Exploring Generative AI


TDD with GitHub Copilot

by Paul Sobocinski

Will the appearance of AI coding assistants corresponding to GitHub Copilot imply that we received’t want assessments? Will TDD change into out of date? To reply this, let’s look at two methods TDD helps software program growth: offering good suggestions, and a method to “divide and conquer” when fixing issues.

TDD for good suggestions

Good suggestions is quick and correct. In each regards, nothing beats beginning with a well-written unit check. Not guide testing, not documentation, not code overview, and sure, not even Generative AI. In reality, LLMs present irrelevant data and even hallucinate. TDD is very wanted when utilizing AI coding assistants. For a similar causes we’d like quick and correct suggestions on the code we write, we’d like quick and correct suggestions on the code our AI coding assistant writes.

TDD to divide-and-conquer issues

Downside-solving through divide-and-conquer implies that smaller issues could be solved ahead of bigger ones. This allows Steady Integration, Trunk-Based mostly Improvement, and finally Steady Supply. However do we actually want all this if AI assistants do the coding for us?

Sure. LLMs not often present the precise performance we’d like after a single immediate. So iterative growth shouldn’t be going away but. Additionally, LLMs seem to “elicit reasoning” (see linked research) once they remedy issues incrementally through chain-of-thought prompting. LLM-based AI coding assistants carry out finest once they divide-and-conquer issues, and TDD is how we try this for software program growth.

TDD ideas for GitHub Copilot

At Thoughtworks, we now have been utilizing GitHub Copilot with TDD because the begin of the yr. Our aim has been to experiment with, consider, and evolve a collection of efficient practices round use of the software.

0. Getting began

TDD represented as a three-part wheel with 'Getting Started' highlighted in the center

Beginning with a clean check file doesn’t imply beginning with a clean context. We regularly begin from a person story with some tough notes. We additionally speak by a place to begin with our pairing associate.

That is all context that Copilot doesn’t “see” till we put it in an open file (e.g. the highest of our check file). Copilot can work with typos, point-form, poor grammar — you identify it. However it might’t work with a clean file.

Some examples of beginning context which have labored for us:

  • ASCII artwork mockup
  • Acceptance Standards
  • Guiding Assumptions corresponding to:
    • “No GUI wanted”
    • “Use Object Oriented Programming” (vs. Purposeful Programming)

Copilot makes use of open recordsdata for context, so retaining each the check and the implementation file open (e.g. side-by-side) vastly improves Copilot’s code completion skill.

1. Crimson

TDD represented as a three-part wheel with the 'Red' portion highlighted on the top left third

We start by writing a descriptive check instance identify. The extra descriptive the identify, the higher the efficiency of Copilot’s code completion.

We discover {that a} Given-When-Then construction helps in 3 ways. First, it reminds us to supply enterprise context. Second, it permits for Copilot to supply wealthy and expressive naming suggestions for check examples. Third, it reveals Copilot’s “understanding” of the issue from the top-of-file context (described within the prior part).

For instance, if we’re engaged on backend code, and Copilot is code-completing our check instance identify to be, “given the person… clicks the purchase button, this tells us that we should always replace the top-of-file context to specify, “assume no GUI” or, “this check suite interfaces with the API endpoints of a Python Flask app”.

Extra “gotchas” to be careful for:

  • Copilot could code-complete a number of assessments at a time. These assessments are sometimes ineffective (we delete them).
  • As we add extra assessments, Copilot will code-complete a number of traces as an alternative of 1 line at-a-time. It should typically infer the right “organize” and “act” steps from the check names.
    • Right here’s the gotcha: it infers the right “assert” step much less typically, so we’re particularly cautious right here that the brand new check is appropriately failing earlier than transferring onto the “inexperienced” step.

2. Inexperienced

TDD represented as a three-part wheel with the 'Green' portion highlighted on the top right third

Now we’re prepared for Copilot to assist with the implementation. An already current, expressive and readable check suite maximizes Copilot’s potential at this step.

Having stated that, Copilot typically fails to take “child steps”. For instance, when including a brand new technique, the “child step” means returning a hard-coded worth that passes the check. So far, we haven’t been in a position to coax Copilot to take this method.

Backfilling assessments

As a substitute of taking “child steps”, Copilot jumps forward and gives performance that, whereas typically related, shouldn’t be but examined. As a workaround, we “backfill” the lacking assessments. Whereas this diverges from the usual TDD stream, we now have but to see any severe points with our workaround.

Delete and regenerate

For implementation code that wants updating, the simplest method to contain Copilot is to delete the implementation and have it regenerate the code from scratch. If this fails, deleting the tactic contents and writing out the step-by-step method utilizing code feedback could assist. Failing that, one of the best ways ahead could also be to easily flip off Copilot momentarily and code out the answer manually.

3. Refactor

TDD represented as a three-part wheel with the 'Refactor' portion highlighted on the bottom third

Refactoring in TDD means making incremental modifications that enhance the maintainability and extensibility of the codebase, all carried out whereas preserving conduct (and a working codebase).

For this, we’ve discovered Copilot’s skill restricted. Think about two situations:

  1. “I do know the refactor transfer I wish to strive”: IDE refactor shortcuts and options corresponding to multi-cursor choose get us the place we wish to go quicker than Copilot.
  2. “I don’t know which refactor transfer to take”: Copilot code completion can not information us by a refactor. Nonetheless, Copilot Chat could make code enchancment options proper within the IDE. We now have began exploring that function, and see the promise for making helpful options in a small, localized scope. However we now have not had a lot success but for larger-scale refactoring options (i.e. past a single technique/operate).

Typically we all know the refactor transfer however we don’t know the syntax wanted to hold it out. For instance, making a check mock that may permit us to inject a dependency. For these conditions, Copilot will help present an in-line reply when prompted through a code remark. This protects us from context-switching to documentation or net search.


The frequent saying, “rubbish in, rubbish out” applies to each Information Engineering in addition to Generative AI and LLMs. Said otherwise: greater high quality inputs permit for the potential of LLMs to be higher leveraged. In our case, TDD maintains a excessive stage of code high quality. This prime quality enter results in higher Copilot efficiency than is in any other case attainable.

We due to this fact advocate utilizing Copilot with TDD, and we hope that you simply discover the above ideas useful for doing so.

Because of the “Ensembling with Copilot” crew began at Thoughtworks Canada; they’re the first supply of the findings coated on this memo: Om, Vivian, Nenad, Rishi, Zack, Eren, Janice, Yada, Geet, and Matthew.


Leave a Reply

Your email address will not be published. Required fields are marked *