Gartner Insights Abstract

Early Lessons in Building LLM-Based Generative AI Solutions

Published: 06 August 2024

Summary

Enterprises building GenAI applications that incorporate large language models are experiencing problems with hallucinations, grounding, poor user experience and inappropriate data stores for use with LLMs. Software engineering leaders must address these issues to ensure successful use of GenAI.

Included in Full Research

Overview

Key Findings
  • Large language models (LLMs) are subject to frequent inaccuracies (also known as “hallucinations”) leading to the increasing importance of grounding of the models and rigorous prompt design.

  • LLMs need to be as accurate as possible, which can be aided by retrieval-augmented generation (RAG) and/or fine tuning with relevant data in the right granularity.

  • End users struggle to adopt the new ways of working required by generative AI (GenAI) applications that have been built using LLMs.

Recommendations
  • Deploy the RAG to ensure that your LLMs are grounded using relevant data and architectures.

  • Plan to add metadata to data stores when needed, as this

Clients can log in to view the entire document.

Analysts:

Van Baker Haritha Khandabattu Philip Walsh

Access Insights

Already a Gartner client?

To access these insights and much more, talk to Gartner today.

Fill out the form to connect with a specialist to learn how we can help you.

By clicking the "Continue" button, you are agreeing to the Gartner Terms of Use and Privacy Policy.

AskGartner: The AI-powered tool our clients use to find trusted Gartner insights, instantly.

AskGartner | Discover the new AI-powered tool to access trusted Gartner insights

Gartner research: Trusted insight for executives and their teams

What is Gartner research?

Gartner research, which includes in-depth proprietary studies, peer and industry best practices, trend analysis and quantitative modeling, enables us to offer innovative approaches that can help you drive stronger, more sustainable business performance.

Gartner research is unique, thanks to:

Independence and objectivity

Our independence as a research firm enables our experts to provide unbiased advice you can trust.

Actionable insights

Not only is Gartner research unbiased, it also contains key take-aways and recommendations for impactful next steps.

Proprietary methodologies

Our research practices and procedures distill large volumes of data into clear, precise recommendations.

Gartner research is just one of our many offerings.

We provide actionable, objective insight to help organizations make smarter, faster decisions to stay ahead of disruption and accelerate growth.

Tap into our experts

We offer one-on-one guidance tailored to your mission-critical priorities.

Pick the right tools and providers

We work with you to select the best-fit providers and tools, so you avoid the costly repercussions of a poor decision.

Create a network

Connect directly with peers to discuss common issues and initiatives and accelerate, validate and solidify your strategy.

© 2026 Gartner, Inc. and/or its affiliates. All rights reserved. Gartner is a registered trademark of Gartner, Inc. and its affiliates. This publication may not be reproduced or distributed in any form without Gartner's prior written permission. It consists of the opinions of Gartner's business and technology insights organization, which should not be construed as statements of fact. While the information contained in this publication has been obtained from sources believed to be reliable, Gartner disclaims all warranties as to the accuracy, completeness or adequacy of such information. Although Gartner business and technology insights may address legal and financial issues, Gartner does not provide legal or investment advice and its insights should not be construed or used as such. Your access and use of this publication are governed by Gartner’s Usage Policy. Gartner prides itself on its reputation for independence and objectivity. Its insights are produced independently by its business and technology insights organization without input or influence from any third party. For further information, see Guiding Principles on Independence and Objectivity. Gartner publications and other content may not be used as input into or for the training or development of generative artificial intelligence, machine learning, algorithms, software or related technologies.