Rethinking documentation: Waterfall → Agile → AI-enhanced workflows

In classic Waterfall (plan-driven): you are more likely to see BRD → PRD/FRD/SRS → design → build → test

In Agile: you are more likely to see vision / roadmap / epics / user stories / acceptance criteria, though some teams still keep a PRD for larger features or releases.

A useful rule:

Minimum set for a small Waterfall project

PhaseMinimum Artifact
PlanningBusiness Case / Charter, Project Plan
RequirementsBRD, SRS/FRD, RTM
DesignHLD, LLD
BuildSource Code, Build/Config Docs
TestingTest Plan, Test Cases, Defect Log, UAT Sign-off
DeploymentDeployment Plan, Release Notes, Rollback Plan
MaintenanceUser Manual, Support Manual, Change Log

Technical docs:

The sequence follows the “Why -> What -> How -> Execute” progression:

Human vs AI

Traditional documentation is optimized for human alignment—building shared understanding over time. AI, on the other hand, requires context optimization.

AI agents act like incredibly fast, highly capable junior developers who have amnesia: they need explicit boundaries, structured inputs, and exact architectural constraints for every task.

New document strategy where AI join

The document strategy you should adopt when driving an AI coding agent:

Shift from Monolithic to Modular

AI struggles with 50-page PDFs. If you feed an entire SDD into an agent, it will lose focus or hallucinate. Your strategy must shift to bite-sized, isolated Markdown files.

Establish a “Global Rules” Document

Before writing any feature code, you need a living document (often a .cursorrules file or a global system prompt) that defines the non-negotiable architectural boundaries. This replaces a lot of the boilerplate found in a traditional SDD.

It should explicitly state:

Use Machine-Readable Technical Designs (TDD/SDD)

AI agents parse structured data much better than prose. Instead of writing paragraphs explaining how a system should work, your technical documentation should use formats the AI natively understands:

The “Prompt-Driven Development” (PDD) Flow

With an AI agent, the document flow looks more like this:

The AI Stack

Steps

  1. Ideation & Architecture: AI as a Sounding Board: Lightweight Architecture Decision Records (ADRs) and Mermaid.js diagrams generated in minutes, rather than massive SDD files.

  2. Context Engineering: The New “Design” Phase: lock down the exact database schema and API contracts first

  3. Implementation: Prompt-Driven Development

  1. Testing & QA: Automated Edge-Case Discovery

The human acts as the auditor, ensuring the right business logic is being tested, rather than just chasing code coverage percentages

  1. The Engineering Management Perspective