← All case studies
Case study · 008 · Media · Voice UX

KRO-NCRV

Chef-kok BinnensteBuiten

Led the user research that built the Netherlands' first voice-controlled cooking assistant on Google Assistant — bringing BinnensteBuiten's chefs into the kitchen, hands-free, and earning two golden awards.

Gouden Spinaward 2019 · AI & Voice
Gouden Dutch Interactive Award 2019 · New Interfaces
Client
KRO-NCRV
Project
Chef-kok BinnensteBuiten
Engagement
Dec '17 – Sep '18 · Embedded
Services
Conversational UX · Voice Research
Role
Lead UX Researcher
I · The challenge

Voice UX in 2017 had no playbook. Voice UX in the kitchen had even less.

KRO-NCRV wanted to bring the chefs of BinnensteBuiten — a beloved Dutch public-broadcaster show about sustainable cooking — into the kitchen with viewers. Not on a screen. In their own voice. Hands-free, on Google Assistant, while users actually cooked the recipes.

The brief was bold: someone with flour on their hands, a pan on the stove, and a glass of wine within reach should be able to follow a chef-led recipe from start to finish without ever touching a device. The problem: voice UX was a frontier discipline at the time. Almost nobody had shipped a non-trivial conversational interface in Dutch. The kitchen made it harder — recipes are non-linear, full of "wait, what was step three again?", and users multitask in ways no UX lab can simulate. There was no playbook to copy. The research had to invent it.

"If we get the words wrong, the user gives up on dinner. There's no second screen to fall back on."

— KRO-NCRV product team, kick-off
II · How I worked

Weekly sprint research. Designed for a discipline nobody had standardised yet.

No legacy methodology applied cleanly to voice. So I built a sprint-based research practice from scratch — fast enough to keep up with weekly design iterations, rigorous enough to catch the things that break a conversation.

01
Weekly sprint research
Throughout

A custom weekly research rhythm matched to the design team's sprint cadence — recruit, run, synthesise, deliver in five days. Voice design moves fast, and research had to keep up without compromising rigor.

02
In-context cooking sessions
Phase 2 onwards

Tested in real kitchens — sticky fingers, sizzling pans, kids in the background. Lab tests would never surface the moments where the user's hands were full and the assistant said the wrong thing.

03
Script + tone validation
Iterative

Tested multiple variations of every key moment — confirmations, error recovery, recipe transitions. Worked closely with the BinnensteBuiten chefs so the assistant kept their voice and personality, not generic TTS politeness.

04
Voice command refinement
Iterative

Closed the gap between what users naturally said and what the system could understand. Mapped the actual phrases users tried — "next bit", "what was that again", "skip ahead" — and fed them back into the model.

III · How it unfolded

Ten months. From frontier to first-place.

Months 1–2 · framing

Defining what "good" sounds like

Started by mapping the cooking scenarios voice had to handle — and where the failure modes lived. Without prior playbooks, every framing decision had to be made from first principles.

Months 3–6 · sprints

Weekly sprints across recipe scenarios

Ran weekly sprint research alongside the design team — testing scripts, tone, recipe variations, and voice commands. Every sprint surfaced new failure modes the team would never have caught at the desk.

Months 7–8 · refinement

Tone, error handling, edge cases

Tightened the chefs' voice persona, hardened error recovery, and stress-tested the edge cases — interrupted users, unclear pronunciations, broken kitchen audio. The unsexy work that decided whether the product shipped or shipped well.

Sept 2018 · launch

Chef-kok BinnensteBuiten ships

Launched as the Netherlands' first voice-controlled cooking assistant on Google Assistant — bringing the show's chefs into real kitchens, recipe by recipe, hands-free.

2019 · recognition

Two golden awards

Gouden Spinaward 2019 in Artificial Intelligence & Voice. Gouden Dutch Interactive Award 2019 in New Interfaces. Recognition as a category-defining piece of Dutch voice UX work.

"

Voice UX isn't designed on a screen. It's designed in words, pauses, and tone — and getting them wrong means the user gives up on dinner.

— The pivotal insight
IV · What I built

A research practice for a discipline that didn't exist yet.

Every artefact had to be invented from the ground up — there were no existing voice-UX research playbooks to copy from in 2017.

01
Weekly sprint research framework
A five-day research rhythm tailored for voice design — recruit, run, synthesise, deliver — keeping pace with weekly product iterations.
02
In-context cooking research protocol
A repeatable way to test voice in real kitchens — capturing sticky-fingers, multitasking, attention-fractured behaviour you can't surface in a lab.
03
Validated chef-voice script library
Every key conversational moment tested across multiple tone variations — preserving the BinnensteBuiten chefs' voice instead of defaulting to generic TTS politeness.
04
Voice command refinement playbook
A documented gap-closing process between what users naturally said and what the system understood — so error recovery felt human, not robotic.
05
The shipped Google Assistant action
Chef-kok BinnensteBuiten — an award-winning hands-free recipe experience on Google Assistant.
V · Results

Ten months. Two golden awards.

2
golden awards (Spinaward + DIA, 2019)
1st
voice cooking assistant on Google Assistant in NL
10m
concept to shipped product
1
voice-UX research methodology built from scratch
Next case study →
DPG Media
Media · Change management
Read case study →
Working on something with no playbook?

I've built research practices for disciplines that didn't exist yet — voice, conversational, hands-free. Tell me what frontier you're on.

Book a discovery call →