Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

AI Insights

How to use AI Insights in ContextQA to analyze real user sessions on your site, discover the journeys users actually take, surface console errors, measure test coverage, and turn any journey into a te

Who is this for? QA engineers, SDETs, and QA managers who want to base their test suite on how customers actually use the application, and to find gaps between real user behavior and existing test coverage.

AI Insights analyzes real user sessions captured on a domain you choose, groups them into the distinct journeys users take through your application, and reports what those journeys reveal — console errors encountered along the way, how well your existing tests cover each journey, and which journeys have no test coverage at all. From any discovered journey, you can generate a test case with a single action, so your suite tracks real usage instead of assumptions.

Unlike AI Test Generation, which creates tests from a source you provide (a ticket, a URL, a design), AI Insights works backward from observed behavior: it looks at what users did, then tells you what is worth testing.

ContextQA AI Insights page showing search, filtering, refresh, creation, and the empty-state guidance for a new workspace

Key concepts

Term
What it means

AI Insight

A single analysis run configured against one domain, a date range of session data, and a schedule. Each insight produces a report.

Journey

A distinct path a user took through your application, reconstructed from one or more sessions. Each journey has a priority, a narrative, and any console errors captured during it.

Gap journey

A journey that no existing test case covers. Gap journeys are the primary output — they show where real usage outruns your test suite.

Coverage

The average match between discovered journeys and your existing tests, expressed as a percentage. It reflects how much of real user behavior your suite already exercises.

Console error

A JavaScript or network error captured in the browser console during a session. AI Insights treats these as real, user-visible defects.

Accessing AI Insights

  1. Open your ContextQA workspace.

  2. In the left navigation, go to AI Insights (route: /td/:versionId/ai-insights).

  3. The AI Insights list shows every insight configured for this workspace, with its domain, environment, status, and date range.

The status column reflects where each insight is in its run:

Status
Meaning

In Progress

The insight is analyzing sessions. Results are not ready yet.

Completed

Analysis finished. Open the insight to view its report.

Stopped

The run was stopped before completion.

Failed

The run could not complete. Use the Retry action to run it again.

Prerequisite: AI Insights needs captured session data for the domain you select. The Domain Name dropdown lists only domains that have recorded sessions, along with the number of events available for each. If your domain does not appear, no session data has been captured for it yet.

Creating an AI Insight

ContextQA Create AI Insight dialog showing domain, name, schedule, date, time, and advanced options

  1. From the AI Insights list, click Create.

  2. Select the Domain Name — the site whose sessions you want to analyze. Each option shows the captured event count, for example app.example.com (12,345 events).

  3. Enter a Name — a descriptive label for this insight.

  4. Choose a Scheduler value to control how often the analysis runs:

    • Daily — runs once every day (default).

    • Once — runs a single time.

    • Weekly — runs once every week.

    • Biweekly — runs once every two weeks.

  5. Set the Date and Time for the first (or only) run. The scheduled date and time must be in the future.

  6. To refine the analysis, expand Advanced Options:

    • URL Path — narrow the analysis to a section of the domain, for example /checkout.

    • Date Range — limit analysis to sessions recorded between a start and end date.

    • Additional Context — optional guidance for the AI, for example "focus on booking flows" (up to 2,000 characters).

  7. Click Create.

ContextQA queues the insight and begins processing. You can view the report once the status changes to Completed.

The Date Range in Advanced Options controls which sessions are analyzed. The Date and Time at the top of the form control when the analysis runs.

Reading the report

Open a completed insight to see its report. The report opens on the Journeys tab. A Legacy report view is also available for insights created before the journeys view.

Report header

The header at the top of the report identifies the insight and where it ran:

  • The title shows the environment the insight ran against.

  • URL shows the site and path the analysis covered, for example app.example.com/checkout, as a link that opens the page in a new tab. When you set a URL Path in Advanced Options, it appears here after the domain.

  • Date range shows the session window the run analyzed, for example Jun 28, 2026 – Jul 5, 2026. This matches the Date Range you set in Advanced Options when you created the insight.

  • A status badge on the right shows the run status (for example, In Progress or Completed).

Together these confirm, at a glance, exactly which site, path, and session window the report is based on.

Overview

The Overview panel summarizes the run in four stat cards:

Card
What it shows

Journeys found

The total number of distinct journeys discovered, and how many are new in this run.

Console Errors

The number of console errors captured across all journeys.

Coverage

The average match between discovered journeys and your existing tests.

Tests Crawled

How many journeys have generated tests, out of the total, and how many are awaiting review.

A schedule summary below the cards shows the schedule type, the next run, and the last run. If any sessions failed to process, the panel notes how many and explains why.

Journeys

The Journeys tab uses a two-pane layout. The left pane lists every journey; the right pane shows the details of the journey you select.

Each row in the list shows:

  • A priority badge (P0 for the highest priority, then P1, P2, and lower) indicating how important the journey is to test.

  • A console error count badge when the journey encountered errors.

  • The journey title and the page URL.

Search the list with the search box at the top of the left pane. If a run produces no uncovered journeys, the tab shows the message "No gap journeys yet."

Journey details

Select a journey to open its detail panel. The header shows the priority, title, and one primary action:

  • Open Requirement — opens the requirement linked to this journey, when one exists.

  • Auto Crawl — generates a test for this journey when it has no linked requirement.

The detail panel has three sub-tabs:

  • Insight — explains the journey. It includes a Why this matters callout with the AI's reasoning, a User journey narrative describing the steps the user took, any Matched Test Cases that already cover the journey, the URLs visited in the session, and any tags.

  • Console Errors — lists the console errors captured during the session. Switch between a flat list view and a grouped view that collapses repeated errors into signatures with occurrence counts and timestamps.

  • Replay — plays an embedded session replay of the journey, when a recording is available.

Generating a test case from a journey

When a journey has no test coverage, turn it into a test case directly from the report:

  1. Select the uncovered journey in the Journeys tab.

  2. In the detail header, click Auto Crawl.

  3. ContextQA generates a test case from the journey and adds it to your workspace.

Generated tests appear in the Tests Crawled count on the Overview panel and are marked as awaiting review until you confirm them. Review each generated test the same way you review any AI-generated test before adding it to a suite.

Summary

AI Insights closes the loop between how users behave and what your tests cover:

  1. Configure an insight against a domain, a date range of sessions, and a schedule.

  2. Review the journeys it discovers, their priorities, and their console errors.

  3. Measure how much of that real behavior your existing tests already cover.

  4. Generate test cases for the gap journeys that matter most.

Because you can schedule an insight to run daily, weekly, or biweekly, your test suite keeps pace with how customers actually use your application.

Related pages

  • AI Test Generation — generate test cases from tickets, URLs, designs, and other sources

  • Requirements Coverage Gaps — find requirements that lack test coverage

  • AI Assistant — the in-app AI assistant for navigation and test creation

  • Test Results — understanding execution result pages

PreviousAI Test GenerationNextTutorial: Generate Tests from Requirements

Last updated

Was this helpful?