Agent

Overview

An agentic QA engine that finds bugs, writes tests, reviews code, and opens pull requests with fixes.

The Paragon Agent is an agentic QA engine that clones your repository, analyzes your code for issues, writes tests, and opens pull requests with fixes. Use it from the dashboard, trigger it from GitHub comments and Slack, or automate it on schedules and events.

What It Can Do

  • Find and fix bugs — Point it at an issue, error, or flaky test and it investigates and patches
  • Write and improve tests — Generate unit tests, integration tests, and increase coverage across your codebase
  • Review code quality — Catch security vulnerabilities, performance issues, and regressions before they ship
  • Validate changes — Run builds, execute test suites, and verify nothing breaks

How It Works

  1. Select a repository — Choose a connected GitHub repository and branch
  2. Describe the task — Tell the agent what you want reviewed, tested, or fixed
  3. Agent executes — The agent clones your repo, analyzes the code, runs tests, and makes changes
  4. Review the PR — Review the diff in the dashboard or on the generated pull request

Session Modes

Paragon offers two session modes depending on task complexity:

ModeBest ForDurationHow It Works
StandardQuick bug fixes, test generation, code reviewMinutesSingle agent processes your prompt directly
GrindComprehensive test coverage, large-scale refactors, multi-file fixesHoursPlans first, then delegates to parallel workers

Models

Choose a model tier when creating a session:

ModelSpeedBest For
MaxSlowestComplex debugging, nuanced code review, architecture-level issues
MidBalancedMost tasks — good balance of quality and speed
FastFastestSimple fixes, test generation, straightforward patches

Next Steps