Quick Start¶
Get up and running with Dezycro in a few steps.
0. Sign in¶
Visit app.dezycro.ai and click Continue with Google. On first sign-in, Dezycro creates your user record and provisions a tenant + a Default Workspace for you. See Authentication for tenant vs workspace, SSO, and PAT details.
1. Create a Workspace (optional)¶
If the Default Workspace works for you, skip this. Otherwise, from the sidebar workspace switcher, click Create Workspace to add another (e.g. one per team).
2. Create a Project (optional)¶
When you first sign up, Dezycro seeds a default My First Project for you — so you can skip this and use that. To organize work differently, create another from the sidebar: a project represents a product or feature area and contains all related features, PRDs, and tests.
3. Connect your Knowledge Base (optional, recommended)¶
Before authoring your first PRD, give the workspace real product knowledge to ground on. In Settings → Knowledge Base, connect Confluence and/or Linear, then click Import to run the import wizard — pick your spaces (or teams/projects), review the AI's document classifications, and start the import. Imported documents become workspace-level grounding that PRD/TRD authoring and chat retrieve from, so drafts start from your product's actual context instead of a blank slate. See the Knowledge Base connectors guide for details, or Document Ingestion to upload files directly.
4. Create a Feature¶
Click New Feature anywhere in the app. A feature is the smallest planned unit of behavior; it auto-creates two documents: PRD and TRD. The chooser offers three ways in:
- Describe it — a sentence or two; Dezycro suggests a name + folder and seeds the PRD with your intent.
- Upload / Import — drop existing markdown/text docs; each file becomes one proposed feature.
- Connectors — import Confluence pages, one feature per page, copied into Dezycro or linked with Confluence as the source of truth. See the Confluence connector guide.
You can then author or refine each document via AI chat, the editor, or /dezycro:author in the Dezycro CLI (guided discovery → drafting → quality gate).
5. Generate Test Cases¶
Open LogicStudio for your feature. Select the documents to generate tests from; Dezycro's AI produces test cases covering happy paths, edge cases, and negative scenarios.
Review the generated tests, toggle individual cases on or off, and finalize when you're satisfied.
6. Run the Verifier¶
Once your service implements the feature, publish your OpenAPI spec (from the feature page or via /dezycro:publish-spec) and run the verifier:
- From the web UI's feature page, or
- Via
/dezycro:verifyin the Dezycro CLI, or - In CI — see the Verifier docs
The verifier executes your journeys against the running service, asserts the responses match the spec + workbook expectations, and uploads results. Once all enforced journeys pass — and the workbook's issue, task, and coverage gates are clear — the feature auto-transitions to VERIFIED.
What next?¶
- Wire the Dezycro CLI into your editor for the day-to-day flow.
- Read about the Workbook — the structured record of what's been decided, built, and verified for each feature.
- Set up auth fixtures so the verifier can authenticate as your test users.