Specnote
Back to docs home
Usage guide
View as Markdown

What You Can Ask Your AI

A one-page reference of everything you can ask your Specnote-connected AI to do, with ready-to-use example phrases. Feed this whole page to your AI and it will understand you even better.

Once Specnote is connected to your AI, everything below can be done with a single sentence. There's no need to memorize tool names — describe what you want in your own words, and your AI picks the right tool.

One tip: click Copy as Markdown at the top right of this page and paste the whole thing to your AI. It will understand what Specnote can do even more precisely.

Managing workspaces

Try sayingWhat happens
"Show me my Specnote workspaces"Lists the workspaces you've made
"Create a workspace called 'My Shop'"Creates a new workspace
"Change this workspace's one-line description"Edits the title and description

Creating and refining tests

All four approaches in Four Ways to Create Tests live here.

Try sayingWhat happens
"Create a test: signing up should send a welcome email"Creates a test from one sentence and fills in steps by walking the real screens
"Create tests from this planning doc"Stores the doc as service knowledge and drafts tests grounded in it
"Update tests based on the files I just changed"Re-measures only the affected scope and refreshes tests
"Look at the code and suggest what tests I need"Proposes test candidates with reasons; only the ones you pick get created
"Rename this test / reorder its steps"Tidies up tests and steps
"Group similar tests into areas"Organizes tests by area

Starting a run group — the PRD approval flow

A new run group (round) starts only on a plan review (PRD) that a person has approved. Ask your AI like this.

Try sayingWhat happens
"Start a verification round for this workspace"Puts together a plan review (PRD) of what to verify and by what rules
"Approve this PRD"Only when you explicitly say so — approves the review for you (the decision is still yours)
"Submit tests from the approved PRD"Submits the tests per the approved review and runs the first verification automatically

Running verifications and reading results

Try sayingWhat happens
"Run this test"Starts a real-browser verification
"Re-verify everything"Re-verifies several tests in place at their existing group, refreshing pass rate
"What was the last verification result?"Reads pass/fail and the round report
"Analyze why it failed"Fetches the fix report (where, why, how) — you can hand it straight into a fix
"Suggest a fix for this failure"Gets fix suggestions grounded in the failure cause

Code connection and sync

Try sayingWhat happens
"Send my current code to Specnote"Sends your code with secrets masked (useful without GitHub, or for un-pushed local changes)
"Which tests does this change affect?"Points out the tests and steps touched by the change

Test environments, accounts & secrets

Everything you'd do on screen in Test Environments & Accounts can be said out loud instead.

Try sayingWhat happens
"Register a test environment at ○○○"Registers the site address to test
"Make Staging the default environment"Switches the default environment
"Add the test account ○○○"Registers the sign-in account (encrypted immediately)
"Verify this test as a member"Sets whether the test signs in (member/visitor)

CI auto-verification

The whole setup in Connect CI Auto-Verification can be delegated.

Try sayingWhat happens
"Wire Specnote auto-verification into this repo"Issues a CI token and creates the workflow file
"How are the CI verifications doing?"Reads recent CI verification status

Service knowledge and docs

Try sayingWhat happens
"Store this policy doc in Specnote"Saves planning/policy docs as the workspace's base knowledge
"Summarize what this service is"Drafts a service description grounded in the code

What your AI can't do (human-only decisions)

Almost everything is one sentence away — but three things are set by a person, on screen, by design:

  • Approving the verification plan (PRD) — confirming "what to verify and by what rules" before a new run group starts. This one you can have your AI click for you if you explicitly say "approve it" — though the decision is still yours.
  • Approving pass criteria — confirming "what counts as success" is human-only.
  • Toggling CI inclusion — a standard that can block a release, so only a person sets it.

The reasoning behind this is covered in How Verification Works. Not connected yet? Start with Connect Your AI (Install MCP).