Three AIs, One Design System

How I turned scattered AI use into governed product workflows for illustration, copywriting, and prototyping across Branch International's product team.

RoleProduct Designer
ScopeAI workflows, UX writing, prototyping
MarketsIndia, Kenya, Nigeria
Core users5 designers
4 UX researchers
15 product managers
Research inputs1:1s, Slack, reviews, FigJam, testing
ToolingChatGPT, Claude, Figma MCP, JSON rules
Summary

Branch's product team works across India, Kenya, and Nigeria, supporting areas such as onboarding, KYC, loans, repayments, rewards, account management, customer support, risk, and operations.

AI was already entering the team's workflow. In a product-team poll I ran, everyone responded, and the results showed that AI was already being used for copywriting: 65% used ChatGPT, 20% used Claude, and others used Gemini.

The issue was not adoption. The issue was reliability. Generic tools could produce fast outputs, but those outputs often lacked Branch's product reality, market nuance, brand voice, component context, and design-system logic.

Branch did not need AI experiments. It needed governed AI workflows for product work.

Team input50+ people consulted

Input came through 1:1s, Slack DMs, product reviews, presentations, FigJam voting, and direct testing.

Copy audit4,390 components audited

Across 530 screens, with 1,778 copy changes implemented.

PRD evaluationAbout 30%

Directional reduction in evaluation time based on general PM feedback.

The Opportunity

Across Branch, PMs, designers, and researchers were already using ChatGPT, Claude, and Gemini to rewrite copy, explore flows, and create early ideas. But every person brought their own prompt, context, and quality bar.

Generic AI tools did not know which products existed in each market. They did not understand how copy should change between a button, screen title, error message, banner, toast, or form description. They also did not know how Branch's product should sound.

The opportunity was to move from loose personal productivity to governed workflows that made AI more useful, consistent, and safe for real product work.

Research

Research Inputs

I used lightweight research methods because the work was internal and moving quickly. The goal was to understand real AI use, not theoretical interest.

MethodWho was involvedWhat I wanted to learn
1:1 conversationsPMs, researchers, designersHow teams were already using AI and where outputs failed
Slack DMsPMs, researchers, designersSpecific pain points from day-to-day copy and workflow use
Copywriting pollFull product teamWhich AI tools people used for rewriting copy
Product-wide reviewsPMs, designers, researchers, stakeholdersWhether the proposed systems matched real team needs
FigJam votingProduct teamWhich illustration direction felt most aligned with Branch
Direct tool testingPMs, designers, developersWhether the workflows were useful in real work
Copywriting poll result65% ChatGPT · 20% Claude · others Gemini

Adoption was already happening. The problem was that every person was bringing their own prompt, context, and quality bar.

Findings

What I Discovered

The research changed the brief. The team did not need to be convinced to use AI. It needed governance, context, and clearer review points.

FindingWhat it meantDesign response
AI adoption already existedThe team did not need convincing to try AIFocus on governance, not novelty
Outputs lacked product truthAI could reference unavailable products or wrong service statesAdd product and market rules
Market language differedThe same copy could feel natural in one country and wrong in anotherAdd market-specific terminology
Brand voice was inconsistentOutputs sounded polished but not like BranchEncode brand voice rules
Component context was missingCTAs, titles, descriptions, errors, empty states, and toasts needed different treatmentAdd component-level copy rules
Prototypes felt genericClaude could prototype, but not in Branch UX patternsMap prompts to Neem components and Branch screen patterns
Illustration styles were fragmentedScreens used mixed visual languagesAlign the team on one reusable illustration system
Strategy

The Strategic Decision

At first, the obvious answer looked like better prompts. But the deeper issue was governance. People already had access to AI tools. What they did not have was a shared system that understood Branch's products, markets, design language, and quality bar.

I treated each workflow like an internal product: define the user and use case, understand failure points, encode product rules, create reusable workflows, test with real team members, turn repeated feedback into system constraints, and keep humans in control of final approval.

The Three Governed Workflows

Initiative 01 - Illustration GPT

Creating one visual language for Branch product illustrations.

Main problemInconsistent illustration styles
Primary usersDesigners
Main outputAround 40 illustrations across markets
StatusAll ready, 60% live

Problem

The issue was not just speed. It was visual consistency. Branch's existing illustration set had grown across different needs and contributors. Some screens used 3D-style assets, others used line illustrations, and some used softer Notion-like visuals. Individually, some assets worked. Together, they did not feel like one product system.

The first challenge was not generating images. It was helping the team align on what Branch illustration style should become.

What I designed

I created an Illustration GPT that could generate Branch-aligned product illustrations using structured rules for colour balance, material treatment, lighting, perspective, product relevance, reusable composition, output quality, and market adaptability.

The goal was not to create random AI illustrations. The goal was to create a repeatable illustration system that could support product surfaces across India, Kenya, and Nigeria.

Team alignment and iteration

To converge on a style, I ran three public review sessions where I presented multiple illustration directions to the product team. I also ran a FigJam vote so designers, PMs, researchers, and stakeholders could compare options and express preferences.

Repeated feedback became a system rule. Isolated preferences were noted but not over-weighted. This helped move the team from subjective opinions to shared visual principles.

Six Major Versions of Illustration System Refinement

The illustration system evolved through repeated review, testing, and constraint tuning. The main work was finding the right level of strictness: enough to create consistency, but flexible enough to support different product moments.

VersionWhat changedWhy it changed
v1Established the first Branch illustration rules, materials, and manifestCreate a consistent baseline
v2Refined early style rules and material handlingImprove alignment with Branch preferred visual direction
v3Added stronger instructions and more detailed rulesReduce inconsistent outputs across prompts
v4Improved system structure and usage guidanceMake generation more repeatable
v5Expanded rule sophistication and prompt controlImprove quality, consistency, and production readiness
v6Tightened final system prompt, rules, materials, and manifestStabilise output for team use and rollout

In practice, the iterations focused on colour balance, material realism, visual weight, lighting, background treatment, perspective, and how much freedom the GPT should have when interpreting a brief.

Result

All illustration sets are ready. About 60% are live in the app, with the remaining rollout dependent on engineering bandwidth. The system reduced design review back-and-forth because new work started from clearer style rules and stronger shared alignment. This gave designers a shared visual baseline instead of restarting style debates for each new illustration.

Initiative 02 - Copywriting AI

Turning individual prompting into a market-aware copy workflow.

Main problemGeneric AI copy lacked Branch context
Primary usersDesigners, PMs, researchers
Main output530 screens, 4,390 components, 1,778 changes
StatusLive product copy improvements

Problem

People were already using AI to write and rewrite product copy. The issue was that generic AI did not understand Branch deeply enough. It could produce clean English, but it often missed product truth, market nuance, brand voice, or component context.

A suggestion could reference a product that did not exist in a market, use terminology that felt unfamiliar to customers in that country, write a CTA like a paragraph, or ignore casing rules, character limits, and component-specific behaviour.

What I designed

I built a copywriting system using versioned JSON rule files and operating guides across brand voice, market terminology, product rules, component rules, heuristics, lint rules, material maps, and workflow guidance.

The system helped the team write, rewrite, and audit product copy against Branch's product reality.

Seven Iterations of Guardrail Tuning

The Copywriting AI evolved through seven versions. Each version adjusted how strict or flexible the system should be across brand voice, component rules, market language, linting, and product context. The work was less about adding features and more about tuning the rules until the system could produce useful copy without becoming rigid or generic.

VersionWhat changedWhy it changed
v1Created the first rule system across brand, markets, components, heuristics, and material mappingEstablish a baseline for structured copy generation
v2Expanded market and component coverageEarly outputs still missed product and market context
v3Strengthened brand and lint logicImprove consistency in tone, casing, and formatting
v4Refined heuristics and constraintsMake outputs more reliable across ambiguous product moments
v5Rebalanced rules to reduce over-correctionSome guardrails needed to be relaxed so copy could still feel natural
v6Added operating guide and stronger workflow structureMake the system easier to use and repeat across teams
v7Tightened final rule logic across brand, market, lint, and component filesStabilise the system after testing and feedback

Across versions, the work moved from "rewrite this copy" to "rewrite, audit, and validate this copy against Branch's product reality."

Before and After: Turning Generic Copy Into Product-Ready Microcopy

To test the system, I audited real product surfaces and compared existing copy against Branch's market, brand, component, and UX writing rules. The goal was not to make copy sound nicer. It was to make each string clearer, more contextual, and more appropriate for the product moment.

Product areaComponentBeforeAfterWhat improved
OnboardingScreen titleVerify your mobile numberEnter your mobile numberClearer task framing
OnboardingInput labelPhone NumberMobile numberBetter India-market terminology
OnboardingInput labelEmail IDEmail addressMore universal and easier to understand
OTPError messageUnfortunately, the provided code does not match. Please try again.Incorrect OTP. Please try again.Shorter, clearer, less formal
KYCCTAProceedContinueMore natural progression cue
RepaymentSection titleRepayment HistoryPayment historySimpler and easier to scan

Copy AI impact

The copywriting workflow supported 530 reviewed screens, 4,390 audited components, and 1,778 implemented changes across onboarding, KYC, loan, account, repayment, rewards, and support flows.

Result

Copywriting became more reliable through Branch-specific product, market, component, brand, and lint rules. The workflow reduced design-review back-and-forth because first drafts started closer to Branch's product reality. This helped reduce review friction because copy started closer to Branch's product, market, and component standards.

Initiative 03 - Neem DS Prototyper

Helping PMs evaluate PRDs through interactive prototypes.

Main problemGeneric prototypes did not follow Branch UX patterns
Primary usersPMs
Main outputInteractive prototypes for PRD evaluation
ImpactAbout 30% reduction in evaluation time

Problem

PMs could already use Claude to create rough prototypes, but the outputs did not understand Branch's UX patterns. Claude could generate a screen, but it did not know how Branch structured flows, how Neem components were used, what screen patterns were acceptable, or how product ideas typically moved through the app experience.

That made the prototypes useful as rough sketches, but weak as alignment tools. The opportunity was to make prototyping faster without making it generic.

What I designed

I created a prototyping workflow that helped PMs move from PRD or product idea to an interactive prototype using Branch's design-system logic. The workflow connected PRD input, Claude Skill interpretation, Figma MCP context, Neem component mapping, token-compliant React prototypes, stakeholder review, and PRD refinement before high-fidelity design.

Result

The Neem DS Prototyper reduced PRD evaluation time by about 30%, based on general feedback from PMs. The tool was tested directly by PMs, designers, and developers. The biggest shift was not only speed: stakeholders could respond to interactive prototypes earlier, before work moved into high-fidelity design. This made PRD feedback more concrete because stakeholders could react to an interaction, not just a written description.

Feedback

Testing and Feedback Loops

I tested the workflows with the people who would actually use them: designers, PMs, UX researchers, and developers. Feedback came through 1:1 conversations, Slack DMs, product-wide presentations, show-and-tell sessions, FigJam voting, and direct tool testing.

Each tool had a different feedback loop. Illustration GPT focused on visual alignment with designers and the wider product team. Copywriting AI was tested broadly because designers, PMs, and UX researchers all wrote copy. Neem DS Prototyper was tested by PMs, designers, and developers to check whether prototypes were useful for PRD evaluation and stakeholder feedback.

The feedback helped separate novelty from usefulness. If a tool only produced impressive outputs, it was not enough. It had to reduce real workflow friction.

Outcomes

What Changed Across the Product Team

The work helped Branch move from scattered AI experimentation to governed AI-assisted product work.

AreaBeforeAfter
AI usageIndividual use of ChatGPT, Claude, and GeminiShared AI workflows with Branch-specific rules
CopywritingManual rewrites and repeated review cyclesMarket-aware copy generation and audit workflow
IllustrationMixed styles across product surfacesUnified illustration direction with reusable generation rules
PrototypingPRDs reviewed mostly as written documentsInteractive prototypes used for earlier stakeholder feedback
ReviewSubjective feedback and repeated correctionsClearer guardrails, quality checks, and approval points
Team enablementAI value depended on individual prompting skillPMs, designers, and researchers had reusable systems
Recognition
“He is an AI-native builder with a designer's eye and a PM's brain.”
Deovrat DwivediDesign Lead · Branch International

What I Learned

  • AI quality depends on context, not just model capability: The same AI tool can produce weak or useful output depending on the rules, examples, constraints, and product knowledge it receives.
  • Guardrails need tuning: Too few guardrails produced generic outputs. Too many made the system rigid. The work was finding the right balance between consistency and flexibility.
  • Internal AI tools need product thinking: A useful workflow needs clear users, repeated problems, feedback loops, usage patterns, constraints, and success criteria.
  • Human review still matters: The goal was not to remove human judgement. It was to help teams start closer to the right answer, reduce repeated corrections, and spend more time on higher-quality decisions.
Final Framing

The real contribution was not just creating three AI tools. It was designing product-team infrastructure that made AI more useful, more consistent, and more aligned with Branch's product reality.