INVISIBLE SCAFFOLDING

Case Study  ·  HR Tech  ·  NLP  ·  USPTO Patent  ·  Acquired 2026

The best scaffolding
is the kind you
never see.

Hireguide was building AI-assisted structured interviewing — a system that makes conversations more consistent, more objective, and 100x more useful. I came on board to tighten the overall user journey and help shape the product experience. I was on the team during the patent filing. HireVue acquired the technology in March 2026.

My Role

Product Designer — UX refinement & user journey · Patent period

Timeline

Oct 2021 – Jul 2022 · ~10 months

Patent

US12106056B2 · NLP of structured interactions · Filed May 2022

Outcome

Technology acquired by HireVue · March 2026

Acquisition · March 3, 2026

The technology I contributed to and was on the team for when the patent was filed was acquired by HireVue — the global leader in skills-based hiring, serving 60%+ of the Fortune 100 across 180M+ assessments worldwide.

Patent US12106056B2
Acquired March 2026
HireVue · 1,150+ enterprise clients

The Problem

Traditional interviews
are a cognitive failure
by design.

An interviewer is simultaneously expected to maintain eye contact and rapport, transcribe legally compliant notes, ask consistent unbiased questions, and evaluate complex behavioral cues — all in real time. No one can do all four well at once.

The result: gut-feeling decisions based on fuzzy recall. Biased outcomes. And 5 hours of wasted prep time reinvented from scratch per role. Almost all useful signal is trapped in fleeting memory or subjective scribbles — 98% of conversational data is permanently lost.

98%
Of conversational interview data permanently lost in traditional hiring
5hrs
Average time wasted reinventing interview prep per role from scratch
2–5×
More predictive hiring decisions using the Hireguide scorecard system

The Shift

From memory & bias
to data & structure.

The Old UX The Hireguide UX
Preparation5 hours reinventing the wheel per role.Minutes. AI automates structured, skills-based guides from job descriptions.
InteractionDistracted note-taking and inconsistent probing.Active listening. AI co-pilot transcribes and tags cues in real time.
EvaluationGut-feeling assessments based on fuzzy recall.Scalable objectivity through comparable skill scorecards.
Data Yield98% of conversational signal permanently lost.100× more interview data organized and searchable automatically.

System Architecture

The patent describes three discrete engines. The design challenge was making each one feel invisible — so that the user only ever experienced the human moment, never the machine underneath.

Build Engine 230

Before the Interview

Translates unstructured job requirements into a standardized script — Roles → Attributes → Cues → Interview Guide.

Processing Engine 240

During the Interview

Captures live audio, transcribes continuously, classifies dialogue acts, maps utterances to cues via similarity scoring.

Analysis Engine 250

After the Interview

Synthesizes 100% of captured data into objective skill scorecards, heatmaps, and comparable candidate rankings.

Build Engine 230 · Phase 1

01

Proactive Design
before the interview starts.

The Build Module abstracts the complex task of instructional design. A hiring manager selects a role, and the system cross-references 129 million job descriptions to extract the right skills, generate behavioral questions, and define targeted follow-up cues — producing a multi-round interview plan in minutes instead of hours.

The design challenge: making a complex NLP extraction pipeline feel like a simple form. The output had to feel authoritative enough to trust but flexible enough to edit. Structure without rigidity.

↓ Try it — add questions to Safety Standards or Quality Control, then generate the guide.

Fig. 01 Guide Builder — Build Engine 230 · Prototype reconstructed from memory & public patent documentation · Original design files remain with Hireguide

Processing Engine 240 · Phase 2

02

Real-Time Assist
during the live interview.

The Processing Engine captures the live audio stream, transcribes it continuously, and runs each utterance through a three-step pipeline: vectorization via TF-IDF/BERT, dialogue act classification (is this a question or an answer?), and similarity scoring to map the response to the pre-built cue.

The design challenge: surface this intelligence without distracting the interviewer. The human-in-the-loop can give a thumbs up or down in real time — a lightweight signal that feeds back into the model. The AI handles the mechanical burden; the human focuses entirely on the conversation.

Fig. 02 Real-Time Assistant — Processing Engine 240 · Live interview view
app.hireguide.com / interview / live · Recording
👤
Sarah Chen
Live · 14:23
AI transcribing · [email protected]
Real-Time Assistant
Question 1 of 9 · Safety Standards
Current Question
Describe a time you identified a safety risk before it became an incident. What did you do?
NLP Pipeline
Raw utterance captured (Transcript 310)
Dialogue act: Answer (candidate)
Matching to cue: Safety Standards
✓ Cue match · 0.84 similarity score
Live Transcript
Q Describe a time you identified a safety risk before it became an incident.
✓ Proactive "...noticed the scaffolding hadn't been inspected after the rain — I shut the site down before the morning shift arrived."
✓ Regulatory "...filed the incident report immediately per OSHA protocol, even though nothing had happened yet."
△ Vague "...the team knew what to do, I just reminded them..."
✓ Outcome "...zero injuries that quarter, and we used it in the next safety training."

Analysis Engine 250 · Phase 3

03

Scalable Objectivity
after the interview ends.

Once the interaction concludes, 100% of the conversational data is available. The Review Module shifts the UX from data collection to data synthesis — providing hiring panels with a structured framework to make decisions based on evidence, not fuzzy memory.

The scorecard heatmap lets multiple team members privately score candidates against the exact same rubric, surface trade-offs, and compare across the same competencies. The result: decisions that are 2–5× more predictive of actual performance.

Critically: the system tells you who performed well — not who to hire. That decision stays with the human. The AI provides evidence; the interviewer provides judgment.

Fig. 03 Scorecard Heatmap — Analysis Engine 250 · Post-interview view
app.hireguide.com / roles / works-delivery-supervisor / candidates
Works Delivery Supervisor — Candidate Scorecard
4 candidates interviewed · Scored against 3 competencies · Private scoring enabled
Candidate Safety Standards Quality Control Leadership Overall Signal
JD
Jonathan Doe
8 yrs exp · Interview: 42 min
88
72
91
84 Strong
SC
Sarah Chen
5 yrs exp · Interview: 38 min
55
94
61
70 Good fit · Review tradeoffs
MR
Marcus Reid
12 yrs exp · Interview: 45 min
79
41
77
66 Mixed signals

Scores reflect AI-mapped cue alignment from transcript. Hiring decision remains with your panel. Private scoring active — team scores revealed after all submitted.

The Synthesis

A continuous intelligence loop — each interview makes the next one smarter.

Post-interview data — user ratings, manual adjustments, accepted cues — trains the embedding models. The next Build phase is infinitely smarter for the entire community. The scaffolding gets stronger with every conversation.

📋

Build Engine 230

Build

Proactive Design
Guides & Cues

🎙

Processing Engine 240

Interact

Real-Time Assist
Human-in-the-Loop

📊

Analysis Engine 250

Review

Scalable Objectivity
Scorecards

🧠

Model Retraining

Learn

Feedback trains embeddings
Next build is smarter

What I Learned

01

The best AI UX makes the AI invisible — and that was the design brief.

The NLP pipeline running behind the real-time assistant is genuinely complex — vectorization, dialogue act classification, similarity scoring. None of that should appear in the UI. The design task was translating machine output into human-readable cues that felt like helpful observations, not algorithmic outputs. The moment the system feels like software, you've lost the interviewer's attention.

02

Structure enables authenticity, not the opposite.

The counterintuitive insight: a structured interview guide doesn't constrain the conversation — it liberates the interviewer from the cognitive burden of remembering what to ask next. When you're not hunting for your next question, you can actually listen to the answer. The scaffolding disappears; the human connection gets better.

03

Lightweight signals compound into objective data.

A thumbs up during a live interview feels trivial. But when aggregated across 50 interviews, those micro-signals become training data that makes the cue-matching model measurably better. Designing the feedback moment to be nearly effortless — one tap, no context switching — was the key to getting enough signal volume to be useful.

04

Objectivity is a design constraint, not just a feature.

The scorecard's most important design decision was keeping scores private until all panelists submitted. This prevented anchoring bias — where the first person's score pulls everyone else's. It required careful UX sequencing and clear communication of the system state. The technology was straightforward; designing trust in the process was the hard part.

Want this kind of thinking on your product?

Let's build something
worth patenting.

Get in touch →