The tool can be triggered automatically every time a new PR is [opened](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened), or it can be invoked manually by commenting on any PR:
Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (might use multiple calls to GPT-4 for large PRs).
To edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66) related to the improve tool (`pr_code_suggestions` section), use the following template:
Extra instructions are very important for the `imrpove` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
Examples for extra instructions:
```
[pr_code_suggestions] # /improve #
extra_instructions="""
Emphasize the following aspects:
- Does the code logic cover relevant edge cases?
- Is the code logic clear and easy to understand?
- Is the code logic efficient?
...
"""
```
Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
- While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically. Critical reading and judgment are required.
- While mistakes of the AI are rare but can happen, a real benefit of the tool is to catch, with high probability, **mistakes or bugs done by the PR author**, when they happen. So, it's a good practice to spend the needed ~30-60 seconds to review the suggestions, even if not all of them are relevant.
- The hierarchical structure of the suggestions UI-UX 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 collpasible, to read the full suggestion description with a code preview example.
In addition, we recommend to use the `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project.
<br>
Consider also trying the [Custom Suggestions Tool](./custom_suggestions.md) 💎, that will **only** propose suggestions that follow specific guidelines defined by user.
