5 Test planning with AI support

 

This chapter covers

  • Associating the value of models with the use of LLMs
  • Using models with LLMs to assist test planning
  • Evaluating the suitability of suggestions generated by LLMs

Now that we’ve started to see how LLMs can help support quality in development, it’s time to tackle the question of whether LLMs generate test cases. On one level, the answer is simple: Yes they can. But the deeper and more important question would be why would you want them to? What are we hoping to achieve by generating swathes of test cases without thought or direction? Just because we can create test cases doesn’t necessarily mean it’s the right thing to do in a given situation.

5.1 Defining test planning in modern testing

5.1.1 Test planning, LLMs and area of effect

5.2 Focused prompts with the use of models

5.2.1 Weak prompts mean weak suggestions

5.2.2 What are models and why can they help

5.3 Combining models and LLMs to assist test planning

5.3.1 Creating a model to identify prompts

5.3.2 Experimenting with different model types

5.4 LLMs and test cases

5.4.1 Having a healthy skepticism of generated risks and test cases

5.5 Summary