Advice: 1,000+ hours building AI chatbots, don't build your own

I’ve personally spent over 1,000 hours building AI chatbots. Here’s what I’ve learnt over the last 6 months, and why I think the majority of businesses are wasting a huge amount of time and resources when they decide to “build their own” AI chatbots.

Advice: 1,000+ hours building AI chatbots, don't build your own
Created time
Oct 4, 2023 08:03 AM
Image
1000hours.png
Publish date
Sep 4, 2023
Slug
why-you-should-not-build-your-own-ai-chatbot
Featured
Featured
Type
Article
Ready to Publish
Ready to Publish
I’ve personally spent over 1,000 hours building AI chatbots.
Here’s what I’ve learnt over the last 6 months, and why I think the majority of businesses are wasting a huge amount of time and resources when they decide to “build their own” AI chatbots.
Consider this, would you build your own enterprise search for your business?

Are chatbots coming back to life with AI?

Let’s start from the beginning though (as you may not be as hyped about AI chatbots as me…)
When chatbots first arrived on the scene 5 years ago, we thought we were going to be able to say goodbye to human customer support, what went wrong?
 
Chatbot interest over time, Google search trends
Chatbot interest over time, Google search trends
 
Maybe you were one of those who tried to build a chatbot on Facebook Messenger, WhatsApp or Intercom? But then you quickly realised the functionality was clunky and the logic was basic at best, forcing you to predict every question a user might ask in advance.
So customers quickly got fed up with having rigid, dead-end conversations, and, like most companies, you probably gave up on building your chatbot, consigning it to another over-hyped tech trend.
Fast forward to 2023, to the launch ofChatGPTand the rise of Large Language AI Models (LLMs).
Overnight, the capability available to you to build AI chatbots has changed radically. The technology is readily (and cheaply) available for you to create a sophisticated and intelligent AI chatbot for your business.
But the age-old software question still stands - do you build or do you buy?

Why you should build your own AI chatbot

It’s never been easier to build an AI chatbot”— no doubt you’ll have heard this countless times in all those daily AI newsletters.
You’ve probably been eyeing upLangchainorLlama Index, read their docs and a few tutorials, and fancy deploying your own AI bot in a weekend hack.
In fact, here’s exactly how you’d do it:
  1. Fetch, transform, and ingest your data into avector database
  1. Spin up a chat interface from atemplate
  1. Connect to a super-intelligent AI model, likeOpenAI’s ChatGPT, that uses your content and can have a conversation with someone — answering their questions like an expert
Simple right?
 
A standard AI chatbot architecture with access to private data or content
A standard AI chatbot architecture with access to private data or content
 
After your weekend hackathon (and after you’ve shared your MVP with your team), you realize you want to take your AI chatbot to the next stage, after all, now you now have complete control over the:
  • Underlying data used by the chatbot- you can add all your private forecast reports or internal process docs and learning materials.
  • User interface and branding -you can make it feel like it’sreallya part of your existing stack.
  • Data privacy and security -you can decide what happens to a user's chat history, or how ingested data is stored and processed. If your data is particularly sensitive, this may even be table stakes.
  • Access to your secure or private systems -systems that you wouldn’t want to expose to a 3rd Party.
All sounds good, right? But there are some pretty significant drawbacks, and there are some things your team willneedin order to make a success of this.

Why you shouldn’t build your own chatbot

Nothing is ever as easy as it seems.
As useful as the frameworks and libraries are to get you started quickly, they hide a lot of detail and a long list of small decisions that all add up to have a significant impact on the quality of your chatbot (and the risk to your business).
Here are all the things you’ll need to consider and stay on top of if you are going to build yourself:
  • Initial business case:A custom AI chatbot for a business isestimated to cost upwards of $50,000and these costs can quickly spiral upwards for use cases that require a high degree of accuracy or where a company has large volumes of content for the chatbot to access. You will need to justify this to management, likely before you can demonstrate the actual value.
  • AI expertise:You’ll need people in the business who understand how LLMs work at a high level. Especially what they can’t do. This expertise will be essential if you want your chatbot to be more than just a novel toy for customers or employees (better start actually reading that AI book you bought yourself to “get up to speed”)
  • Product continuity:What happens when you leave? Looking forward to having to document how your AI chatbot works for the next person or team?
  • AI provider and model selection:You’ll need to decide on which AI provider you partner with and which AI model you want to use. This will involve weighing up the Pros and Cons and trade-offs you’ll need to make e.g. Speed vs. Cost vs. Quality
  • Keeping up with AI developments:You’ll need a team to constantly stay on top of the latest AI developments to make sure your chatbot is leveraging the newest tech. But importantly, to make sure you’re not reliant on methods that are being phased out. We’ve seen changes to AI models that change answer quality overnight, the solutions for which, never seem to be straightforward!
  • Preparing your data and content: The data processing stage is crucial, this is where your content is manipulated into an optimal format for AI models to use. There are 20+ small, technical, decisions packed into just this topic and hundreds of edge cases to consider (did you know Arabic takes up 4x as many tokens as English for example?). There are already large groups of companies dedicated to solving just this problem, likecarbon.aiandpsychic.dev
  • Automated chat testing:You’ll have to define a testing approach to understand how changes you make affect the quality of your chatbot. The biggest challenge here is the sheer number of permutations that are available to you. We worked out there are over 1 million combinations today, and this grows with every new model and parameter. With each permutation, you have to test your AI chatbot like real humans would — but in an automated way, at scale, to be meaningful.
  • Integrations:Do you want to integrate your chatbot with Slack or Teams? Or embed it on your website? These are all additional features that need to be built and approvals for them takes months with A LOT of back and forth on minor details.
We live and breathe all these topics and challenges every day (and even for us some days they can feel overwhelming!). But we specialise, deeply, in all these areas with a single goal: creating the best AI chatbot to provide answers based on your content.

Why reinvent the wheel?

Now, back to our enterprise search analogy. You wouldn’t consider building it yourself, even though it is fundamental in helping your teams locate the right content or data. You know how intricate and specialized the art ofgoodsearch is. AI chat is much the same but withmuchmore uncertainty.
You also have to ask yourself if there aren’t more important challenges to be working on in your business? For instance, considering where AI fits more strategically, instead of how you are going to pre-process 5,000 PDF reports.
So, after 1,000+ hours building AI chatbots, I’m confident when I say that for 90%+ of businesses, buying in your AI chatbot solution is the way to go, but if you are still not convinced, here is the breakdown to help:
 
If you want to BUILD…
If you want to BUY…
AI capability and knowledge
Existing internal AI capability or expertise
Limited or no existing AI knowledge in the business
Data sensitivity
Highly sensitive data is required for the AI chatbot to access
Private (not highly sensitive) or public data and content
Content type
Business content is static and limited to <500 items/reports/documents
Business content can be dynamic, growing, and, available in large volumes of >1,000 items/reports/documents
Dedicated team
Ability to dedicate a team to building and managing an AI chatbot
Objective to integrate AI chatbot capability into an existing team to manage (like enterprise search)
Chatbot as core differentiator
You expect an AI chatbot to be a significant differentiator and part of your business’s offering
An AI chatbot will leverage or enrich your business’s existing core offering e.g. your editorial trend reports
 
And while you may think thatSlackorTeamsintegrations,personalization,data security, andenterprise controlsare other reasons to build your own. With My AskAI, and some other providers, these features come out of the box.
Of course, your ‘buy instead of build’ strategy may change over time. For example, if your chatbot becomes a central part of your business offering or how it works, then it might justify the investment to build your own at some stage. But initially, while you dip your toes to see where generative AI solutions, like a chatbot, fit within your business. It’s probably best to just optimize for learning quickly and getting something live.

So, what next?

The best thing you can do for your business is to start. Today.
The average My AskAI customer has their first AI chatbot live in under 10 mins.We’ve become known for being the easiest place to launch an AI chatbot.
 
We’ve helped over 30,000 businesses build an AI chatbot, trained on their own data and content, branded and personalized, and launched to where their customers or employeesmostneed it.
 
notion image
 
Try us out for free today— you can always tell your boss you built it😉
 

Start using AI customer support in your business today

Create free AI agent

Written by

Alex Rainey
Alex Rainey

Alex is an experienced CTO and founder who largely focuses on all the technical areas of My AskAI, from AI Engineering, Technical Product Management and overall Platform Development.

Related posts

Are AI chatbots the future of UX?

Are AI chatbots the future of UX?

Artificial intelligence (AI) has transformed the way we interact with technology, and AI chatbots are at the forefront of this revolution. OpenAI's ChatGPT is a prime example of the strides made in chatbot technology, yet skepticism remains among some.

We Explored 5 of the Best PDF.ai Alternatives

We Explored 5 of the Best PDF.ai Alternatives

We explored 5 of the best PDF.ai alternatives to help you start chatting and getting answers from all your PDFs

Best ChatPDF Alternatives We’ve Found For You

Best ChatPDF Alternatives We’ve Found For You

In this My AskAI guide, we introduce you to eight ChatPDF alternatives that you can use to create PDF files from your chats. We cover features, pricing, and more to help you make the right call for your business.

Great Chatbase Alternatives For Every Use

Great Chatbase Alternatives For Every Use

In this My AskAI guide, we explore the key features and benefits of these Chatbase alternatives. From advanced customization options to comprehensive analytics, we’ve got you covered.

Here’s Our List of the 5 Best Chat PDF Tools Available Now

Here’s Our List of the 5 Best Chat PDF Tools Available Now

Chat PDF tools like My AskAI transform static PDFs into searchable wells of information and insights—helping to make workflows more efficient. Rather than searching for information manually, you can ask questions in natural language and get the correct answers instantly.

Our List of the 5 Best AI Customer Support Software

Our List of the 5 Best AI Customer Support Software

This article explores the benefits of AI customer support software and provides a comprehensive list of some of the top tools out there.

Here Are the 5 Best AI Assistants We’ve Found

Here Are the 5 Best AI Assistants We’ve Found

Learn all about AI assistants and discover the 5 best tools for automating tedious tasks.

8 Best Customer Support Chatbots

8 Best Customer Support Chatbots

Maximize your business performance and customer satisfaction with our best customer support chatbots in 2024.

Alex Rainey, co-founder, My AskAI

Alex Rainey, co-founder, My AskAI

Learn more about Alex’s role at My AskAI, his previous experience, hobbies and interests, and how you can contact him or read more of his content.

Silly Headline from Goldman Sachs AI Report

Silly Headline from Goldman Sachs AI Report

Goldman Sachs' recent AI report headline is misleading. They compare forecasted AI investments with current economic benefits, ignoring long-term ROI. This premature analysis overlooks the rapid advancements and potential of AI technology. Here's why their perspective is flawed.

Why Building Your Own AI Assistant Could Hurt Your Business

Why Building Your Own AI Assistant Could Hurt Your Business

Focus on your core business like Jeff Bezos advises. Discover why outsourcing AI assistants for customer support can enhance efficiency and quality. Try My AskAI to automate 75%+ of your support and let your team focus on what truly matters.

The Path to Startup Success: Embrace Failures and Learn More

The Path to Startup Success: Embrace Failures and Learn More

Discover why struggling founders learn more and build lasting success. Embrace obstacles, gain invaluable insights, and create a mental playbook for startup triumph. Learn the true path to sustainable growth beyond quick wins and viral success.