Build guide

How to build a code review bot with Vikasit AI

A code review bot reads a diff and posts focused feedback on correctness, security, and maintainability. Hook it into CI or your Git host so every pull request gets an automatic first-pass review.

Recommended model

Vikasit 3 Coder

Tuned for code understanding and structured output, so it produces precise, actionable review comments.

Steps

1
Fetch the diff for the pull request (e.g. via the Git host API or git diff).
2
Construct a prompt asking for review comments grouped by severity.
3
Send the diff to vikasit-3-coder with a system prompt that defines your review standards.
4
Parse the model's response into individual comments.
5
Post the comments back to the pull request via the host API.
6
Run it in CI on every PR; cap diff size and chunk large diffs.

Code

The Vikasit Inference API is OpenAI-compatible, so this uses the standard OpenAI Python SDK pointed at https://api.vikasit.ai/v1.

code-review-bot.py

from openai import OpenAI

client = OpenAI(
    base_url="https://api.vikasit.ai/v1",
    api_key="sk-vikasit-...",  # get one at vikasit.ai/auth
)

def review_diff(diff: str) -> str:
    resp = client.chat.completions.create(
        model="vikasit-3-coder",
        messages=[
            {
                "role": "system",
                "content": (
                    "You are a senior code reviewer. Report bugs, security issues, "
                    "and maintainability concerns. One finding per line: "
                    "severity, location, problem, fix."
                ),
            },
            {"role": "user", "content": f"Review this diff:\n{diff}"},
        ],
    )
    return resp.choices[0].message.content

Build your code review bot today

Get an API key and 2M free tokens a day on Vikasit Nova. Pay-as-you-go, no minimums, OpenAI-compatible.

Get an API key See all models & pricing