Case Study · Fintech × Generative AI · Product Design

AI Content Generation for IDFC FIRST Bank

An internal tool that turns a product brief into on-brand, channel-ready campaign copy, in minutes instead of days.

Role
Lead Product Designer
Scope
Product · UX · Design System
Year
2024
Platform
Internal web tool
Scroll
Context

A bank that needed more marketing copy, and could trust less of it.

Their internal team produced campaign copy across WhatsApp, email, Google and Meta ads, and SMS, by hand, from scattered and outdated reference docs.

They needed far more output as products, cohorts, and channels multiplied. And because it's a bank, every line had to be unmistakably on-brand and approved before it could ship. Speed and trust pulled in opposite directions.

WhatsAppEmailGoogle AdsMeta AdsSMS+ more
What I owned
End-to-end product design, research synthesis, information architecture, interaction design, a Material-3-based design system on IDFC's brand tokens, and the working prototype handed to engineering.

Centered on employee care, the user wasn't a customer, it was a marketer under deadline. The job was to remove decisions and rework, not add features.

The real problem

It was never a copywriting problem.

It would be easy to frame this as "build a copywriting tool." The harder, more interesting problem was that speed, consistency, and control were in tension.

Marketers could move faster with templates, but templates flattened the brand. They could stay on-brand with manual review, but review was the slowest part of the process. Optimise one at the expense of the others and the tool dies the moment it hits real hands.

The brief I set

Get a marketer from a product brief to approved, on-brand, channel-ready copy, with the fewest decisions and the least rework.

That reframe split the work into two halves: control at the input, so output is on-brand by construction, and trust at the output, so a regulated team can actually ship it. The output was never the deliverable, the marketer's confidence in shipping it was.

The strategic bet

Generation is the easy 20%.
The other 80% is everything after the first draft.

Editing, comparing, approving, and keeping track of what shipped, that's the 80% that decides whether a tool like this gets adopted. Most AI tools at the time treated generation as the product and left the rest as an afterthought.

I bet the opposite: control the input so output is on-brand by construction, then design the whole refine-and-approve loop so a bank can trust what comes out. Generation is the entry point, not the destination, and the work splits cleanly into two acts.

Act I, Control at the input
Win consistency before a word is generated.
If the brief is structured and on-brand, the output is on-brand by construction, not something you catch in review.
01

Make the brief the product

Tension

The fastest way to get off-brand copy is a blank prompt box. But marketers shouldn't have to prompt-engineer, and a bank can't risk freeform input quietly producing freeform brand voice.

Designed

A structured brief, product, use-case, tone, theme, cohort, channel, hooks, variant count. Intent is captured as fields, not prose, so generation runs on a schema the bank controls.

Why

This is where consistency and control are actually won, at the input, before a single word exists. On-brand becomes the default state, not a correction.

IDFC FIRST
New Brief · Inputs
Step 1 of 2
ProductSavings Account
Use-caseCross-sell
ToneConversationalExclusive
ThemeFestiveExclusivity
CohortFemale18–25
ChannelWhatsApp
Hooks“All your accounts in one place”
Variants5
Structured brief, on-brand by constructionLive
02

One brief, every channel, natively

Tension

WhatsApp, email, ads, and SMS aren't one medium at different sizes, they have different rules for length, tone, and format. The same copy pasted everywhere reads wrong everywhere.

Designed

The same structured brief generates channel-native variants. Pick the medium and the output reshapes, emoji-led and short for WhatsApp, subject-plus-body for email, a headline and a tight description for ads.

Why

Marketers brief once and get output that's already correct for where it lands. The bank's channel conventions live in the tool, so correctness scales without a style guide in everyone's head.

IDFC FIRST
One brief · Every channel
Same input
WhatsApp Email Google Ads SMS
WhatsApp · conversational · emoji on
🌟 Your IDFC FIRST Savings Account, opened in minutes. Minimal docs, instant activation. 🔗 Start now
One brief → channel-native outputLive
Act II, Trust at the output
Make it shippable inside a bank.
Refine, steer, approve, and track, the loop that turns a generator into a tool a regulated team can actually use.
03

Make every variant editable in place

Tension

Marketers never accept the first AI draft verbatim, but sending them to a separate editor for each tweak breaks flow and quietly discourages iteration.

Designed

Each variant lives in its own tile that doubles as an editable field. Selecting a variant shifts it to a clear selected state; entering edit mode deepens the hue so there's never doubt which tile you're in.

Why

The marketer stays in one surface from generation to final copy. Editing isn't a mode switch, it's the same gesture as reading.

Variant 1
ExclusivityConversational
🌟 Welcome to IDFC Bank's Savings Account Services!

🔹 Quick and Easy Account Opening. Open your account in a few simple steps with minimal documentation and instant activation.

🔸 Join us today, open your IDFC Savings Account and start your journey towards smart banking.

🔗 Open Your Account Now
Regenerating…
Default Selected Editing Favourited Regenerating
Variant tile, state modelLive
04

A filter bar that changes with what you're doing

Tension

Tiles need a lot of possible actions, copy, edit, favourite, feedback, delete, but stamping all of them onto every tile created noise that buried the content itself.

Designed

One dynamic action bar above the variants. Nothing selected → global controls: sort, select-all, generate-more. A variant selected → contextual actions for that selection. One bar, two states, zero clutter on the tiles.

Why

The interface only surfaces what's relevant in the moment. The decision I'm proudest of, it solved a density problem without adding a single new screen.

IDFC FIRST
Text Generation · Variants
English ▾
Select All Filters Tone Theme Generate More
1 selected Copy Feedback Favourite Delete
Variant 1
🌟 Welcome to IDFC Bank's Savings Account Services! Quick and easy account opening, minimal documentation, instant activation. Open your account now.
Variant 2
🌟 Seamless banking, maximum benefits. High-interest rates and zero maintenance fees. Join the IDFC family today.
Variant 3
🔹 One-stop financial management. See all your accounts in one place and bank smarter from day one.
Action bar, context-aware statesLive
05

Let marketers steer the AI without rewriting the prompt

Tension

The first set of variants is rarely the last, but "try again" tells the model nothing, and asking a marketer to re-engineer a prompt is asking them to do the AI's job.

Designed

A structured feedback step. Marketers flag what missed, quality, relevance, consistency, format, add an optional line of context, and regenerate. A vague "make it better" becomes specific, machine-usable direction.

Why

This is the heart of the bet. Generation was never the hard part; steering is. Structured feedback makes the refine loop fast and repeatable, and quietly gives the bank signal on what "on-brand" really means.

IDFC FIRST
Regenerate · Feedback
1 selected
What didn't work for you?
Content Quality Content Relevance Consistency Text Format
Tell us more about what to modify…
Variant 1● Updated
🌟 Welcome to IDFC Bank's Savings Account Services! Quick and easy account opening, minimal documentation, instant activation.
Structured feedback → regenerationLive
06

Build the sign-off into the flow

Tension

In a bank, nothing ships unreviewed. Bolt approval on as a side-channel of emails and spreadsheets and the entire speed gain evaporates.

Designed

A maker–checker flow inside the tool. The marketer shares a variant for approval; an approver reviews it in context and approves or rejects; the decision is logged. Version history sits underneath as the audit trail.

Why

This is the real unlock. Governance is the reason a regulated team can adopt generative AI at all, and designing it into the product, instead of around it, is what kept the tool fast.

IDFC FIRST
Variant 1 · Approval
Marketing Manager
Draft In review Approved
Variant 1Draft
🌟 Welcome to IDFC FIRST Bank's Savings Account. Open in minutes, minimal documentation, instant activation.
Approver · Brand
Maker–checker, nothing ships unreviewedLive
07

Make version history legible, not just available

Tension

Marketers generate, regenerate, and tweak across a session. Without a way to track that, they lose good drafts and can't compare directions.

Designed

Versioned tabs, each showing when it was created and how many variants it holds. Switching is instant, so comparing two directions is a click, not a hunt.

Why

It turns an invisible history into a navigable one. Marketers move backward without fear of losing work, which makes them more willing to explore forward.

Latest6
Version 46
Version 34
Version 28
Version 18
Original4
REGENERATED, LATEST · 6 VARIANTS
Version history, instant comparisonLive
The system

Unmistakably IDFC, and reusable by anyone.

A Material-3 foundation themed entirely in IDFC's brand tokens: the primary red with a tint-and-shade scale for states and surfaces, set in Inter for its tall x-height and screen legibility, which matters in an interface that is, fundamentally, walls of text.

The system went past components. Reusable templates and content guidelines let a team save a winning brief and apply it again, so "on-brand" stopped depending on who was at the keyboard and started compounding.

Primary Red#9B1E26
Secondary#6E0A0F
Background 1#F0DADC
Background 2#F6E5E5
Tint 10
Tint 30
Tint 40
Tint 50
Aa
Inter
ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz 1234567890&@#?!
Tall x-height · built for screens
Outcome

From a demo to a tool a bank could actually ship with.

Validated with the marketing team across multiple sessions. What landed wasn't the generation, it was the loop around it: the structured brief, the in-place refine, and the approval flow were singled out as the difference between a flashy demo and something a regulated team would trust with live campaigns.

TK
Reduction in campaign-copy turnaround time
TK
On-brand variants generated per session
TK
Marketing teams onboarded to the tool

TK = "to come." Swap each for a real figure before you publish, even a directional or qualitative number beats a blank. A single stakeholder quote here does more than a paragraph of description.

What I'd carry forward

The risk isn't the model.

The adoption risk in an AI tool isn't the quality of the model, it's the workflow around it. Designing the brief-to-approval loop mattered far more than the generation screen ever did.

Control is won at the input.

The cheapest place to keep output on-brand is before it exists. A structured brief and reusable templates made "on-brand" the default state, so review caught exceptions, not the norm.

In a bank, governance is the adoption mechanism.

Maker–checker approval and a visible audit trail weren't compliance overhead bolted on at the end, they were the specific reason a regulated team could put generative AI anywhere near a live campaign.

Structured feedback is a data asset.

Because marketers steered with structured reasons rather than free-text prompts, every regeneration left signal behind. Over time that, paired with the analytics view, teaches the bank what "on-brand" actually means, in data.