Skip to content

Dezycro Documentation

Welcome. Dezycro is an AI-powered specification + verification platform: write PRDs and TRDs, generate journey-based tests, run them with a per-feature verifier binary, and keep the whole workbook honest as you ship.

Reading this as an AI agent?

A machine-readable index of these docs is at /llms.txt, and the entire documentation as a single file at /llms-full.txt. Prefer those over scraping the rendered pages — every doc page also has a clean .md twin (append index.md to any page URL).

What Dezycro does

  • Authors PRDs and TRDs via AI chat or the guided /<prefix>:dz-author flow — grounded in your Knowledge Base, with a built-in quality gate that blocks broken TRDs from being approved.
  • Generates journeys (test scenarios grounded in your TRD intents) via the Validation Center.
  • Builds a per-feature verifier binary from your OpenAPI spec — runs locally or in CI, asserts journey outcomes against your service. See The Verifier.
  • Tracks decisions, issues, assumptions, tasks, and coverage in a structured workbook per feature — the source of truth for what's been decided, built, and proven.
  • Surfaces gaps proactively through the Dezycro CLI — blocks tasks from going DONE without verifier evidence, nudges you to re-publish specs when controllers change, and auto-sweeps the workbook for decisions at wrap-up.
  • Gives every coding agent the same team rules via the Agent Playbook — corrections you give an agent today become rules every agent follows tomorrow — and lets your team ship its own playbooks as workspace skills.

Core workflow

flowchart LR
  Docs["Knowledge Base<br/>uploads · connectors"] --> Feature["Feature<br/>PRD + TRD"]
  Feature --> Journeys["Journeys<br/>Validation Center"]
  Journeys --> Verifier["Verifier runs<br/>local / CI"]
  Feature --> Workbook[("Workbook<br/>decisions · issues · tasks · coverage")]
  Verifier --> Workbook
  Playbook["Agent Playbook<br/>team rules"] -.-> Agent["Coding agent<br/>/acme:dz-*"]
  Agent --> Feature
  Agent --> Verifier

Surfaces

  • Web app — app.dezycro.ai — Home, AI chat, the Validation Center, feature pages, settings
  • Dezycro CLI — /<prefix>:dz-* slash commands in Claude Code and Cursor, team rules on every request, Companion V2 background hooks (install)
  • MCP server — for AI clients (Claude Code, Cursor, custom MCP)
  • Public REST API — https://api.dezycro.ai/api/v1/... for CI / custom integrations

Getting started

New to Dezycro?

  1. Quick Start — sign in, create a feature, generate tests, run the verifier.
  2. Authentication & access — tenants, workspaces, PATs, BYOK.
  3. Dezycro CLI — wire Dezycro into your coding agent.
  4. Agent Playbook — make what your agents learn stick.

Already onboarded?