Skip to main content
Bugzy participates in your software development lifecycle the way a QA teammate would — reacting to changes, proposing actions, executing tests, and reporting back. This page explains the interaction model.

​
Triggers and tasks

Everything starts with a trigger. A trigger runs a predefined or preconfigured task: 
Trigger (manual via UI, Slack/Teams message, GitHub event, deployment, schedule)
  → Task executes (tests, triage, verification, exploration)
    → Results reported back (Slack, Teams, PR comment, dashboard)
      → Team provides feedback (dispute findings, ask questions)
        → Bugzy learns and improves
Some triggers execute automatically — cron schedules, deployment hooks, and GitHub webhooks run their configured task without manual confirmation. Conversational triggers like Slack or Teams messages go through a confirmation step via the blocked-task-queue, giving your team a chance to review before Bugzy acts.

​
Tasks

Bugzy uses a task-based architecture. Each task is a step-by-step workflow that composes subagents to accomplish a goal.
TaskWhat Bugzy does
onboard-testingEnd-to-end onboarding: explore app, plan, generate tests, execute, fix, report
generate-test-planCreates a structured test plan from product description + browser exploration
generate-test-casesConverts test plan into manual test docs + automated Playwright scripts
run-testsExecutes tests, triages, auto-fixes, files bugs, notifies team
verify-changesRuns relevant tests after a code change (PR, deployment, ticket)
triage-resultsClassifies failures as product bugs vs test issues
explore-test-codebaseAnalyzes an existing test repo to understand structure and patterns
handle-messageResponds to team messages from Slack or Teams
process-eventHandles webhook events (GitHub, Jira, meeting transcripts)

​
Subagents

Subagents are specialized AI capabilities that tasks compose together. You configure which subagents are active and which integrations they use during project setup.
SubagentRoleAlways active
Browser AutomationNavigates pages, interacts with UI via PlaywrightYes
Test EngineerGenerates Playwright scripts, debugs failures, fixes flaky testsYes
Test Case ManagerManages test cases via filesystem or external TMS (Zephyr Scale)Yes
Team CommunicatorPosts results to Slack, Teams, or emailYes
Issue TrackerFiles bugs in Jira, Azure DevOps, Asana, or LinearWhen connected
Documentation ResearcherSearches Notion, Confluence, or Jira wikis for product contextWhen connected
Source ControlReads PR/commit history, posts PR comments, creates check runsWhen connected

​
Deep dive

Execution environment

Container isolation, the 15-step pipeline, and where test artifacts live.

Extend test coverage

How Bugzy generates test plans and Playwright automation.