Intro
Work
Skills
About
Contact
Mental Health
Misophonia
Counter Live
AI Recruiting
UX Researcher & Product Designer

Gal Shachaf.

Where human behavior
meets intelligent systems.

I translate complex human behaviors into intuitive digital experiences — and build AI agents and automation systems that feel natural to use. My foundation is in HCI and Psychology.

EducationM.A. HCI, Reichman
B.A. Psychology, Ariel
FocusUX Research · AI Systems · Automation
ToolsFigma · Claude API · n8n · Make
StatusOpen to projects

Location

Tel Aviv, Israel

Available

Freelance · Full-time

Languages

Hebrew · English

Specialty

Mental Health UX

Expertise

What I Bring

03
01

UX Research

User interviews, usability testing, journey mapping, insight synthesis. Research that drives real product decisions.

02

Product Design

End-to-end design: wireframes to high-fidelity Figma prototypes. Rooted in psychology and accessibility-first thinking.

03

AI Agent Design

Building agents with Claude API — context engineering, tool design, UX principles for conversational AI.

04

Automation Systems

Complex workflow automation with Make and n8n. Translating manual processes into intelligent, scalable systems.

05

Psychology × HCI

M.A. HCI, B.A. Psychology. Cognition, emotion, and behavior — the human layer every system needs.

06

Mental Health UX

Specialized experience designing for sensitive populations. Mental health apps, clinical interfaces, accessibility-first.

About

A bit about me

04

"Understanding human behavior is the prerequisite for designing good technology — whether that's a mobile app or an AI agent."

I'm a UX Researcher and Product Designer with a strong foundation in Psychology and Human-Computer Interaction. I specialize in translating complex human behaviors into intuitive digital experiences.

Beyond UX, I build — AI agents, automation workflows, recruiting systems. I don't separate the design work from the technical work. The best products come from understanding both.

Before transitioning into UX and AI, I spent 4.5 years as an IT/Communications Officer in the IDF — managing complex technological systems under pressure, where clarity and reliability weren't optional. I also worked for two years with at-risk youth and a year supporting children on the autism spectrum. That time on the ground shaped the way I think about inclusive design, edge cases, and building for people whose needs rarely make it into the default use case.

2023–2024

Reichman University

M.A. Human-Computer Interaction

Interaction Design, Cognitive Psychology

2020–2023

Ariel University

B.A. Psychology & Sociology

Dean's Honors. Graduated with distinction.

2019

Netcraft Academy

UX Design Certificate

LocationTel Aviv, Israel
FocusUX Research · AI Systems
Product Design · Automation
ToolsFigma · Miro · Claude API
n8n · Make · SAP
ResearchInterviews · Usability Testing
Journey Mapping
LanguagesHebrew (Native) · English (Fluent)
AvailableFreelance · Full-time · Consulting

Contact

Let's work together.

05

Got a project?
Let's build.

Whether it's UX research, an AI system, or automating a complex workflow — I'd love to hear about it.

Based in Tel Aviv — available for remote work globally. Response time usually within 24 hours.

Open to UX research contracts, full-time product design roles, AI consulting, and automation projects.

01 / 04
UX Research · Mental Health · 2024

Mental Health App
— Angel Startup

Led user research for a mental health and habit-building app. Leveraged qualitative insights to simplify the onboarding journey, reducing cognitive load and significantly cutting down early drop-off rates.

RoleUX Researcher
CompanyAngel (Startup), Remote
Year2024
MethodsIn-depth Interviews · Usability Testing · Journey Mapping

Problem

The Challenge

Angel had strong retention for active users — but was losing over 60% during onboarding. My role: lead the full research cycle from recruiting through synthesis into actionable design decisions.

Original onboarding — friction points

⚠ Drop-off — too many fields

Process

Research Methodology

10 in-depth interviews conducted by the research team with users aged 20–38. Semi-structured sessions focused on mental models of habit formation, emotional vulnerability, and decision fatigue.

Phase 01

Recruitment

10 participants — churned users, active users, first-timers.

Phase 02

Interviews

40-min semi-structured sessions conducted by the research team. Think-aloud, recorded with consent.

Phase 03

Usability Sessions

8 participants through current onboarding. 3 critical drop-off points identified.

Phase 04

Synthesis

Thematic analysis and affinity mapping were used to synthesize raw data. We focused on identifying psychological barriers, specifically how 'Emotional Vulnerability' and 'Decision Fatigue' directly contributed to the 60% drop-off rate.

Insights

Key Findings

01

Vulnerability Threshold

Personal mental health questions before any trust was built caused abandonment. Timing matters as much as content.

02

Decision Fatigue

14+ choices in the first 3 screens. Users felt overwhelmed — the opposite of what they came for.

03

Value Before Commitment

Users shown concrete app value before setup completion had 3× higher completion rates.

Solution

Redesigned Onboarding

Build trust first, show value before asking, progressively disclose personal questions over the first week.

Redesigned flow — progressive disclosure

Value first
Anxiety
Sleep ✓
Focus
One question
Plan ready
Home ✓

Results

Impact

42%

Onboarding completion rate

60%

Drop-off at question screens

3×

Completion when value shown first

Next

Misophonia Physiological Monitoring Interface

02 / 04
UX Research Lead · Healthcare · 2024

Misophonia
Monitoring Interface

Designed an adaptive physiological monitoring interface to support misophonia treatment. One data model — two completely different interfaces for therapist and patient.

RoleUX Research Lead
ContextGraduate Project, Reichman University
MethodsExpert Interviews · Diary Study · Comparative Analysis

Context

The Problem Space

Misophonia sufferers and their therapists need the same physiological data — but in completely different forms. Clinical tools are inaccessible to patients. Patient-facing tools lack clinical precision. The solution: one system, two views.

Process

Methodology

Phase 01

Expert Interviews

6 sessions with therapists. Mapped clinical workflows and data needs.

Phase 02

Diary Study

8 patients, 2 weeks. Trigger events, emotional context, self-reports.

Phase 03

Comparative Analysis

14 health monitoring dashboards reviewed for data visualization patterns.

Phase 04

Evaluation Protocol

Custom criteria: comprehension, stress response, task success per user type.

Design

Dual-View Interface

Therapist view: raw physiological data with clinical controls. Patient view: the same data in calm visual language — zero medical jargon.

Therapist dashboard

PATIENTS
P. Cohen ●
R. Levi
HR
84 BPM
GSR
↑ HIGH
TEMP
36.8°C
Timeline
trigger

Patient view — calm language

Right now
calm
Right now
tense
Try breathing
Today
Triggers

Results

Impact

2×

User groups from one data model

89%

Patient data comprehension

Anxiety in patient view testing

Next

Counter Live — Real-Time Support Platform

03 / 04
Product Design · Emotional Support · 2024

Counter Live

Real-time emotional support platform for misophonia sufferers. End-to-end product design: stakeholder interviews, competitive analysis, user flows, high-fidelity Figma prototype.

RoleProduct Designer
ContextGraduate Project, Reichman University
OutputProduct Strategy · User Flows · Hi-Fi Figma Prototype

Problem

The Gap

All existing support for misophonia is asynchronous — therapy, forums, guides. When a trigger hits, nothing helps in the moment. Counter Live fills that gap: real-time tools, community connection, coping support on demand.

Insights

What Research Revealed

01

Speed is Everything

10–15 seconds before a trigger escalates. Active support needed in 3 taps from any state.

02

Community > Content

Every competitor led with content. Users said peer connection in the moment felt more grounding.

03

Zero Cognitive Load

When emotionally activated, complex UI fails. One action per screen. Decision overhead close to zero.

Design

3-Tap Emergency Flow

Emergency flow — 3 taps to active support

I'm triggered
Tap 1
What do you need?
Breathe with me
Talk to someone
I need space
Tap 2
Breathe in...
4 sec
Tap 3 ✓
How do you feel?
😤😐🙂
Post-trigger log

Results

Validation

3

Taps to active support

8/8

Task completion in testing

Reported feeling supported

Next

AI-Powered Recruiting & Screening System

04 / 05
AI System Design · Automation · 2024

AI-Powered Recruiting
& Screening System

End-to-end recruiting system with four AI agents in n8n + Claude API. UX design principles applied to workflow automation — seamless for recruiters and candidates alike.

RoleUX Designer + Builder
Stackn8n · Claude API · Make · Airtable
MethodsService Design · Workflow Mapping · Prompt Engineering

Architecture

Four Agents, One Pipeline

Service design first — the full candidate journey was mapped before writing a single prompt. Then four AI agents were built to handle distinct pipeline stages.

Agent 01

CV Screener

Scores CVs against criteria. Outputs structured evaluation with plain-language reasoning.

Agent 02

Scheduler

Coordinates availability, sends personalized invites, handles rescheduling via Google Calendar.

Agent 03

Communicator

Status updates in a warm, human tone — customized per candidate from application data.

Agent 04

Monitor

Tracks pipeline in Airtable, flags stale stages, surfaces daily recruiter digest with action items.

UX Design

Designing AI Transparency

Every AI score includes reasoning. Every recommendation has an override. The human is always the final decision-maker.

Recruiter dashboard

3 new ●
PIPELINE
New (12)
Screening (6)
Interview (4)
Sarah K. — Senior UX Designer
2h ago · LinkedIn
AI: 87%
"Strong match — healthcare UX. Gap: no B2B SaaS."
Override
Ran M. — Product Designer
4h ago · Website
AI: 62%
"Partial — limited research exp."

Principles

UX Applied to AI

01

Reasoning Transparency

Every score includes a plain-language explanation. Users understand why — critical for hiring decisions.

02

Override Always Visible

The system is a tool, not an authority. Recruiter judgment is always the final layer.

03

Candidate Experience

Automated messages feel personal. Excellent response times — without candidates knowing an AI was involved.

Results

Impact

80%

Time on CV screening

4

AI agents in parallel

Candidate response rate

Next

Gemini Candidate Screening Pipeline

05 / 05
AI System Design · Automation · 2024

AI-Powered Recruiting
& Screening System

Three-node Make automation that turns a Fillout form submission into a Gemini AI-scored evaluation — structured report delivered to the recruiter's inbox in under 60 seconds.

RoleUX Designer + Builder
StackMake · Google Gemini AI · Fillout Forms · Gmail
MethodsService Design · Prompt Engineering · Form UX

Architecture

Three Nodes, One Pipeline

A lean, fully automated flow. No manual steps between submission and evaluation — the recruiter receives a structured report the moment the candidate clicks submit.

Make automation — live pipeline

Fillout Forms
Watch New Responses
Google Gemini AI
Generate a response
M
Gmail
Send an email
Node 01

Fillout Forms

5-step Hebrew candidate form — collects name, phone, email, CV upload, and simulation answers.

Node 02

Google Gemini AI

Receives form payload, evaluates each simulation answer, scores 0–100, generates plain-language reasoning.

Node 03

Gmail

Sends structured evaluation report to recruiter — score, brief, and final recommendation included.

Form Design

Candidate-Facing Interface

A 5-step Fillout form designed for clarity and low friction. Hebrew RTL layout, clean step-by-step flow — candidates know exactly where they are and what's left.

Fillout form — step 1 of 5 (candidate view)

שם מלא *
טלפון *
🇺🇸
כתובת מייל *
קורות חיים *
📁
גרור ושחרר קובץ או נייוט
הבא

Output

Evaluation Report

Gemini structures its output as a recruiter-ready report: candidate name, numerical score, plain-language explanation, and a clear final recommendation. Zero ambiguity for the hiring manager.

Gmail report — recruiter receives this per submission

דו״ח הערכת מועמד — יומלא
מאי שחף
:שם המועמד
:ניתוח Gemini
100 מתוך 0 :ציון סופי
המועמדת לא הגישה תשובות לאף אחת מחמש הסימולציות. בשל כך, לא ניתן היה להעריך את יכולותיה או את התאמתה לדרישות התפקיד על פי מפתח הניקוד שסופק. כל שאלה קיבלה ציון של 0 נקודות.
:המלצה סופית לא ניתן להעריך את המועמדת ללא תשובות לסימולציות.
הדו״ח הופק אוטומטית על ידי מערכת הסינון של יומלא.

Design Decisions

UX Applied to Automation

01

Minimal Pipeline

Three nodes only. Every additional node is friction — for the builder and for the system. Lean by design.

02

Structured AI Output

Gemini prompt engineered to return consistent report format every time — score, brief, recommendation. No freeform noise.

03

Candidate-First Form

5-step form breaks a complex submission into digestible steps. RTL Hebrew layout, clear field labels, no unnecessary friction.

Results

Impact

3

Node pipeline — fully automated

< 60s

Evaluation delivered after submit

Consistent scoring across all candidates

Back to first

Mental Health App — Angel Startup