Source inputs
Product context, workflows, support topics, website truth, policy boundaries, and source evidence maps.
Pre-Onboarding Kit
Prepare Canonica before setup starts.
Give your AI coding agent one prompt. It turns the product sources you actually have - repo, docs, website links, API specs, support exports, owner notes, policies, recordings, or screenshots - into a Canonica-ready upload package.
Agent outputReview ready
1standardized source inputs
2api-payloads/*.jsonl
3production-onboarding/*.csv
4asset-inputs/screenshot plan
What it prepares
Structured source truth before Canonica intake.
The prompt does the preparation work outside Canonica, then leaves the owner with a reviewed package to upload.
Upload skeletons
Manifest and Canonica add-source payloads that match the generated source files.
Support tests
Owner-style questions that prove Canonica can answer routine support and escalate risky topics.
Screenshot rules
Asset slots, demo walkthrough briefs, capture plan, scrub level, and approval gates before public website use.
Owner guide
What to prepare, how to run the prompt, how to review the generated folder, and when to enable live support.
OpenAgent guide
Rules for the AI IDE: source-first inspection, missing-source handling, validation, and confidence language.
OpenFull guide
A human-readable runbook for repo, website-only, docs-only, owner-notes, and early-product paths.
OpenWorkflow
From scattered product material to reviewed intake inputs.
The agent prepares the package. Canonica still reviews drafts before anything becomes live support.
01
Paste prompt
Run the master prompt in a repo, docs workspace, website brief, or owner-notes workspace.
02
Inspect sources
Check website pages, docs, app routes, policies, support flows, and screenshots.
03
Create package
Generate source files, payloads, product surfaces, support tests, and asset rules.
04
Owner review
Remove private data, fix inaccuracies, and approve what can enter Canonica.
05
Upload to Canonica
Use Knowledge Intake to create review drafts from the prepared source set.
06
Enable support
Go live only after answers, surfaces, widget context, and test questions pass.
Source modes
It adapts to the product material you have.
A full repo is useful, but not mandatory. The prompt keeps Canonica inputs structured while marking unavailable sources instead of guessing.
Repo and website
Multi-product repo
Website only
Docs only
Owner notes and screenshots
Mixed source bundle
Safety boundary
The prompt prepares inputs. It does not publish authority.
Pre-onboarding makes the first Canonica intake cleaner, but it only covers sources the agent can actually read. Canonica still requires source review, owner approval, and production checks before answering live users.
No secrets, tokens, cookies, or service accounts.
No payment details, raw logs, or private customer records.
No legal, privacy, refund, or security claims without approved source wording.
No guarantee that every AI IDE can inspect every private repo, login-only app, website, recording, or file.
Unavailable sources must be marked pending instead of treated as covered.
No live support until sources, product surfaces, widget context, and test questions pass.
Start before onboarding
Give Canonica better source truth on day one.
Use the prompt first, review the output, then upload the selected sources into Canonica Knowledge Intake.