Overview
Spur AI is a built-in chat assistant available across the entire Spur app. Describe what you want to investigate, organize, or generate in plain language, and Spur AI works through it using your tests, suites, and run data. There are two ways to use it:- Chat widget — a persistent widget available on every page. Dock it to the side or float it as a compact panel. The widget picks up context from the page you’re on, and your chat session follows you between pages.
- Full-page view — click Spur AI in the left sidebar to open the dedicated chat page with quick access to your recent sessions.
What you can do
Summarize recent runs
Ask for a summary of your recent runs to see how your tests have been performing without digging through run history.
Triage and heal failing tests
Work through failures conversationally — Spur AI surfaces screenshots and logs so you can understand what went wrong and fix it.
Generate and organize tests
Generate new tests from the material you provide, or ask Spur AI to help organize your existing tests.
Track coverage and test health
Ask about your test coverage and overall test health to spot gaps and flaky areas.
Sessions and context
Conversations are saved as sessions, so you can pick up where you left off. Recent sessions are one click away from both the widget and the full-page view, and an active session persists as you navigate — the widget carries your conversation from page to page and uses the current page as context for your questions.Attaching files and links
You can give Spur AI extra context by attaching material to your message:- Spreadsheets — upload a CSV or spreadsheet, for example test input data. For an Excel workbook with several sheets, ask Spur AI to read the sheet you need by name or number.
- Documents — upload PDFs such as specs or requirements
- Tickets and work items — reference a Jira, Linear, ClickUp, Azure DevOps, or Asana item to give Spur AI its details
- PRs or commits — share a link to a public PR or commit page for Spur AI to read
- Loom links — share a recording as context
Rich results
Spur AI renders results inline in the conversation — charts, screenshots, log viewers, and test run cards — so you can inspect outcomes without leaving the chat.Tasks and test cases panel
The chat includes a panel with two tabs:- Tasks shows a task list for each request Spur AI works through, with a progress count such as “2 of 5 tasks done”. Finished lists fold into a summary row.
- Test cases lists every test Spur AI created or edited in the session, grouped by suite. Each test shows its last run. Filter the list by Not run, Failed, Warnings, or Passed. Click a test to open it in the editor inside the panel.
Exporting tests
Ask Spur AI to export tests from one or more suites, or from a Test Plan. The export includes each test’s numbered steps by default. Spur AI returns a download card with a Download Excel button. To get a CSV file, open its menu and select Download CSV. You can also ask for specific columns, cell colors, or column widths. To use your own formatting, attach an.xlsx template and ask Spur AI to fill it with your tests.
Each export is limited to 5,000 tests and about 4 MB. A Test Plan export includes the tests selected by that plan.
Queueing messages while Spur AI responds
You don’t have to wait for Spur AI to finish before you send your next message. While Spur AI is responding, a send button appears beside the stop button. Messages you send then are queued and sent one at a time, after the current response finishes. Use this to add follow-ups or steer the next step of the work. Queued messages appear in a tray above the message box. In the tray, you can:- Click the pencil icon to edit a queued message before it sends.
- Click the trash icon to delete a queued message.
PDF reports and Excel workbooks
Ask Spur AI to compile a downloadable PDF with paragraphs, tables, charts, run screenshots, or uploaded images. For example: “Create a PDF of this week’s failed runs with screenshots of the failures.” Click Download PDF on the report card. You can reopen the chat session to download the report again. For a spreadsheet, ask Spur AI to create an Excel workbook and click Download Excel. You can upload an.xlsx template and ask Spur AI to fill it with your data.
Generate tests from source material
Paste a Jira or Linear ticket link and ask Spur AI to draft tests from its requirements. Spur AI can read ticket text and images through your connected integration. You can also provide a publicly shareable Loom link. Tell Spur AI which parts to test, then review its proposed steps and destination before you approve creating the tests.Send Slack messages and emails
Ask Spur AI to share results with your team, for example: “Email Priya a summary of today’s failed runs” or “Post the failing tests to Slack.” Spur AI shows the message and asks for your approval before it sends anything.- Email: Spur AI can email anyone on your Spur team, including you. It looks up teammates by name. It can’t email addresses outside your team. Replies go to you, and the email notes that you sent it from Spur chat.
- Slack: Spur AI posts to the Slack channel picked for chat in the Application. The message notes who sent it.
- Connect Slack for the Application. See Slack Alerts.
- In Spur AI, click the MCP button below the message box. If Slack isn’t connected yet, the Explore tab shows a Slack tile. Click Set up to open the Integrations page.
- On the Connected tab, pick a channel on the Slack row. Everyone on your team who uses Spur AI in this Application posts to the same channel.
Saved skills
Save instructions you use often as a skill. Keep a skill personal or share it with your team, then insert it into a chat from the composer. To manage your skills, click the Skills button below the message box, or type/. Open a skill there to edit it or view its version history. You can also ask Spur AI to save or update one.
Best practices
- Keep each session focused on one topic — scope matters. See Using Spur AI Effectively for how session length affects both answer quality and usage.
- Reference tests by name — the closer your phrasing is to the actual test or suite name, the more accurate the match.
- Name environments explicitly — include the environment (for example, “on staging”) when your request targets a specific one.
- Follow up on failures — after asking what failed, ask how to fix it to get debugging context from logs and screenshots.
- Attach data for context — if your request depends on external material, attach the spreadsheet, document, ticket, or PR rather than describing it.
