B2B · FOUNDING PRODUCT WRITER & CONTENT DESIGNER/STRATEGIST · CURRENT
Ingram Micro Xvantage
Ingram Micro Xvantage is a B2B ecommerce platform that gives resellers and IT partners a single place to browse, quote, and purchase technology products and services from Ingram Micro's global catalog. I'm the founding product writer and content designer/strategist.
AI
Problem
AI agents in Xvantage were being built in silos across more than a dozen domains, so no two agents spoke or behaved consistently. It's no wonder trust was the biggest barrier to adoption, both internally and with customers.
Solution
My first big bet in this role was standardizing AI agent personas across Xvantage, defining one consistent personality and voice for all agents to use.
- First, I defined how Ingram Micro's existing voice and tone tenets (always honest, somewhat geeky, and extra empathetic) should flex specifically for AI and conversational experiences.
- From there, I created 2 layers of guidelines: one in the guardrails and one at the evaluation level. I built a system prompt specific enough for AI to understand and follow, yet generic enough to work across every agent and use case, and lightweight enough not to drive up latency. This was the first system prompt the UX team had ever created, and much of the work was educating on why this was the right approach, as it lives outside the normal release cycle, so content standards can be updated instantly across every agent without waiting on a code release or re-deploy.
- I pitched the approach to the AI Council of Excellence, who signed off and gave content design access to sync the prompt as a constitutional layer across every agent, and to formally add it to the release gates in the Agent Development Lifecycle (ADLC).
- As part of the release gate, I built 5 content-based evaluation items, giving teams concrete test prompts and ideal outputs to measure agents against.
Impact
This work made content design a required, non-optional stage in AI agent development at Ingram Micro, and established the single voice and tone standard now governing all 15 agents in production. It also gave us the credibility to start getting UX more involved in the ADLC overall.
Identity and purpose
You are a professional AI agent built for Ingram Micro. Your role is to help users complete their work quickly and confidently.
Voice tenets
- • Always honest
- • Somewhat geeky
- • Extra empathetic
Error handling
Every error state must include at least one clear path forward: try again, rephrase, use an alternative tool, contact support.
Help and Support redesign change management
Problem
We redesigned the entire Xvantage Help and Support program with AI at its core, changing how every customer gets help, across every subscription tier. The new model introduced an AI-powered Help and Support Agent and self-service tools as the foundation for all customers. Pro customers would rely on that AI-first experience as their primary support path, while Pro+ and Elite kept associate chat and phone support layered on top. Customers needed to understand the new program, what support they had, and how to reach it. The bigger risk was perception: if the comms read as a list of what each tier was losing, Pro customers would see the change as a downgrade and higher tiers would miss the value they were paying for.
Solution
I built a tiered change management email system with one shared structure and tier-specific framing. Every customer received the same announcement: Enhanced Help and Support is now available on Xvantage. That consistency positioned the AI redesign as an upgrade for everyone, so no tier was told it was getting a lesser version of the change. From there, I tailored the value story to what each segment actually needed:
- Pro: Framed AI and self-service around speed and control, with answers at their fingertips faster than before.
- Pro+: Positioned support as intentionally designed around what makes the biggest difference for businesses like theirs.
- Elite: Emphasized the full range of support and the partnership behind it.
Each email included a tier-specific benefits table in plain language, clear severity-based response times so customers knew what to expect, and a single entry point to Help and Support so there was one obvious next step.
Impact
Customers get help faster, and every tier knows exactly where to go and what to expect. Centralizing support through AI lets us track issues and support themes more seamlessly while cutting associate hours and costs, and the comms made the shift land as an upgrade instead of a cutback.
Pro
Pro+
Elite
Reseller onboarding communications
Problem
New resellers registering for Xvantage were flooded with system-generated emails that fired at unpredictable points in the process. The volume was high, but the value was low: messages didn't include what resellers actually needed to know, and the important information was buried across too many emails.
Solution
As part of our onboarding redesign, I led an initiative to identify the right communication touchpoints across the onboarding journey so that each email maps to a real milestone and delivers only what resellers need at that moment. For example, registration sets clear expectations and separates legal consent from marketing opt-in. While a welcome email confirms registration by name and company, explains when credentials will arrive, and prompts resellers to set their communication preferences, so they control what they receive going forward.
Impact
Every email a reseller gets now reflects a real, verified step, so they can trust what we send, act on it right away, and start doing business with Ingram Micro. We're already seeing early wins: resellers have started treating our emails as something worth reading instead of something to ignore, and open rates have increased.
Xvantage voice
Problem
Ingram Micro had three established brand voice characteristics: always honest, somewhat geeky, and extra empathetic. The only guidelines for writing in this voice were built for marketing, which serves a different purpose than product experiences and communications. That left a gap in how these characteristics should flex across in-product surfaces and comms.
Solution
Starting with research: I led and worked with our UXR team to design a voice study across the different user personas. Each session showed participants different versions of the same content across real product and comms scenarios. From there, we moved into interviews to dig into how each version made them think and feel. I only kept themes that repeated across participants, so every guideline traces back to what users told us. My goal was for every voice decision to be defendable with data.
- Bringing the voice to life: I turned those findings into guidelines for writing our voice across product experiences and communications. For each characteristic, I defined how it shows up overall and how it flexes for associates and customers. Associates pass what they read on to partners, so every X4A message needs to be complete enough to repeat, simple enough to read mid-task, and specific enough to act on. Customers care more about outcomes, so their copy stays simpler with the same level of transparency. I paired each characteristic with Do this / Not that examples, so anyone writing in the voice can apply it without having to interpret it.
- Building the style guide: This voice became the foundation of our content style guide. It covers design system guidelines for content components with formulas and reusable patterns, how the voice shows up for AI agents, editorial guidelines, accessibility and inclusivity (including writing alt text), and writing English copy that translates well for our global audience.
- Scaling with tooling: I'm currently introducing Figma skills and agents trained on all our guidelines to work across Figma Make and Figma Design to check, suggest, and directly replace content in mocks.
Impact
This is how we solve for quality and consistency at scale across over a dozen domains. To measure it, I'm tracking content debt through bi-annual audits, using my initial CX audit as the baseline, and tracking adoption of our reusable patterns to see how consistently teams are putting the guidelines into practice.
