Study Copilot for boilerplate code and testing
Okta engineers used Copilot for routine coding and testing. A study involving 74 survey participants found improved motivation and perceived skills, but no significant change in pull requests, code volume or cycle time. Later results for Claude Code are separate.
Source checked: the source link is valid and the automated fact check passed. The summary is AI-assisted. This is not human verification. Check the original source before relying on its claims.
For whom
Engineering leaders in medium or large companies; access to development metrics.
Not for
Unsuitable for treating developer satisfaction as proof of higher organizational output.
Brain Score
- Impact
- 0/2
- Evidence
- 1/2
- Reproducibility
- 1/2
- Maturity
- 2/2
- Reach
- 1/2
Five values from 0 to 2. The total has a minimum of 1. A reading aid based on the source, not an independently measured performance result. How the score works
Still current?
Partly, better ways exist
Today: Use Copilot agents to generate and run tests; the reported Copilot study measured a 2024 assistant workflow.
Augments or replaces?
Augments your skills
Today: Engineers retain coding and testing decisions while AI drafts boilerplate and suggests tests.
Original source
- Type
- Blog
- Published
- Data as of
The data date records when this dataset was included in the collection. It is separate from the publication date of the source.