Artificial Intelligence · How I Build · Methodology

The Pre-Build Method

Nine stages One document per stage No code until the thinking is done

Every failed build has the same root cause: someone started coding before they finished thinking. This method makes the thinking explicit, sequential, and documented — so the build is execution, not exploration.

HR Srinivas September 2026 Artificial Intelligence Methodology 12 min read
The Thesis

Code is the cheapest part. Clarity is the expensive part.

I build automation systems and intelligent workflows using AI — Google Workspace, Apps Script, Copilot Studio, Claude API. No formal engineering background. What I have is 25 years of domain depth and a method that separates thinking from building so cleanly that by the time I write the first line of code, every decision has already been made.

The method produces nine artefacts. Each one exists because the previous one surfaced a question that needed answering. Skip a stage and the next stage is built on assumptions instead of decisions. The sequence matters.

Every hour spent in pre-build saves five in rework. I know this not from theory but from the builds where I skipped stages and paid for it later — in code that had to be thrown away, in features that didn't fit, in UX that made sense on paper and fell apart the moment someone tried to use it.

"The build should be execution, not exploration. Every decision was made in Stages 1–8. Stage 9 is where you type, not where you think."

Think First, Build Last Code is the cheapest part. Clarity is the expensive part. Every hour spent in pre-build saves five in rework.
One Document Per Stage Each stage produces exactly one artefact. If you can't fit it in one document, the thinking isn't clear enough yet.
Exit Gates, Not Deadlines You don't move forward when time runs out. You move forward when the exit gate is satisfied. Quality over speed.
Rinse and Repeat The method is the same whether you're building a compliance engine, a CRM module, or a customer portal. The domain changes. The process doesn't.
The Nine Stages

Each stage answers one question. If the answer is "not yet" — that's the stage you're in.

01 Genesis What if...
02 Iteration What exactly...
03 Scope What's in, what's out
04 Detail Fill Every detail
05 Requirements Specify everything
06 Prototype Make it visible
07 UX Deep Dive Walk every path
08 Build Doc Build-ready brief
09 Build Code it
Thinking stages (1–5) — Claude Chat Visualisation stages (6–8) — HTML + docs Execution stage (9) — Claude Code
The Stages In Detail

Nine stages. Nine artefacts. One working application.

01
Genesis What's the idea and why does it matter?
Idea note

The spark. The raw idea before anyone tries to make it sensible. Write it in plain language. What's the problem? Who has it? What would "solved" look like from their perspective? Don't research. Don't design. Just articulate. The only job is to capture it honestly — before the inner editor cleans it up, before feasibility enters the picture.

Exit Gate
  • The idea is written down in plain language
  • You can explain it to someone in under two minutes
  • The problem is clear even if the solution isn't
02
Iteration What does this actually look like when fleshed out?
Evolved concept doc

Take the genesis note and have a conversation with it. This is the back-and-forth stage — you and Claude going through rounds of "but what about..." and "how would that work when...". The idea evolves here. Features appear. Constraints emerge. The user becomes real — not abstract. Don't lock anything down yet. Explore every branch before you prune.

Exit Gate
  • The concept is fleshed out enough to debate specifics
  • User types are identified with distinct needs
  • Key features are listed — not detailed, listed
  • Open questions are flagged, not buried
03
Scope & Structure What's in, what's out, and how does it hang together?
Scope document

This is the convergence stage. The iteration gave you breadth — now you define edges. What modules exist? How do they relate? What's Phase 1 vs Phase 2? What gets cut entirely? Think of it as the table of contents for everything that follows. Every module is named. Every data flow identified. The boundary between "ours" and "theirs" is drawn. This is also where you make the hard priority calls — everything can't be Phase 1.

Exit Gate
  • Every module is named and its responsibility is clear
  • The module relationship map exists
  • Phase 1 scope is explicitly defined
  • Out-of-scope items are listed, not just implied
04
Detail Fill What happens inside every module, every flow, every edge case?
Feature specs

You have the skeleton from Stage 3. Now put flesh on the bones. Take each module and describe exactly what happens inside it — every user action, every system response, every conditional path, every error state. This is where "the user can manage policies" becomes a paragraph of precise behaviour. Work module by module. No hand-waving. No "the system handles this."

Exit Gate
  • Every module has a detailed specification
  • Every user flow is documented step-by-step
  • Edge cases and error states are covered
  • Business rules are explicit, not implied
05
Requirements Document Is every requirement captured at granular, build-ready detail?
Requirements spec

Stages 1–4 were exploratory. This stage is definitive. Take everything from the previous stages and compress it into a single, comprehensive requirements document that reads like a contract between the thinker and the builder. The discipline: if something isn't in this document, it doesn't get built. If it's ambiguous in this document, it gets built wrong. This is the single source of truth.

Exit Gate
  • The document is self-contained — no external references needed
  • Every requirement is specific enough to test against
  • A developer reading only this document would know what to build
  • Ambiguities have been resolved, not deferred
06
HTML Prototype Can I see and click through what I'm building?
Interactive prototype

Words lie. Screens don't. Build an interactive HTML/CSS prototype — not a wireframe, not a sketch, but a clickable representation of every screen, every state, every interaction. Build it in Claude as an HTML artifact. Use real labels, real data shapes, real navigation. The goal is to experience the application before investing in building it. This prototype surfaces questions that words never could.

Exit Gate
  • Every screen from the requirements document is prototyped
  • Major user flows are clickable end-to-end
  • Discoveries from the prototype are fed back into the requirements
  • Stakeholders have "walked" the app
07
UX Deep Dive Have I walked every user journey, every screen, every interaction?
UX walkthrough doc

The prototype shows what the application looks like. The UX deep dive documents what it feels like to use. Take each user type. Walk through their entire journey — from first login to daily use to edge-case scenarios. Document what they see, what they do, what the system responds with. Note where the experience is smooth and where it's rough. This is also where accessibility, responsiveness, and performance expectations are documented.

Exit Gate
  • Every user type has a documented journey
  • Interaction patterns are explicit and consistent
  • The prototype has been updated with UX findings
  • No screen exists without a documented purpose and flow
08
Build Document Can a developer — or AI agent — build this without asking questions?
Build playbook

The translation layer — where everything from Stages 1–7 gets compressed into a single technical brief. Technology stack with rationale. Database schema — every table, field, relationship, index. Folder structure. API design. Authentication model. Deployment target. Third-party services. Phased build plan with verification gates. For AI-assisted builds using Claude Code, this document IS the prompt. If the agent has to guess, the document failed.

Exit Gate
  • The document is self-contained — all technical decisions are made
  • Database schema is complete — no TBD fields
  • Build phases are defined with explicit deliverables per phase
  • An AI coding agent given only this document can start building immediately
09
Build Does the running application match the spec?
Working application

If Stages 1–8 were done properly, this stage is mechanical. The build document goes into Claude Code. Each phase is executed in order. Each verification gate is checked before moving to the next. The rule: one phase per session. When something discovered during the build contradicts the spec — stop and go back to the document. Don't patch it in code. Fix the spec, then fix the code. The document stays the source of truth even during the build.

Exit Gate
  • Every phase's verification gate has passed
  • The running application matches the requirements document
  • The prototype and the application are recognisably the same thing
  • No features were added or dropped without a documented decision
The One Rule

If you're making architectural decisions during the build, you skipped a stage.

Every stage has an exit gate. You don't move forward when time runs out. You move forward when the gate is satisfied. If you find yourself in Stage 6 making decisions that should have been made in Stage 3 — stop, go back, and make them there.

The most commonly skipped stages are Stage 3 (Scope) and Stage 7 (UX Deep Dive). These cause the most pain downstream. Stage 3 because everyone wants to skip from idea to building. Stage 7 because it feels like documentation — but it's actually the last chance to discover UX problems before they're coded into the product.

For a new project Start at Stage 1. One document per stage. Stages 1–4 typically take a few sessions. Stages 5–8 take a few more. The entire pre-build takes days, not weeks — and saves weeks, not days.
For a project already started Identify which stage you're actually at based on the exit gates. Write the missing documents retroactively. The thinking still needs to happen — it's just more expensive to do it late.
For a feature within a product The same process at a smaller scale. Genesis is the feature idea. Requirements is the feature spec. The prototype might be a single screen. Scale to scope — but don't skip stages.
For the citizen developer

The engineer without domain experience and the domain expert without engineering — this method serves both. Differently.

A software engineer who has never worked in insurance can build an insurance system from a requirements document. The domain expertise is encoded in Stages 1–5. By the time the build document reaches the engineer — or the AI agent — the domain knowledge has been translated into specifications they can execute without needing to understand the underlying problem.

A citizen developer — someone with 25 years of domain depth and no formal engineering background — can now build systems that previously required that engineer. The Pre-Build Method is what makes that possible. Not because it replaces engineering knowledge, but because it externalises domain knowledge into a form that AI can execute.

The citizen developer's advantage is that Stages 1–5 are trivial — they know the domain, the user, the edge cases, the regulatory constraints, the business rules, intuitively. These stages are hard for the engineer. The citizen developer's challenge is Stages 6–8 — the technical translation. This is where AI does the heavy lifting.

The method works because it separates what each party does best. The domain expert thinks. The AI translates. Neither pretends to do the other's job.

Think first. Document always. Build last.

Nine stages. Nine artefacts. One working application that matches the spec because the spec was worth building from.

The build is the easy part — if the thinking was done properly. Code is the cheapest part of any software project. Clarity is what costs.

Every hour spent in pre-build saves five in rework.
About this method: The Pre-Build Method is a repeatable nine-stage process developed through building automation systems, CRM modules, compliance engines, and workflow tools across insurance, fintech, and enterprise domains using AI — primarily Claude (Anthropic) for thinking stages and Claude Code for the build stage. It is not a theoretical framework — it is what emerged from repeatedly discovering, through painful experience, which stages cannot be skipped. The methodology is published here as a working document. It is intended to be adapted, not followed rigidly — the exit gates matter more than the stage names. This article was researched and written with Claude (Anthropic) as a writing collaborator.