4 AI-assisted testing for developers

According to a poll on dev ecosystems conducted by JetBrains in 2022, 81% of respondents have a developer-to-QA ratio greater than one to one. Forty percent reported that they had “less than 1 QA per 10 developers,” and only 1% reported that they had “more QAs than developers” (see www.jetbrains.com/lp/devecosystem-2022/testing.)

Understanding and building in quality is essential to delivering value to our users, yet the ratio between development and testing is nearly always imbalanced, and this is so for many reasons. Some organizational leaders choose to educate developers to build in quality with the support of quality coaches, and others simply don’t want to invest in roles that advocate for testing and quality. Either way, this situation puts pressure on everyone on a team to deliver high-quality applications. So, how can artificial intelligence (AI) tools help relieve this pressure?

4.1 Examining the rise of the automated developer

4.2 Pairing with LLMs

4.2.1 Analyzing ideas

4.2.2 Analyzing code

4.2.3 Recognizing that a simulation is better than nothing at all

4.3 Building in quality with AI assistance

4.4 Creating our first TDD loop with LLMs

4.4.1 Preparing the work

4.4.2 Loop 1: Save a timesheet entry

4.4.3 Loop 2: Retrieve a timesheet entry

4.4.4 Loop 3: Calculating times for a project

4.4.5 Refactoring code

4.5 Improving documentation and communication with LLMs

4.5.1 Generating code comments

4.5.2 Generating release notes

4.6 Maintaining a balance with code assistants

Summary