Parent Case Study · Enterprise UX Umbrella · 2022–2024

Discovery, design systems, applied AI, and operations — designed as one program.

Elanco Knowledge Systems (EKS) was the internal product surface that let Elanco's commercial, veterinary, and operations teams find, ask, and act on company knowledge. The infrastructure underneath it — discovery, design system, AI tooling — wasn't four parallel projects. It was one program with three deliverables that depended on each other.

Enterprise UXDesign systemsApplied AIOperational infrastructurePlatform strategy
Company
Elanco Animal Health
Timeline
Feb 2022 — Aug 2024 (30 mo)
Role
Lead Product Designer
Direct reports
3 designers · matrix to research + content
Partner teams
EKS Eng · Data Platform · Veterinary · Commercial
Body of work
3 connected projects · 12+ shipped surfaces
01 / PremiseWhy a parent case study
Framing

Discovery, design systems, and AI tooling are usually treated as three independent budgets. Here they were one.

EKS started as a discovery effort: who used company knowledge, where it lived, and what got in the way. That work produced a service model that needed a coherent visual + interaction system to land. That system, in turn, became the substrate the AI tooling rendered into. Each piece would have been weaker on its own; the value compounded because they were built together.

In one sentence

Three connected projects — Continuous Discovery, the Elanco Design System, and ElancoGPT — designed and shipped as one operational infrastructure for enterprise knowledge work.

02 / Program shapeHow the three connect

Three projects, one dependency graph.

The diagram below maps the dependency direction. Discovery output fed the design system's information architecture and naming. The design system became the rendering substrate for AI surfaces. AI tooling fed structured queries back into discovery's tracking loop.

EKS program · dependency graphdirected network
Project node Shared substrate Output / signal flow
Fig 1 — Edges encode dependency direction. The shared substrate nodes (tokens, content model, taxonomy) are what made it possible to run the three projects as one program rather than three.
03 / ChildrenThree projects under the umbrella

Three connected projects.

Each child has its own dedicated case study with the depth a single-project review needs. Here they're framed as members of one program.

CHILD · 01 / 2022

Continuous Discovery

Lead Product Designer · Foundational research + service design
Read full case study

The umbrella began with discovery. Who actually used company knowledge? Field interviews across veterinary affairs, commercial sales, regulatory, and customer service surfaced a pattern that had been invisible to the org chart: knowledge work happened in handoffs, not in roles. A regulatory writer's morning question became a vet's afternoon answer became a salesperson's customer email — and the system that should have supported that flow didn't exist as a product, only as a series of inboxes.

The discovery deliverable wasn't a research report. It was a service model — a map of where knowledge originated, where it got transformed, and where it had to land for someone to act on it. That model became the brief for everything that followed.

Preview · service-model fragment
01 · OriginRegulatory writer · primary source
02 · TransformVeterinary affairs · clinical context
03 · LandCommercial · customer-facing
04 · ActCustomer · downstream effect

Fragment of the EKS service model. Bar width = observed knowledge fidelity at each stage. Fidelity loss at "act" was the founding insight.

FACT61% of customer-facing answers traced back to a regulatory or veterinary source, but only 8% of those answers cited the source by reference.
INFERENCEThe bottleneck wasn't access to knowledge. It was structured transformation between roles. Without traceability, every handoff had to be redone from scratch on the next inquiry.
ACTIONBuild a knowledge surface where structure travels with content — citations, provenance, role context — so downstream consumers don't have to reconstruct it.
CHILD · 02 / 2022–2023

Elanco Design System

Lead Product Designer · Brand, layout, tokens, components
Read full case study

The discovery output needed a rendering substrate. Elanco had a brand system but not a product design system — color and type guidelines without tokens, no shared component library, no naming convention that survived a sprint. Engineering teams built their own buttons. Product teams couldn't review specs against a source of truth.

The Elanco Design System (EDS) was the answer to that. Tokens-first, Tailwind-aligned utilities, breakpoint-aware components, all governed by a shared decision log. It shipped as the substrate for EKS surfaces first and then propagated to adjacent product teams — the kind of organic adoption a forced rollout never achieves.

Preview · color token set
blue-500
navy-700
teal-400
sand-300
paper-100

EDS uses a paper-and-ink palette as ground, with the brand blue/navy/teal reserved for product surfaces. Sand and paper act as a quiet foundation under content-heavy enterprise screens.

Before EDS

Three different button libraries across EKS surfaces. Color values hard-coded. Spec reviews had to re-litigate hierarchy every sprint.

After EDS

One token sheet, one component library. Spec reviews focused on flow logic, not visual primitives. New surfaces shipped in 60% the time of pre-EDS comparables.

The EDS launch document was the first time the company had a single document that said "this is what 'good' looks like" for product UI. That document changed adjacent teams' onboarding more than any training session would have.
CHILD · 03 / 2023–2024

ElancoGPT

Lead Product Designer · Enterprise AI, retrieval, internal tooling
Read full case study

With the service model and the design system in place, the AI tooling could be designed as a decision surface, not a chatbot. The discovery insight — structure should travel with content — meant ElancoGPT outputs couldn't be loose paragraphs. They had to be parseable into the same fact / inference / risk / action shape downstream consumers were already trained on.

Retrieval-augmented generation handles the source-grounding. The interesting design problem was the output structure: every response is rendered as four typed blocks, each with a confidence indicator, each separately citable, each capable of being attached to a downstream artifact (a customer email, a regulatory note, a sales-call brief). The AI never returns "an answer." It returns a structured argument.

Preview · structured response shape
FACTGalliprant (grapiprant) is approved for osteoarthritis pain in dogs ≥ 9 months old at 2 mg/kg PO once daily.
INFERFor this customer's clinic mix (mostly senior dogs), the dosing simplicity is the most likely conversion lever vs. competitor NSAIDs.
RISKNot recommended in dogs with severe hepatic impairment. Confirm baseline LFTs before recommending substitution.
ACTIONSend the clinic-specific dosing card + LFT-baseline reminder template attached.

Every ElancoGPT response renders into these four typed blocks. Users can copy any one block independently, cite it, or attach it to downstream artifacts.

Adoption · 6 mo71%Of eligible commercial + vet users · weekly active
Avg. answer time-68%Vs. pre-tool baseline for same query class
Source citation rate100%Every block ships with provenance · by design
04 / CompoundingWhy one program, not three

The three projects were worth more than the sum.

If discovery had shipped alone, it would have been an internal report. If EDS had shipped without the service model, it would have been a token sheet without a domain. If ElancoGPT had shipped without either, it would have been a chatbot with no place to land its output. Treating them as one program is what produced compounding value — and the lead-level part of the work.

Discovery → EDS

The service model's role taxonomy became the EDS information architecture. Components were named after the roles they served — RegulatoryCard, VetBrief, CommercialThread — not after their visual shape.

EDS → ElancoGPT

ElancoGPT renders into EDS components. The four-block response uses the same VerticalSemanticCard pattern as the discovery-side knowledge surface. Users don't have to learn a second visual grammar.

ElancoGPT → Discovery

Structured queries flow back into the discovery-side analytics, surfacing emerging knowledge gaps in near-real-time. The discovery loop continues running, but now with a signal source it didn't have at the start.

05 / OutcomesProgram-level metrics
Connected surfaces12+Shipped under one design system
Time-to-answer-68%For knowledge queries in scope of EKS
Adoption · 18 mo71%Weekly active across eligible org
Adjacent teams6Adopted EDS without mandate
Knowledge gaps surfaced240+Via ElancoGPT analytics · routed to regulatory + vet
Designers grown3Mid → senior on this program
06 / ReflectionWhat this program taught me

What I'd defend.

Designing the three projects as one program. The temptation in big orgs is to scope them as independent budgets and ship them independently. The compounding value only shows up if they share substrate from the start — and that requires a designer with the standing to argue for it across three sponsoring VPs.

What I'd do differently.

Invest in EDS contribution tooling earlier. Once adjacent teams started adopting EDS, the contribution model became a bottleneck. A clearer path from "I have a new component idea" to "it's in the shared library" would have accelerated cross-team adoption by months.

What changed for me.

This is the program where I learned to think in dependency graphs. Lead-level work is mostly about understanding what depends on what and protecting the shared substrate — because once it's poisoned, every project downstream of it pays the tax.

Why it mattered.

EKS isn't a consumer product. It's the infrastructure that lets thousands of veterinary, commercial, and regulatory professionals do their work without re-deriving knowledge that already exists somewhere in the org. Invisible when it works, expensive when it doesn't.

07 / What followedCurrent work · 2024 — present
Current

T-Mobile · IoT Connectivity

The EKS program shaped how I think about infrastructure surfaces. The current work — designing the experience architecture for IoT connectivity at T-Mobile — applies the same dependency-graph logic at a different scale: provisioning, fleet management, and lifecycle across millions of devices. Different domain, same lead-level practice.

Read the IoT case study