Skip to content

Workflow Framework

Development Framework Challenge

All known AI development frameworks currently assume: single product, single team, small workforce.

Without reinventing the wheel, we need to extend these existing specification-driven frameworks to adapt to multi-product, multi-endpoint, multi-role environments. After referencing AWS AI DLC, the following proposal was generated. Some scenarios have been implemented in several feature development processes documented in the appendices. Here we present the complete picture:

Multi-Level Specification Management

Why Multi-Level Architecture

A single specification document cannot satisfy the needs of different roles. PMs care about business value and scope, designers need user flows and visual standards, engineers need technical details and interface contracts. Putting all information into one document means everyone must filter through irrelevant content to find what they need.

Multi-level architecture allows each role to read only the specification levels relevant to them. High-level specs define "what to build," while specialized specs define "how to build." Each level has clear input sources and output deliverables, forming a traceable specification chain. When requirements change, affected levels can be quickly identified rather than searching through a single massive document.

Level Structure

Each level inherits from and extends its predecessors:

LevelInputsOutput
High-Level SpecDiscussed Business IntentFeature Requirements, Scope, Impact
Design DocumentHigh-Level SpecArchitectural Decisions, Trade-offs, Risks
UX SpecHigh-Level SpecUser Flows, Design Tokens, Wireframes
API SpecHigh-Level Spec + API PrinciplesInterface Contracts, Schema Definitions
Backend SpecHigh-Level + API SpecImplementation Design, Data Models
Frontend SpecHigh-Level + API + UX + Design SystemComponent Architecture, State Management
Test SpecAll AboveTest Cases, Acceptance Criteria

Simplified Spec Levels for Smaller Projects

If your project is relatively simple—such as a backend-only service, frontend-only application, or solo full-stack development—you don't need to adopt all levels. Omit intermediate specs that don't apply to your project:

  • Backend-only API service: Skip UX Spec, Frontend Spec
  • Frontend-only application: Skip Backend Spec, API Spec (if using third-party APIs)
  • Small full-stack project: High-Level Spec maps directly to implementation, skip intermediate specialized specs

The key is to retain levels that are meaningful for your project, not to mechanically apply the full architecture.

Agentic Product Development Flow Architecture

PhaseDescriptionParticipants
Receive IntentReceive requirement intent from business or productPM, Business
Intensive DiscussionComplete all key decision convergence within 2-3 daysAll Stakeholders
Form ProposalProduce a spec-reviewed proposal documentPM, Tech Lead, Design
Produce SpecsGenerate detailed specs via OpenSpecEach Role + AI
Review SpecsEach role reviews specs for correctness and feasibilityEach Role
Implement from SpecsAI agents generate implementation based on specs, humans reviewEngineers + AI

Key: Early Convergence

The core of this workflow is the 2-3 days of intensive upfront discussion. All stakeholders who might influence the spec must complete opinion convergence during this phase to avoid late-stage changes causing rework.

Why No AI in Early Convergence?

According to AI-DLC definitions, AI should theoretically be involved in the early convergence phase. However, after actual experimentation, we found that AI produces over-extended specs when context is not sufficiently clear.

Therefore, at this stage we still recommend using human thinking for specifications. This is also where humans contribute the most wisdom and work most intensively throughout the entire workflow.

During this intensive discussion of intent and proposals, everyone becomes a core designer of the product—everyone is closely connected to it.

The Standard Workflow Pattern

Each functional role follows a consistent cycle:

  1. Receive - Obtain standardized specifications from upstream
  2. Combine - Merge with domain-specific context (Design System, API Principles, Coding Standards)
  3. Delegate - Submit to AI Agent for proposal generation
  4. Review - Evaluate agent output for correctness and quality
  5. Refine - Iterate with agent until acceptable
  6. Archive - Commit to version control as single source of truth

Workflow Topics

This section covers specific workflows for different scenarios in spec-driven development:

TopicDescription
Requirement Seed ContentMinimum necessary information to initiate an OpenSpec change proposal
Bug Fix FlowWorkflows for handling bugs based on whether they indicate spec or implementation problems
API Design FlowAPI-First approach with AI agent integration for API specification
Change ArtifactsManaging supplementary documents that support OpenSpec change proposals

References