18d • AI&QA
Autonomous Exploratory Testing with Playwright CLI and AI Agents
You cannot be in two places at once. But your AI agent can.
Learn how to use AI agents with Playwright CLI to do exploratory testing, while you are working in parallel on something more fun.
────────────────────────────────────────
🧠 𝐖𝐡𝐚𝐭 𝐝𝐨𝐞𝐬 𝐡𝐮𝐦𝐚𝐧 𝐞𝐱𝐩𝐥𝐨𝐫𝐚𝐭𝐨𝐫𝐲 𝐭𝐞𝐬𝐭𝐢𝐧𝐠 𝐥𝐨𝐨𝐤 𝐥𝐢𝐤𝐞?
A tester:
∙ Thinks about what to try next
∙ Clicks, observes, and takes notes
∙ Stops when something blocks them
∙ Hands findings to the team
Playwright CLI + AI coding agent can do the same. Completely autonomously.
And you can set it up and configure it in 30 minutes, then send it to work for hours.
⚙️ 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐬𝐞𝐭𝐮𝐩:
You need to create only 1 file `𝐬𝐭𝐞𝐩𝐬.𝐦𝐝` that defines the mission and the rules for the agent:
- How to use Playwright CLI
- Start URL (and environment)
- Scope. What area or flow to explore:
- What area of the application should be covered and what should ignored.
- Credentials or test data (or where to find them)
- Rules. What to look for and what to ignore
- Where to write the report with all findings: `𝐫𝐞𝐩𝐨𝐫𝐭.𝐦𝐝`
📌 𝐑𝐮𝐥𝐞𝐬 𝐒𝐞𝐜𝐭𝐢𝐨𝐧 𝐁𝐫𝐞𝐚𝐤𝐝𝐨𝐰𝐧 in `𝐬𝐭𝐞𝐩𝐬.𝐦𝐝`
────────────────────────
What to look for (report these):
⤷ Functional bugs. Button does nothing, wrong redirect, form does not submit
⤷ Broken UI. Missing elements, layout breaks, overlapping content
⤷ Wrong or missing copy on critical paths (checkout, login, errors)
⤷ JavaScript errors that break user actions
⤷ Failed network requests on critical APIs (auth, payment, save)
⤷ Accessibility blockers.
⤷ Dead ends. 404, infinite spinner, error with no recovery
What to ignore:
⤷ Third-party analytics / tracking failures (Google Analytics, etc.)
⤷ Benign console warnings (deprecated API in a vendor script)
⤷ Cosmetic-only issues (misalignments, font weight on footer)
⤷ Cookie banner / GDPR UI unless it blocks the flow under test
────────────────────────
After you are done with the `𝐬𝐭𝐞𝐩𝐬.𝐦𝐝`, just point the AI agent to the file and let it loose. The agent will read the file and create an empty `𝐫𝐞𝐩𝐨𝐫𝐭.𝐦𝐝` to fill as it goes.
🔍 𝐇𝐨𝐰 𝐈𝐭 𝐖𝐨𝐫𝐤𝐬 𝐔𝐧𝐝𝐞𝐫 𝐭𝐡𝐞 𝐇𝐨𝐨𝐝
For each step the agent performs:
∙ `open` / `goto` the page using Playwright CLI
∙ `snapshot` to read what is on screen
∙ Decide the next action (click, fill, navigate)
∙ Run the action
∙ `snapshot` again
∙ Append findings to `𝐫𝐞𝐩𝐨𝐫𝐭.𝐦𝐝`
∙ Move to the next step
𝐓𝐡𝐞 𝐚𝐠𝐞𝐧𝐭 𝐬𝐭𝐨𝐩𝐬 𝐨𝐧𝐥𝐲 𝐨𝐧 𝐚 𝐜𝐨𝐦𝐩𝐥𝐞𝐭𝐞 𝐛𝐥𝐨𝐜𝐤𝐞𝐫:
∙ Login wall with no credentials
∙ Captcha or MFA with no bypass
∙ Missing test data that cannot be inferred
∙ Environment down (5xx, blank page, cannot load app)
𝐀𝐭 𝐭𝐡𝐞 𝐞𝐧𝐝 𝐲𝐨𝐮 𝐫𝐞𝐯𝐢𝐞𝐰 𝐫𝐞𝐩𝐨𝐫𝐭.𝐦𝐝 𝐚𝐧𝐝 𝐝𝐞𝐜𝐢𝐝𝐞 𝐰𝐡𝐚𝐭 𝐭𝐨 𝐝𝐨 𝐧𝐞𝐱𝐭.
────────────────────────────────────────
📋 Why `𝐫𝐞𝐩𝐨𝐫𝐭.𝐦𝐝` is important
The agent writes to `𝐫𝐞𝐩𝐨𝐫𝐭.𝐦𝐝` after every single step:
∙𝐘𝐨𝐮 𝐜𝐚𝐧 𝐰𝐚𝐭𝐜𝐡 𝐢𝐭 𝐥𝐢𝐯𝐞. Open the file while the agent runs and see findings appear in real time. No need to wait for it to finish.
∙ 𝐍𝐨𝐭𝐡𝐢𝐧𝐠 𝐠𝐞𝐭𝐬 𝐥𝐨𝐬𝐭. If the agent hits a blocker or crashes mid-session, everything found up to that point is already saved.
At the end you get a flat list of every action taken and every bug found.
────────────────────────────────────────
🟠 𝐏𝐫𝐚𝐜𝐭𝐢𝐜𝐚𝐥 𝐓𝐢𝐩𝐬
⧽ Run in parallel, not in series
If you have a few user workflows, run a few agents in parallel. Just open different AI chat windows and give each agent its own rules file.
⧽ Headed vs headless
First run on a new flow: headed, so you can glance at the browser if needed. Repeat runs on the same flow: headless is fine.
⧽ Exploration ≠ automation
This is not a replacement for automation. Automation is deterministic; this approach is not. It is designed to mimic a human tester doing exploratory testing with somewhat random steps.
────────────────────────────────────────
📌 Want to set this up on your repo with rules files, report templates, and live agent workflows?
Join the AI AutoTest Live Workshop — hands-on practice with Playwright CLI, exploratory charters, and QA-specific agent instructions.
👉 Click here to read more: https://www.skool.com/qa-automation-career-hub/welcome-to-qa-automation-roadmap-lab-start-here
4
0 comments
Autonomous Exploratory Testing with Playwright CLI and AI Agents
skool.com/qa-automation-career-hub
From QA Automation to AI-Powered SDET. Join AI & QA Accelerator.
Powered by