Common Mistakes in the Development of AI Assistants

How AI assistants are often developed for companies, why they fail and what we can learn from them.

“The fault-finder will find faults even in ~~paradise~~ in the development of AI assistants.”
_{(Henry David Thoreau ChatGPT)}

How fortunate that people make mistakes: because we can learn from them and improve. We have closely observed how companies around the world have implemented AI assistants in recent months and have, unfortunately, often seen them fail. We would like to share with you how these failures occurred and what can be learned from them for future projects: So that AI assistants can be implemented more successfully in the future!

How AI assistants have been developed in companies so far

A Story in 5 acts: Pitfalls in AI assistant development

Chapter 1: The vision

Every project involving AI assistants starts with an ambitious vision: to develop an assistant that can master specific challenges - from answering complex questions to analyzing business data.

The goals are clear: to increase process efficiency, speed up decision-making and ultimately drive the company's success.

Chapter 2: The research

After thorough research, development teams choose advanced AI tools and platforms, convinced by their maturity and the many success stories in the market.

Popular options such as LangChain, LlamaIndex and QDrant provide the necessary technology to realize ambitious AI assistants.

The development phase is characterized by innovation and creativity. Teams immerse themselves in the world of vector databases, develop intelligent agents and experiment with complex algorithms to bring the first prototypes to life.

The initial results are promising: the AI assistants provide precise and well-founded answers, a strong indication of the project's potential.

Chapter 3: The problems become apparent

However, unexpected difficulties arise after the successful launch.

The systems are prone to errors and "hallucinations", especially for specific queries, which undermines confidence in the technology.

The realization that even advanced AI systems have their limitations leads to the search for solutions to improve accuracy and reliability.

Chapter 4: In search of a solution

Fortunately, public resources offer many ways to improve the accuracy of a misbehaving AI assistant. Well, at least that's what they claim... Common ideas include:

Better prompting
Tweaking retrieval and fine-tuning embeddings
Query transformations (expansion)
Chunk reranking
Adding multiple agents building routers

What actually results from this? Often an unnecessarily complex architecture of the AI assistant. Despite attempts to improve it, it will not always be able to answer simple questions. It will lack accuracy and occasionally generate incorrect information: The system will still hallucinate.

What were the pitfalls that caused the team to fail?

At this point, we have good news: The mistakes that many teams make when developing AI assistants, as described here, can be traced back to three frequently incorrect assumptions:

3 common, incorrect assumptions in AI assistant development

False Assumption 1

"Publicly available materials and articles tell the full truth about how cutting-edge AI systems actually work in business."

False Assumption 2

"If we break our documents into small pieces and then insert them into a vector database, the AI will be able to create meaning from them as if by magic."

False Assumption 3

"We need to build an all-powerful AI assistant with complex architecture to bring real value to the business."

What concrete measures can be derived to successfully implement AI assistants?

Discover our tried-and-tested tips & tricks to help you avoid common pitfalls during implementation and build good AI assistants for companies cost-effectively.

8 tips for developing AI assistants

Would you like to use KI Assistants in your company?

Then we look forward to hearing from you.

First Name *

Last Name *

Company *

E-Mail *

Phone number

Message *

* required

We use the data you send us only for contacting you in connection with your request. You can find all further information in our privacy policy.

Martin Warnung

Sales Consultant TIMETOACT GROUP Österreich GmbH +43 664 881 788 80

Contact

Blog 5/17/24

8 tips for developing AI assistants

8 practical tips for implementing AI assistants

Blog 7/22/24

So You are Building an AI Assistant?

So you are building an AI assistant for the business? This is a popular topic in the companies these days. Everybody seems to be doing that. While running AI Research in the last months, I have discovered that many companies in the USA and Europe are building some sort of AI assistant these days, mostly around enterprise workflow automation and knowledge bases. There are common patterns in how such projects work most of the time. So let me tell you a story...

Technologie

IBM Watson Assistant

Watson Assistant identifies intention in requests that can be received via multiple channels. Watson Assistant is trained based on real-live requests and can understand the context and intent of the query based on the acting AI. Extensive search queries are routed to Watson Discovery and seamlessly embedded into the search result.

Blog

The ROI of Gen AI

Discover how leading companies are already profiting from Gen AI!

Blog 7/22/24

Let's build an Enterprise AI Assistant

Let’s take the basic principles of building AI assistants for a spin with a product case that we worked on: using AI to support enterprise sales pipeline.

Blog 4/16/24

The Intersection of AI and Voice Manipulation

The advent of Artificial Intelligence (AI) in text-to-speech (TTS) technologies has revolutionized the way we interact with written content. Natural Readers, standing at the forefront of this innovation, offers a comprehensive suite of features designed to cater to a broad spectrum of needs, from personal leisure to educational support and commercial use. As we delve into the capabilities of Natural Readers, it's crucial to explore both the advantages it brings to the table and the ethical considerations surrounding voice manipulation in TTS technologies.

Blog

Responsible AI: A Guide to Ethical AI Development

Responsible AI is a key requirement in the development and use of AI technologies. You can find everything you need to know here!

Branche

Digitization of the energy industry

The energy sector is undergoing an unstoppable process of change. Progressive digitization and the energy transition are causing traditional system and process boundaries to disappear.

Blog 2/21/22

The Power of Event Sourcing

This is how we used Event Sourcing to maintain flexibility, handle changes, and ensure efficient error resolution in application development.

Blog 5/25/21

From the idea to the product: The genesis of Skwill

We strongly believe in the benefits of continuous learning at work; this has led us to developing products that we also enjoy using ourselves. Meet Skwill.

Service

Application Development

Application Development refers to the process of modifying, designing and/or developing one or more applications. Gaps in the software landscape can be closed by tailoring applications individually to the customer.

Service 9/12/22

App Development

Integrations, Tools and Apps - customized developments for your Atlassian solutions

Service

Fullstack Development

The trend in Software Development is towards Full-Stack Development. Full-stack developers are programmers who work in both frontend and backend development and thus have competencies in the areas of databases, servers, systems and clients.

Mit Google Cloud passende Lösungen finden

Service

Cloud Development

Finding a standardized solution for complex challenges is unfortunately a rarity. Our experts analyze your problem and present customized solutions.

News 1/26/21

The IPG Group becomes part of the TIMETOACT GROUP

The TIMETOACT GROUP acquires the majority of the shares of IPG Information Process Group Holding AG, based in Winterthur. Through the acquisition, the competencies for Identity and Access Management (IAM) solutions in the DACH market are combined.

News 1/26/21

The IPG Group becomes part of the TIMETOACT GROUP

The TIMETOACT GROUP acquires the majority of the shares of IPG Information Process Group Holding AG, based in Winterthur. Through the acquisition, the competencies for Identity and Access Management (IAM) solutions in the DACH market are combined.

Referenz 4/13/23

The new Idea and Innovation Management of the DDPS

The new solution is available to employees in the familiar portal and in the same design. It is very easy to use and adapted to the needs of the role holders. It was easy to move away from the old platform. The switch to the new solution is rated very positively by all roles.

Unternehmen 7/30/21

Our management – the engine of ARS

Get to know our management team!

Blog 4/8/25

The End of SAP Business ByDesign

This article explores why the end of SAP Business ByDesign is being widely anticipated, what this means for your business, and how you can plan a successful transition to future-ready ERP solutions.

News 3/24/25

SAP Partner of the Year 2025

WCA Walldorf Consulting GmbH has been named “Partner of the Year” by SAP in the SAP S/4HANA Cloud Public Edition category!

Common Mistakes in the Development of AI Assistants