For Max at Alex AI
A design system built for Alex AI's complexity
I spent some time studying your product and what stood out to me is how many different surfaces and interaction models Alex has to support. Here's what I think a design system built specifically for Alex could look like.
What I see
This is way more than a chatbot
I went through alex.com, read through the Series A coverage, and watched the candidate testimonial videos. A few things kept standing out.
Every channel is its
own design challenge
Phone, video, SMS, WhatsApp. Each channel has completely different interaction patterns, constraints, and user expectations. The recruiter dashboard has to make sense of conversations happening across all of them at once.
Two very different user types
Candidates experience Alex as a conversational AI interviewer. Recruiters experience it as a screening, scoring, and coordination platform. Those are fundamentally different products sharing the same system, and they both need to feel polished.
Trust is the product
Verify, fraud detection, identity validation, explainable signals. When you're making hiring decisions with AI, every piece of the UI needs to communicate confidence and transparency. That's a design systems challenge as much as a product one.
You're scaling into enterprise fast
Fortune 100 companies, Big 4 accounting firms, nationwide restaurant chains. $20M raised. 1M+ candidates interviewed. At that pace, every new feature and integration needs to ship with consistency baked in from the start.
What I'd build
A system designed around what Alex actually needs
Not a generic component library. I'm talking about a system built around the specific patterns your product uses every day, designed to grow with the team and the roadmap.
01
Multi-channel conversation components
Alex operates across phone, video, SMS, and WhatsApp. I'd build a unified component system for conversation UI that adapts across channels: transcript views, real-time status indicators, channel switching, and conversation summaries. Consistent patterns that work regardless of how the candidate is interacting.
02
Candidate evaluation and scoring UI
Resume screens, AI interview scores, fraud signals, qualification markers. I'd create a pattern library for how recruiters consume and act on AI-generated insights: score displays, confidence indicators, comparison views, and shortlist workflows. So every new evaluation feature feels immediately familiar.
03
Trust and verification patterns
Verify is a huge differentiator for Alex. I'd build dedicated patterns for surfacing fraud signals, identity confidence scores, and explainable AI decisions. These need to feel authoritative without being alarmist, and they need to be consistent everywhere trust data appears in the product.
04
Token architecture
Colors, spacing, typography, elevation. I'd set up a token structure in Figma that maps directly to your codebase so design and engineering are always on the same page. No more eyeballing spacing or guessing which color to use.
05
ATS integration patterns
Alex integrates with 33+ ATS platforms, and each one surfaces data differently. I'd build flexible integration UI patterns for sync status, data mapping, and configuration screens that scale as you add new ATS partners without redesigning from scratch each time.
Why now
Post-Series A is when this starts to really matter
Before Series A, speed matters more than consistency. You're finding product-market fit, shipping fast, making decisions on the fly. That's exactly what you did and it clearly worked.
After Series A, things shift. You have Fortune 100 enterprises expecting polish. You're expanding into new channels and integrations. You're onboarding enterprise customers who need the product to feel trustworthy from the first screen. And every new feature is touching components that were built quickly during an earlier phase.
This is the point where a design system stops being a nice-to-have and starts being the thing that determines how fast you can ship without accumulating design debt. I've seen both sides of this play out, and the companies that invest here now are the ones that pull away from competitors over the next year.
Recent work
This is what I do
I build design system infrastructure for scaling B2B products. I work directly with product leaders and designers who need their teams to ship faster without things getting inconsistent. Here's what that looks like.
Whisker Labs (Ting)
Currently building design system infrastructure for their consumer product, working directly with their Director of Product. Complex platform with data visualization dashboards, alerting workflows, real-time grid monitoring, and device management across mobile and web.
Thalamus
Built design system infrastructure for a data-heavy B2B platform, working alongside their product designer. Complex institutional workflows, multi-role dashboards, and a growing product surface that needed consistent patterns across features.
SMB.co
Built their first design system from scratch, giving the team a foundation they could actually build on as the product grew.
"Keara built our first real design system and gave us a foundation we could truly build on. It was exactly what we needed at that stage."
Next step
I'd love to walk you through this
No pitch deck, no pressure. Just a conversation about what Alex AI's design system could look like and whether it makes sense to work together.
Or just message me on LinkedIn. Happy to chat there too.
hello@keara.design
Email Copied