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.
What Dezycro does¶
- Authors PRDs and TRDs via AI chat or the guided
/dezycro:authorflow — with a built-in quality gate that blocks broken TRDs from being approved. - Generates journeys (test scenarios grounded in your TRD intents) via LogicStudio.
- 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 Claude Code Plugin — 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.
Core workflow¶
Documents (upload) → Feature (PRD + TRD) → Journeys (LogicStudio)
↓ ↓
Workbook ←————————————————— Verifier runs (local / CI)
(decisions, issues, tasks, coverage)
Surfaces¶
- Web app — app.dezycro.ai — Mission Control, AI chat, LogicStudio, feature pages, settings
- Claude Code plugin —
/dezycro:*slash commands + 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?
- Quick Start — sign in, create a feature, generate tests, run the verifier.
- Authentication & access — tenants, workspaces, PATs, BYOK.
- Claude Code plugin — wire Dezycro into your editor.
Already onboarded?
- The Workbook — the data model behind every feature
- The Verifier — how the per-feature binary works + CI integration
- Companion V2 — the background loop that catches silent regressions
- MCP server — tool reference for programmatic access