Tester Agent · User Manual

Tester Agent Manual

Everything you need to know about your resident QA engineer — what it tests, how to read test reports, how to set up your test suite, and how to direct it to investigate regressions.

Contents
1. What the Tester Agent does2. Test types3. Setting up your test suite4. E2E testing5. Load testing6. Accessibility testing7. Auth & security testing8. Schema change detection9. Automatic bug reports10. Reading test reports11. Communicating with your agent12. Best practices13. Tier capabilities14. Troubleshooting

1. What the Tester Agent does

The Tester Agent is your always-on QA engineer. It runs your test suite on a schedule, detects regressions the moment they appear, and automatically files detailed bug reports with reproduction steps. It covers end-to-end flows, API contracts, load limits, accessibility compliance, authentication edge cases, and schema changes.

Unlike a CI pipeline that only runs on push, the Tester Agent also runs proactively on a schedule — so a regression caused by a third-party dependency update or an infrastructure change will be caught even if no code was deployed.

2. Test types

Test typeWhat it checksRun frequency
E2E flowsCritical user journeys: signup, login, checkout, core feature useEvery 30 min (Pro), every 5 min (Studio)
API contractHTTP response shapes match expected schema; status codes correctOn every API schema change + scheduled
Load testThroughput, latency, error rate under simulated concurrent usersWeekly (Pro), daily (Studio), on demand
AccessibilityWCAG 2.1 AA compliance: contrast, ARIA, keyboard nav, screen reader flowWeekly crawl on all public pages
Auth & securityAuth token expiry, CSRF protection, privilege escalation, rate limitingDaily on all auth endpoints
Schema watcherAPI response shape changes; database schema migrations; OpenAPI spec driftOn every deploy + continuous monitoring

3. Setting up your test suite

Getting started takes one message. Tell the agent your app URL, the critical flows to test, and any credentials needed. The agent generates a test plan, confirms it with you, and starts running.

First message example:

"My app is at staging.myapp.com. The critical flows are: user signup, login, creating a project, and inviting a team member. Login credentials for the test account: test@myapp.com / TestPass123. Also monitor the public /api/health and /api/v1/projects endpoints. Start with a full E2E run and set up daily scheduling."

What to give the agent upfront

InfoWhy it matters
Base URL (staging or prod)Agent needs the target environment
Test credentialsLogin + any API keys needed to exercise auth flows
Critical user flows (list them)Agent writes E2E scripts for these first
Endpoints to monitorAgent adds these to continuous API contract testing
Known slow pagesAgent prioritises load testing here
Accessibility standardDefault is WCAG 2.1 AA; tell agent if you need Section 508 or AAA

4. E2E testing

The agent writes and runs E2E test scripts using a headless browser. Each script follows a real user journey — no mocking, no stubs. The test interacts with your actual UI, clicks real buttons, fills real forms, and verifies the outcome.

How the agent writes E2E tests

Give the agent the flow in plain English and it generates the test:

"Write an E2E test for the checkout flow: user adds an item to cart, goes to checkout, enters card 4242 4242 4242 4242, exp 12/30, CVV 123, and completes purchase. Assert that the order confirmation page shows the order ID."

E2E test results

StatusMeaning
PASSAll assertions passed, flow completed without errors
FAILAt least one assertion failed — bug report created automatically
FLAKYTest passed and failed on the same code — intermittent issue flagged
TIMEOUTPage or element took too long — performance issue flagged
ERRORTest itself errored (bad locator, auth failed) — agent self-heals or alerts you

5. Load testing

The load test service simulates concurrent users hitting your application and measures throughput, response time percentiles, and error rates. Results are compared to the previous week's baseline so you know if performance is improving or degrading.

How to run a load test

"Run a load test on the /api/v1/projects endpoint. Simulate 200 concurrent users over 5 minutes. Target is p95 latency ≤ 500ms and error rate ≤ 1%. Alert me if either threshold is exceeded."

Load test metrics explained

MetricWhat it meansTarget
ThroughputRequests per second your server handledDepends on your expected traffic
p50 latencyMedian response time — half of requests were fasterShould match normal production latency
p95 latency95th percentile — slowest 5% of requests≤ 2× your normal p50
p99 latency99th percentile — slowest 1%No more than 5× your p50
Error ratePercentage of requests that returned 5xx or timed out< 0.1% for critical endpoints
Saturation pointNumber of concurrent users where error rate starts climbingKnow this before traffic spikes in production
Never run load tests on production without warning. Always run on staging first. If you need a production load test, tell the agent: "Run a gentle 10-user ramp on production to measure real latency — stop immediately if error rate exceeds 0.5%."

6. Accessibility testing

The agent crawls every public page of your site and checks for WCAG 2.1 AA compliance. Violations are categorised by impact: critical (blocks screen reader users), serious (significant barrier), moderate, and minor.

Common accessibility issues the agent catches

IssueWCAG criterionImpact
Missing image alt text1.1.1 Non-text ContentCritical — screen readers read filename instead
Insufficient color contrast1.4.3 Contrast (Minimum)Serious — text invisible for low-vision users
Missing form labels1.3.1 Info and RelationshipsCritical — form fields unusable with screen reader
Non-keyboard-navigable modals2.1.1 KeyboardCritical — keyboard-only users trapped
Missing ARIA landmarks1.3.6 Identify PurposeModerate — navigation harder for screen reader users
Focus not visible2.4.7 Focus VisibleSerious — keyboard users cannot see where they are
Auto-playing media1.4.2 Audio ControlSerious — disorienting for screen reader users

How to fix an accessibility issue

Ask the agent for the fix:

"On /signup the submit button has insufficient contrast. What exact colour values should I change and why?"

The agent gives you the specific element, the current and required contrast ratio, and the exact hex value to use to pass the AA threshold.

7. Auth & security testing

The auth check service verifies that your authentication and authorisation flows behave correctly under adversarial conditions. It does not perform penetration testing — that is the Security Agent's domain — but it does verify that your auth layer is wired correctly.

CheckWhat is verified
Token expiryExpired JWT/session cookies are rejected with 401, not silently accepted
CSRF protectionState-changing endpoints reject requests without CSRF token
Role isolationUser A cannot access User B's resources using a valid User A token
Rate limitingLogin endpoint is rate-limited after N failed attempts
Logout completenessAfter logout, the old session token no longer works
Password reset flowReset tokens are single-use and expire within the expected window
OAuth redirect safetyOAuth redirect_uri is validated against allowlist — no open redirect
If the agent finds a privilege escalation issue (User A can access User B's data), it creates a critical priority bug report and emails you immediately — it does not wait for the daily report. Fix these before anything else.

8. Schema change detection

The schema watcher monitors your API responses and compares them to the last known schema. When a field is added, removed, or changes type — even in a nested object — the agent detects it and alerts you.

This is critical for catching breaking changes before they reach consumers. If your API returns { "user_id": 123 } today and { "userId": "abc-123" } tomorrow (field renamed, type changed to string), every client that expected user_id as an integer will break.

How to add an endpoint to schema watching

"Watch the schema for GET /api/v1/users/:id and POST /api/v1/projects. Alert me if any field changes name, type, or disappears — even nested fields."

9. Automatic bug reports

When the agent detects a failure, it immediately files a structured bug report in your session chat and optionally in your ticketing system (Linear, GitHub Issues, or Jira on Pro/Studio).

What a bug report contains

FieldWhat it includes
TitleShort description: "E2E FAIL: Checkout flow — order confirmation not shown"
SeverityCritical / High / Medium / Low based on which flow failed
EnvironmentURL, browser, viewport, timestamp
Steps to reproduceExact steps the test took before the failure
Expected resultWhat the test was asserting
Actual resultWhat actually happened (error message, wrong text, missing element)
ScreenshotCaptured at the moment of failure (Studio tier)
LogsBrowser console errors and network request failures during the test
AI root causeLLM analysis: most likely cause based on the failure pattern

10. Reading test reports

The agent sends a daily test summary at 8 AM in your timezone (configurable).

Daily report sections

SectionWhat it tells you
Overall healthPASS / DEGRADED / FAILING — worst status across all tests
Run summaryTotal tests, passed, failed, flaky, skipped
New failuresTests that passed yesterday but failed today — regressions
RecoveredTests that were failing and now pass again
Flaky testsTests with inconsistent results — intermittent bugs, not regressions
Performance trendWhether p95 latency improved or degraded vs last week
Accessibility deltaNew violations or fixed violations since last week
Recommended actionTop priority: what to investigate or fix today

11. Communicating with your agent

Your Tester Agent session has a dedicated email (tester-a3f9b2c1@agents.boboyka.com) and an in-session chat panel. Both share the same history.

Things you can ask the agent

Request typeExample
Run a specific test now"Run the checkout E2E test right now and report back"
Investigate a failure"Why is the login test failing since yesterday? Is this a code change or infra?"
Add a new test"Write an E2E test for the new team invite flow we shipped today"
Start a load test"Ramp to 500 concurrent users on /api/search and tell me the saturation point"
Accessibility audit"Run a full accessibility audit on the new /dashboard page"
Auth check"Check if our rate limiting on /login is working after the Nginx config change"
Schema check"Compare the current /api/v1/orders response to what it was two weeks ago"

12. Best practices

Test on staging, alert on production differences

Run the full test suite on your staging environment continuously. For production, run a lighter "smoke test" of the 5 most critical flows every 15 minutes. When staging and production diverge unexpectedly, the agent alerts you.

Define test ownership

Tell the agent which engineer owns each feature area: "Authentication tests are owned by alice@mycompany.com. When auth tests fail, add her to the CC on bug reports."

Keep test credentials fresh

Test accounts get stale — passwords expire, email services block them, or the account gets deleted. Tell the agent when test credentials change: "The test account password changed to NewPass456."

Treat flaky tests as real bugs

A test that fails 20% of the time is not a bad test — it's a real intermittent bug. Ask the agent to investigate flaky tests: "The 'invite team member' test is flaky — it fails about 1 in 5 runs. What is causing the inconsistency?"

13. Tier capabilities

FeatureStarterProStudio
E2E test runsEvery 30 minEvery 15 minEvery 5 min
Max concurrent tests210Unlimited
Load testing✅ (100 VUs)✅ (2,000 VUs)
Accessibility audit✅ (weekly)✅ (daily)✅ (on every deploy)
Auth checks✅ (daily)✅ (hourly)✅ (real-time)
Schema watcher
Bug report to ticketing system✅ (Linear, GitHub)✅ (all + Jira)
Screenshots on failure
Daily email report
Slack alerts
Agent chat panel

14. Troubleshooting

Tests pass locally but fail in the agent

The agent runs tests in a headless browser in a cloud environment — results can differ from local if your app behaves differently without a GUI, depends on local environment variables, or has timing-sensitive UI interactions. Ask: "The checkout test fails but works locally. What is the error message and where does it fail?"

The agent reports WCAG violations my design team approved

Some WCAG violations are acceptable by design (e.g., a specific contrast ratio exception for decorative elements). Tell the agent to suppress specific rules: "Suppress WCAG 1.4.3 violations for elements with the CSS class .decorative — these are intentional."

Load test is hitting production accidentally

If you notice a load test is targeting production, ask the agent to stop immediately: "Stop the current load test immediately." The agent will terminate all running virtual users within 30 seconds.

Test credentials stopped working

Send the agent fresh credentials via the secure chat panel (not email, to avoid credentials in email history): "Test credentials updated: email test-new@myapp.com, password: [paste in chat]."

← All agent docsHire the Tester Agent →