AI generated post, talking about an AI generated app. So next I'm expecting the AI agent deleted our prod database posts.
5/28/2026, 4:22:26 PM
by: coderintherye
Since their private equity buyout in 2022, Zendesk will absolutely attempt to get you to sign agregious terms. They will attempt to hoodwink you. They will pretend they never received your cancellations and charge you for another year of contract. Legal counsel should be leveraged when dealing with them to ensure you don't get screwed.
5/28/2026, 4:07:27 PM
by: petcat
For real. Does stuff like Zen desk even have any moat at all? It's an easy framework crud app with a million features that you don't need.<p>Just get an AI bot to make one for you
5/28/2026, 3:59:32 PM
by: ahknight
86% AI generated text. Seriously, does nobody write anymore?
5/28/2026, 4:13:49 PM
by: scsh
If you have an internal CRM and are maintaining a Zendesk integration to create support tickets within your product, you've likely already done half the work needed to instead create those tickets in your own internal CRM tool yourself. This makes a lot of sense.<p>As someone who's had to maintain a Zendesk integration such as this for a large app it's hard to understate the benefit of having all that support info so close to the rest of your user's data. I have seen a huge amount of effort go into trying to get just the right balance of data in and out of ZD. Also helps alleviate concerns with sharing too much customer data with a third party.<p>This definitely isn't the right call for everyone, but there's a lot of upside if it can work for your organization.
5/28/2026, 4:29:03 PM
by: pirsquare
Hahaha totally relatable. Love Zendesk but they kept charging and adding more features I don't need.<p>I built <a href="https://pointanswer.com/" rel="nofollow">https://pointanswer.com/</a> for myself to host 3 of my own SaaS instead of paying more than $100/mo for simple helpcenter. I'm the only one using it with no customers but it's still way better than paying for Zendesk.<p>But did spent too much time on it as I built in pre-Claude era.<p>My personal experience: For many years I used Zendesk to manage support and host my documentation. It's a powerful platform with help center structure that I liked liked the most. I was paying about US$30/mo for OnVoard.<p>When I use Zendesk for my second SaaS business, RenderKu, it costs me $70/mo. This amount is more than 3 Hetzner servers I'm paying to host the whole infrastructure. And I'm only choosing Zendesk mainly for hosting documentation.<p>At this point, when I was planning to start my 3rd app business, the thought of forking another $70/mo for hosting documentation made me rethink my options. I've eventually come to the conclusion it would be better for me to start PointAnswer and use it as helpcenter for myself since I only needed simple and affordable helpcenter.
5/28/2026, 4:08:52 PM
by: alanwreath
I have a friend who’s doing this for himself. He owns an AC business. He has need for tools but does not like plunking down money for a feature set that moves him in a direction he doesn’t wish to go. Solution? Create a bespoke internal system of one off apps for his OWN business using an LLM.<p>He’s not a software developer, he has no concept of software maintenance or security.<p>I’ve been watching and it’s interesting to me because I would not be surprised that he’s not alone as a small family business. Many probably feel liberated from company’s that would enforce a certain cookie cutter shape.<p>Does this mean AI is shifting towards contractor jobs more? Does it mean a huge security issue brewing? Both? Maybe business owners turned SWVibers like him will swing back to an off the shelf option once pouring more effort into 3am-my-stuff-is-broke scenarios becomes more of a chore than it’s worth.<p>I feel like there are a million billion green field projects brewing that will soon turn brown for one reason or another.
5/28/2026, 4:17:17 PM
by: sandeepkd
It would be an interesting read if they publish how things are working after a month or so. The first 90% is always is interesting and quick stuff.<p>On a different note, what Zendesk did is pretty much regular play now, hopefully some serious competition will keep that in check.
5/28/2026, 4:40:49 PM
by: dustywusty
We ended up doing that ourselves, moved completely to an internal system that integrates well with our own administrative capabilities. It has been such a breath of fresh air, and took us about the same time to accomplish.<p>The final straw was attempting to move Zendesk down to one seat to have historical/archive capabilities for a period of time, and they couldn't even manage that process properly.
5/28/2026, 4:16:12 PM
by: VikingCoder
At some point, some people will just publish open source single-shot LLM prompts that define a clean-room spec for every over-priced product.<p>Why not make an open source alternative to the product?<p>Because everyone's needs are just a little different, and collaborating takes maintenance. Forks are free, merges are expensive.
5/28/2026, 4:15:57 PM
by: mawadev
Big win for all the developers out there. This is how simple it can be, I loved every word in this
5/28/2026, 4:11:08 PM
by: reacharavindh
It certainly is true that many SaaS subscriptions can be replaced with custom written(supercharged by AI) tools. The key question however remains “Who are you going to call when something goes wrong?” Or “who is going to maintain this software?” Because essentially that’s what SaaS subscriptions genuinely offloaded and let you focus on your core business things.<p>As is most things in engineering, this is a trade-off and the line where buy vs build exists somewhere to be found and justified. Sure AI moves the line closer to build these days.
5/28/2026, 4:23:03 PM
by: prima-facie
> We pulled an ultrahackathon. The team who built this did not sleep much for two days. They worked through Wednesday night, through Thursday, through Thursday night, through Friday. They ate at their desks. They wrote the spec late Wednesday evening and they wrote the cutover commit on Friday afternoon, and in between they did the work that the time between those two moments required.<p>Cool story but I would not want to be in their shoes. Treating your employees poorly only to justify overnight changes in business needs creates a highly toxic work environment.
5/28/2026, 4:09:10 PM
by: spiderfarmer
This is what I did for multiple customers now. Not Zendesk, but other expensive SaaS.<p>I only built the 20% they actually needed, with faster UI and better UX.<p>If you freelance, this is where you can make money with AI.
5/28/2026, 4:04:01 PM
by: catigula
>The honest answer is the boring one. We pulled an ultrahackathon. The team who built this did not sleep much for two days. They worked through Wednesday night, through Thursday, through Thursday night, through Friday. They ate at their desks. They wrote the spec late Wednesday evening and they wrote the cutover commit on Friday afternoon, and in between they did the work that the time between those two moments required.<p>Man, they must have gotten paid crazy overtime. Kudos!
5/28/2026, 4:03:44 PM
by: christoff12
Extor-zen
5/28/2026, 4:14:35 PM
by: ocdtrekkie
Our helpdesk provider wanted a three year annual commitment at double the price we've been paying after they got bought by private equity. We are not continuing with our helpdesk provider.<p>The correct answer to this behavior <i>needs</i> to be "lol no" until these companies learn this behavior is unacceptable at any price. They could've boiled the frog at a 10% annual hike and nobody would've cared, but you double and you are fired as a vendor and that's that.
5/28/2026, 4:12:15 PM
by: AndrewKemendo
This is precisely the future of consumer software engineering (no I’m not saying anything here about building robots rockets medicine etc. at least for the next decade probably)<p>This idea that software developer productivity being the goal for AI companies is just not it - every piece of code you put into an LLM is a you giving these giant companies your expertise<p>People need to remember where the bulk of engineering money goes: consumer advertising and consumer facing applications, and don’t forget most of them have tragically bad user experiences and dark patterns because they’re trying to make the software as a service model work for investors<p>if I can spend a week replicating your software that has all these bullshit dark pattern features and I can replicate that for my own why why wouldn’t I?
5/28/2026, 4:06:09 PM
by: frenchie4111
This happened to me recently with a few providers. Their billing teams got aggressive and I said fuck it and AI coded a replacement in a few nights/weekends. For me it was: Temporal, Zapier and DocuSign<p>I strongly believe the build/buy equation is much different in 2026 than it was in 2024
5/28/2026, 4:02:38 PM
by:
5/28/2026, 4:20:06 PM
by: fellowniusmonk
My successful startups had their own internal CRM as distinguishing factor to their success, it's not hard.<p>One started out as an acquisition of a group on sales force, we wrote migrated to our brand new crm the first month and integrated our PBX and several other functions within the first 3 months.<p>It's not hard, most CRMs don't need "webscale", you can whip up a highly targeted and integrated CRM in rails in the blink of any eye.<p>That's why I'm pretty sure in 2001/02 I had the earliest real customer, real time, audio reviews published online in the world.<p>Like any decision during a startup buy/build is a situation specific decision you have to make at every point and 3rd party CRMs are fine to launch with... but, I mean, come on.
5/28/2026, 4:10:27 PM
by: ashtondev
[flagged]
5/28/2026, 4:50:43 PM
by: _pdp_
[dead]
5/28/2026, 4:13:12 PM
by: tom86150
[dead]
5/28/2026, 4:02:55 PM
by: dominotw
[flagged]
5/28/2026, 4:02:50 PM