Guide to AI assisted engineering

Rolling out AI code assistants is becoming a key priority for many technology organizations. Despite significant enthusiasm around these tools, achieving widespread developer adoption and optimal usage remains challenging.

Industry research consistently highlights a critical barrier: AI-driven coding requires new techniques many developers do not know yet. Without clear instructions and best practices, developers struggle to integrate these tools efficiently into their workflows, especially when time is limited.

This guide addresses these challenges directly. Drawing from interviews and empirical data collected from AI-savvy engineers across various organizations, it provides concrete strategies for developers on how to leverage the benefits of AI assistants, along with guidance for leaders contained in the appendix. While large language models (LLMs) offer transformative potential for productivity, their impact is contingent on thoughtful adoption. Organizations investing in AI technology must prioritize educating and supporting their developers to unlock the full value of these innovations.

In addition to developer enablement, ongoing measurement of AI adoption and impact is critical for maximizing ROI from AI code assistants. For guidance on how to measure AI’s impact on productivity, read How to Measure GenAI Adoption and Impact. GenAI assistants have the capacity to be transformative productivity boosters, but just like any other technology investment, success requires diligence and advocacy.

How to use this guide

This guide is split into three sections, each of which can augment and enhance utilization and integration of AI code assistants into daily workflows. Each section is meant to be utilized in a specific way, as described below:

• Effective AI prompting techniques - Coding assistants, just like any other tool, can be used optimally or suboptimally depending on the experience and knowledge of the user. This section illustrates some of the practices used by advanced AI users to elicit the best responses from GenAI models.
• Top developer-recommended use cases - Here, the top ten most valuable use cases for AI are outlined, according to self-reported stack ranking of use cases based on perceived time savings. Distribute these use cases to individual engineers, and ensure that users are not blocked from taking advantage of them.
• Leadership strategies for encouraging AI use - Meant for engineering leaders who will distribute this guide to their developers, this section will outline the behaviors and responsibilities of leadership for driving success of AI initiatives within an organization.