FAQ¶
Question: Can PR-Agent serve as a substitute for a human reviewer?
Answer:¶
PR-Agent is designed to assist, not replace, human reviewers.
Reviewing PRs is a tedious and time-consuming task often seen as a "chore". In addition, the longer the PR – the shorter the relative feedback, since long PRs can overwhelm reviewers, both in terms of technical difficulty, and the actual review time. PR-Agent aims to address these pain points, and to assist and empower both the PR author and reviewer.
However, PR-Agent has built-in safeguards to ensure the developer remains in the driver's seat. For example:
- Preserves user's original PR header
- Places user's description above the AI-generated PR description
- Cannot approve PRs; approval remains reviewer's responsibility
- The code suggestions are optional, and aim to:
- Encourage self-review and self-reflection
- Highlight potential bugs or oversights
- Enhance code quality and promote best practices
Read more about this issue in our blog
Question: I received an incorrect or irrelevant suggestion. Why?
Answer:¶
- Modern AI models, like Claude 3.5 Sonnet and GPT-4, are improving rapidly but remain imperfect. Users should critically evaluate all suggestions rather than accepting them automatically.
-
AI errors are rare, but possible. A main value from reviewing the code suggestions lies in their high probability of catching mistakes or bugs made by the PR author. We believe it's worth spending 30-60 seconds reviewing suggestions, even if some aren't relevant, as this practice can enhances code quality and prevent bugs in production.
-
The hierarchical structure of the suggestions is designed to help the user to quickly understand them, and to decide which ones are relevant and which are not:
- Only if the
Category
header is relevant, the user should move to the summarized suggestion description. - Only if the summarized suggestion description is relevant, the user should click on the collapsible, to read the full suggestion description with a code preview example.
- Only if the
-
In addition, we recommend to use the
extra_instructions
field to guide the model to suggestions that are more relevant to the specific needs of the project. - The interactive PR chat also provides an easy way to get more tailored suggestions and feedback from the AI model.
Question: How can I get more tailored suggestions?
Answer:¶
See here for more information on how to use the extra_instructions
and best_practices
configuration options, to guide the model to more tailored suggestions.
Question: Will you store my code ? Are you using my code to train models?
Answer:¶
No. PR-Agent strict privacy policy ensures that your code is not stored or used for training purposes.
For a detailed overview of our data privacy policy, please refer to this link
Question: Can I use my own LLM keys with PR-Agent?
Answer:¶
When you self-host, you use your own keys.
PR-Agent Pro with SaaS deployment is a hosted version of PR-Agent, where Codium AI manages the infrastructure and the keys. For enterprise customers, on-prem deployment is also available. Contact us for more information.