Skip to content
Daniel Motza
Daniel Motza

{{ t.hero_kicker }}

{{ w.t }}

{{ t.hero_sub }}

{{ m.v }}
{{ m.l }}

Companies I’ve worked with

IEC
IAI
IntSights
abra
EL AL
SysAid
Rapid7
Clalit
BIGI
Gov.il

{{ t.wk_heading }}

{{ t.wk_note }}
Coming soon

{{ w.title }}

{{ w.year }}
{{ w.tag }}

{{ w.desc }}

{{ w.metric }} {{ w.metricLabel }}

{{ w.cta }}

{{ t.rc_heading }}

{{ r.name }}
{{ r.role }}
{{ r.tag }}
{{ r.quote }}
Daniel in space
Hover to reveal Move your cursor across the photo

{{ t.ab2_heading }}

{{ t.ab2_p1 }}

{{ t.ab2_p2 }}

{{ t.ab2_p3 }}

{{ t.lead_kicker }}

{{ t.lead_intro }}

{{ t.lead_sub }}

{{ lp.t }}
{{ lp.d }}

How I work

{{ t.pr_heading }}

{{ t.pr_sub }}

Stage 01 / 05 Discovery
01 · Discovery
02 · Strategy
03 · Design
04 · Validate
05 · Ship
01/ 05
Stage

Discovery & research

Interviews, data and market context, to find what is worth building before any screens.

Deliverables
User interviews Data & analytics Market context
02/ 05
Stage

Strategy & definition

Turning ambiguity into a strategy: success metrics, priorities and a plan everyone can commit to.

Deliverables
Success metrics Priorities Roadmap
03/ 05
Stage

Design & systems

Flows, interfaces and scalable design systems, including conversational UX and human-AI patterns that feel clear and trustworthy.

Deliverables
Flows UI design Design system
04/ 05
Stage

Prototype & validate

AI-accelerated prototypes, usability tests with real users and WCAG accessibility checks, so we learn before we build.

Deliverables
Hi-fi prototypes User testing Fast iterations
05/ 05
Stage

Ship & iterate

Close work with engineering and AI-native design-to-code workflows to reach production, then measure impact and refine.

Deliverables
Dev handoff QA & polish Measure & refine
01/ 05

Discovery & research

Interviews, data and market context, to find what is worth building before any screens.

Deliverables
User interviews Data & analytics Market context
02/ 05

Strategy & definition

Turning ambiguity into a strategy: success metrics, priorities and a plan everyone can commit to.

Deliverables
Success metrics Priorities Roadmap
03/ 05

Design & systems

Flows, interfaces and scalable design systems, including conversational UX and human-AI patterns that feel clear and trustworthy.

Deliverables
Flows UI design Design system
04/ 05

Prototype & validate

AI-accelerated prototypes, usability tests with real users and WCAG accessibility checks, so we learn before we build.

Deliverables
Hi-fi prototypes User testing Fast iterations
05/ 05

Ship & iterate

Close work with engineering and AI-native design-to-code workflows to reach production, then measure impact and refine.

Deliverables
Dev handoff QA & polish Measure & refine

Tools I use

💻 FigmaFigma ClaudeClaude ChatGPTChatGPT MobbinMobbin MixpanelMixpanel MiroMiro JiraJira MazeMaze AdobeAdobe
{{ t.ct_l_loc }}
{{ t.ct_v_loc }}
LinkedIn
Daniel Motza
Thanks for reading
Want to talk? Email danielmotza@gmail.com
Daniel Motza - {{ t.footer_tag }}
© {{ year }} · {{ t.ct_v_loc }}
Daniel Motza
Work

{{ activeCase.tag }}

{{ activeCase.title }}

{{ activeCase.summary }}

{{ t.cd_l_tldr }}

{{ td.l }}
{{ td.d }}
{{ coverEl }}
{{ t.cd_l_role }}
{{ activeCase.role }}
{{ t.cd_l_timeline }}
{{ activeCase.timeline }}
{{ t.cd_l_team }}
{{ activeCase.team }}
{{ t.cd_l_platform }}
{{ activeCase.platform }}
{{ t.cd_l_overview }}

{{ activeCase.overview }}

{{ activeCase.challengeTitle }}

{{ activeCase.challenge }}

{{ t.cd_l_approach }}

{{ ap.t }}

{{ ap.d }}

How I worked

Redesigned end to end, with the in-house studio

I worked with SysAid's in-house studio, led by Tomer Gilat, alongside the product manager, engineering and our design partners, who joined interviews, live sessions and prototype tests. Together we ran competitor and user research with qualitative and quantitative interviews, then took the queue and ticket page from wireframes to tested prototypes. What came out was a design system and an entirely new end-user UI.

Methodology map. Daniel works alongside SysAid's in-house studio, led by Tomer Gilat, with the product manager, design partners, engineering and senior stakeholders. The work moves in five steps, from research to a design system, a new end-user UI and Template Designer.
Methodology map · Reconstructed for this case study Each step fed the next, from first research to the shipped system.
Read as text
  • Context: Classic, the legacy platform in use since 2002 → Spaces.
  • Who: me, Senior UI/UX Designer · SysAid's in-house studio, led by Tomer Gilat · product manager · design partners · engineering and senior stakeholders.
  • 1 Research: competitor and user research, design partners, qualitative and quantitative interviews. 18 interviews · 240+ surveys · 6 competitors.
  • 2 Synthesis: 3 recurring themes · 4 segments · 4 principles.
  • 3 Wireframes: the queue as a clear table with fast filtering · the ticket page as a labeled, sectioned layout.
  • 4 Prototypes and testing: 3 usability rounds on service-record resolution, related items and action-item workflows.
  • 5 Delivered: a design system · an entirely new end-user UI · Template Designer.

Sources: the case text and Daniel's notes. No invented data.

Research & discovery

{{ activeCase.researchNote }}

{{ r.v }}
{{ r.l }}
Synthesis board from the joint research: 18 interviews, 240+ survey responses, 6 competitors and 3 testing rounds, grouped by source. Three themes recur: the queue was overwhelming, bulk work was slow and non-technical teams could not shape their own templates. Synthesis board from the joint research: 18 interviews, 240+ survey responses, 6 competitors and 3 testing rounds, grouped by source. Three themes recur: the queue was overwhelming, bulk work was slow and non-technical teams could not shape their own templates.
Synthesis board · Reconstructed for this case study From the joint research with SysAid's in-house studio, grouped by source so each finding shows where it came from. Findings paraphrased; no verbatim quotes exist.
Read as text
  • Methods: 18 user interviews (admins and agents) · 240+ survey responses · 6 competitors benchmarked · 3 usability testing rounds.
  • Who: SysAid's in-house studio (led by Tomer Gilat), the PM and design partners.
  • Design partners (interviews, live sessions, prototype tests). Valued: the reliability of Classic. Pain: complex UI · limited customization · clunky asset management.
  • Customer surveys. Valued: customization · API integration · ticket tracking. Pain: customization complexity · unresolved tickets.
  • Competitors (ServiceNow, Jira and 4 more). Valued: strong customization and dashboards. Pain: overwhelming UI · steep learning curves, industry-wide.
  • Segments: small existing, need simple workflows, struggle with the outdated UI and migration · large existing, need advanced customization, face workflow strain · small new, want intuitive design and quick onboarding · large new, demand scalability, wary of steep learning curves.
  • Recurring themes: the queue was overwhelming · bulk work was slow · non-technical teams could not shape their own templates.

Sources: the case text and Daniel's notes. No invented data.

{{ rp.t }}

{{ rp.d }}

Who we designed for
{{ pe.t }}

{{ pe.d }}

The principles it led us to
{{ pr2.t }}

{{ pr2.d }}

Strategy

Every fix traced to a problem

The research pointed at four clear problems with the legacy queue. I designed a deliberate answer to each, and each answer shipped as a feature.

Decision map with four rows. Each problem in the legacy queue leads to a design move, the feature that shipped and, where known, the shift it made, such as editing a ticket field going from 6 clicks to 1. Decision map with four rows. Each problem in the legacy queue leads to a design move, the feature that shipped and, where known, the shift it made, such as editing a ticket field going from 6 clicks to 1.
Decision map · Reconstructed for this case study Getting buy-in meant tying every decision back to a real problem and a measurable result.
Read as text
  • Row 1. Theme: the queue was overwhelming. Problem: an outdated interface, dense tables and text that made it hard to spot what was urgent. Move: a modern queue with chips, avatars and dynamic cues. Shipped: graphic chips. Shift: not stated.
  • Row 2. Theme: bulk work was slow. Problem: losing to competitors with a dated look. Move: time-saving power, with inline editing and bulk actions. Shipped: inline edit, every cell edits in a single click. Shift: editing a ticket field, 6 clicks → 1 click.
  • Row 3. Problem: a steep learning curve. Move: personal queue views to add, reorder and save columns. Shipped: custom columns and queue views. Shift: queue columns, fixed → configurable.
  • Row 4. Theme: non-technical teams could not shape their own templates. Problem: dependence on support, where small changes needed pro services. Move: self-sufficiency. Shipped: Template Designer, no-code. Shift: building a ticket template, pro services → self-serve.
  • Foundation, across all rows: one governed design system. Shift: UI components, ad-hoc → 50+ governed.

Sources: the case text and Daniel's notes. No invented data.

The redesign

The main ticket table

The heart of SysAid. I rebuilt it around scannability and speed - clearer hierarchy, status and priority cues, bulk actions and multi-select - so agents move through queues with far less friction.

Wireframes & prototypes

{{ activeCase.wireNote }}

Before
Main ticket table before: alert dots, SR type, Priority, Category, Title, Status, Request user and Admin group as plain text in a dense grid
After
Main ticket table after: Title, Priority chips, Urgency, Due date bars, Status chips and assignee avatars
Main ticket table · before and afterDense plain text became visual cues, so agents can see what needs attention first.
  1. Priority: plain text became colored chips that read at a glance.
  2. Due date: time left shows as a bar, so urgent tickets stand out.
  3. Status: labeled chips replace plain text, so a ticket's state is quick to scan.
What makes the queue fast
{{ qf.t }}

{{ qf.d }}

Ticket page & insight panel

I rebuilt the single ticket into a focused two-column view with a contextual insight panel (open SRs, relevant KB, time-to-repair) and a clear activity journey - plus complex reusable components like the multi-select assignee.

BeforeSysAid ticket page before
AfterSysAid ticket page after
Ticket page · before and afterA focused two-column view, with an insight panel for open SRs, relevant KB and time-to-repair.
The right-side tabs I designed
{{ tt.t }}

{{ tt.d }}

Flagship feature

Template Designer - a no-code builder

A huge feature I owned end to end: a low-code / no-code builder that lets non-technical people compose ticket templates for their organization - sections, fields, workflows and per-field properties - by dragging from a field library, with a live preview. It put template creation in the hands of the teams who actually run the processes.

SysAid Template Designer
Template DesignerTeams drag sections and fields from a library and check them in a live preview, with no code.
Foundation

The design system

I created and maintained the design system from scratch - color, typography, an icon set and complex components with every state documented - so the whole platform stays consistent and ships faster.

SysAid design system
Component sheetEvery state documented, so the platform stays consistent and ships faster.
Outcomes

What changed for admins

{{ activeCase.metricsNote }}

{{ mt.metric }}
{{ mt.before }} {{ mt.after }}

{{ mt.d }}

{{ o.v }}
{{ o.l }}
Where they started

{{ activeCase.challengeTitle }}

{{ activeCase.challenge }}

The system they had

This is the interface operators actually worked in before we arrived - a dense grid of near-identical panels, color-coded state, and repeated controls with no hierarchy or search. Everything competed for attention at once. It set the bar the new system had to beat, and it is the reason a flexible, no-code, search-first console mattered so much.

The legacy systemIn daily use for years before the redesign - blurred for classification. Dozens of identical panels, color-coded state, repeated controls, no hierarchy and no search.
Research and collaboration

Research without access to users

Classified meant no interviews, no analytics, no recordings and no way to benchmark competitors. So I worked through the people closest to the system. The Product Owner was effectively its super-user, who built and operated the screens and brought insight from the field. With the Product Owner and the development team I ran recurring on-site sessions at the client's offices, gathered as much internal client data as I could and mapped the commands operators fire most, the failures they chase daily and how critical uptime is to the whole operation. Then I iterated, by trial and error, until one design served every user level. Every decision traced back to that picture.

Research-channel map. Inside a classified program with no user access, analytics or remote sessions, Daniel worked through the Product Owner, the system's super-user, and the development team. Operators were reached only through the Product Owner, and the work moved in a loop of trial and error. Research-channel map. Inside a classified program with no user access, analytics or remote sessions, Daniel worked through the Product Owner, the system's super-user, and the development team. Operators were reached only through the Product Owner, and the work moved in a loop of trial and error.
Research-channel map · Reconstructed for this case study The people closest to the system stood in for the users I could not reach. Labels abstracted for classification.
Read as text
  • The frame, a classified program: no access to end users · no analytics · no remote sessions · competitor research blocked, because systems like this are classified.
  • Outside the frame: operators, reached through the Product Owner.
  • People inside: the Product Owner, the system's super-user, who built and operated the screens and brought insight from the field · the development team.
  • Methods inside: on-site working sessions at the client's offices · internal client data, as much as could be gathered · a legacy system audit · a frequent-actions inventory of commands, checks and calibrations, ranked by frequency and criticality.
  • The loop: iterative trial and error across different user levels · a Concept Design Review with the client and development · every iteration reviewed against real usage.
  • Note: all manual, a pre-AI workflow.

Sources: the case text and Daniel's notes. No invented data.

Prioritization

From daily work to what shipped

With no analytics to lean on, prioritization came straight from the ranked frequent-actions inventory. Commands, checks and calibrations, ranked by frequency and criticality, became requirements, principles and a prioritized plan. Below, each daily need sits next to the answer that shipped and the shift it made.

Requirements map. Five daily needs from the frequent-actions inventory, each traced to the answer that shipped and the shift it made, from menu digging to tab and search and from a dev task to drag and drop. Requirements map. Five daily needs from the frequent-actions inventory, each traced to the answer that shipped and the shift it made, from menu digging to tab and search and from a dev task to drag and drop.
Requirements map · Reconstructed for this case study With no analytics, the ranked inventory was the only evidence for what to build first. Labels abstracted for classification.
Read as text
  • Ranked by frequency and criticality → requirements, principles and a prioritized plan.
  • Reaching a screen. Answer: tabs, where every new tab opens on search plus the common pages. Shift: menu digging → tab + search.
  • Firing a frequent command. Answer: quick actions on the common pages. Shift: seconds, not menus.
  • Running checks and calibrations. Answer: macros, step by step, with live progress and failure drill-down. Shift: expert-only → guided macros.
  • Chasing failures. Answer: one real-time console with a live status panel. Shift: scattered → one console.
  • Building a new operator screen. Answer: UI Builder, dragging elements from the ICD, no code. Shift: dev task → drag and drop.
  • Across all five, different user levels: operators with 20+ years kept the dense layout of about 60 elements, and hierarchy and search were added instead.

Sources: the case text and Daniel's notes. No invented data.

Concept Design Review

Two concepts, one validated direction

Before committing to build, I ran a CDR - a Concept Design Review with the client and development - to validate a direction both operationally and technically. I brought two concepts to the table.

Decision matrix comparing two concepts reviewed with the client and development. Concept A, a tabbed workspace, was selected for real-time speed. Concept B, an aircraft hologram, looked striking but was set aside.
Decision matrix · Reconstructed for this case study Reviewed with the client and development before anything was built, so the direction held up operationally and technically.
Read as text
  • Reviewed with the client and development, operationally and technically.
  • Concept A, tabbed workspace, selected. Navigation: browser-like tabs, each a full screen of operational elements. Real-time operation: built for it. Speed and feel: the least time and fewest clicks possible, fast and familiar. Outcome: earned technical and practical validation and became the operator console.
  • Concept B, aircraft hologram, explored. Navigation: a 3D model of the aircraft as the navigation surface. Real-time operation: never gave real comfort for it. Speed and feel: looked striking, but more gimmick than tool. Outcome: set aside.

Sources: the case text and Daniel's notes. No invented data.

The client and development loved the tabbed workspace, and it earned the technical and practical validation to move forward - it became the operator console that follows.

Decision log

Trade-offs I made

Real programs are full of tension between the ideal design, engineering reality and how people actually work. A few calls I owned:

{{ dc.tag }} {{ dc.title }}
The idea

{{ dc.idea }}

The tension

{{ dc.tension }}

The call

{{ dc.call }}

The solution

The operator console

Live telemetry streams into configurable sections - sensors, meters, cameras, toggles and commands - while a status panel surfaces connection state and activity failures the moment they happen. Operators see, decide and act on a single screen, at speed.

IAI real-time monitoring console
Operator consoleTelemetry, commands and failures on one screen, so operators see, decide and act at speed.

Automated macros for maintenance & calibration

Routine check and calibration flows run as macros - step-by-step sequences with live progress, remaining time and a drill-down into every failure with its recommended action. Work that used to demand deep technical knowledge became a guided flow operators move through quickly.

IAI macro runner with failure drill-down
Macro runnerLive progress, time remaining and a drill-down on every failure with its recommended action.

Browser-fast navigation

Screens live in tabs, and every new tab opens on search plus the most common pages with their quick actions attached - so reaching any screen or firing a frequent command takes seconds, not menus.

IAI new tab - search and common pages
New tabSearch plus the common pages and their quick actions, so any screen is seconds away.
Flagship feature

UI Builder - operator screens without code

The interface is fully flexible: an admin composes the screens their operators work on by dragging elements straight from the ICD onto sections, tuning each element's properties in place, and publishing. Low-code and no-code by design - building a screen requires no technical sense, so the interface adapts to the operation instead of the other way around.

IAI UI Builder - composing a screen
UI Builder · composingAn admin drags elements from the ICD onto sections, with no code.
IAI UI Builder - element properties
UI Builder · propertiesEach element's properties are tuned in place, then the screen is published.
Craft & methodology

The system behind the system

{{ activeCase.dsIntro }}

{{ df.t }}

{{ df.d }}

{{ g.t }}{{ g.c }}

Real frames from the IAI design-system and Element Index files in Figma - the reference developers implemented against.

Outcomes

What changed in daily work

{{ activeCase.metricsNote }}

{{ mt.metric }}
{{ mt.before }} {{ mt.after }}

{{ mt.d }}

{{ activeCase.reflection }}

{{ o.v }}
{{ o.l }}
Requirements

Requirements-led, to a strict brand book

This was a short project, led by requirements rather than a research phase. I worked closely with the PM, the development team and the Clalit studio, to a brand book with specific do's and don'ts. Each requirement below has the design response it got.

Requirements map. Six requirements for a workshop portal for members of every health plan, from audience and accessibility to Clalit's brand book, each with its design response, inside a short project run in close collaboration with the client. Requirements map. Six requirements for a workshop portal for members of every health plan, from audience and accessibility to Clalit's brand book, each with its design response, inside a short project run in close collaboration with the client.
Requirements map · Reconstructed for this case study With no research phase, the brief and the brand book set every requirement.
Read as text
  • At the center: a workshop portal for members of every health plan.
  • Audience: every age, every level of digital comfort, diverse abilities. Response: a prominent search field and layered filters up front.
  • Catalog: a wide range, held in person or online, from smoking cessation, alcohol withdrawal and weight management to many more. Response: filters for topic, audience, region, language and format, and the essentials on every card.
  • Accessibility: strict adherence to accessibility principles. Response: high-contrast modes and accessibility testing throughout.
  • Responsive: one experience from mobile to desktop. Response: catalog, filters and registration rebuilt for touch.
  • Brand book: a clear brand book with specific do's and don'ts. Response: a portal style guide aligned to it.
  • Registration: guide people through registration without friction. Response: one clear path to register.
  • Around it: a short project, 3 months from brief to handoff · close collaboration with the PM, the development team and the Clalit studio.

Sources: the case text and Daniel's notes. No invented data.

The experience

From discovery to done

{{ activeCase.flowIntro }}

User flow in five steps, from the workshop catalog to a booked place, with an empty-state branch that leads back to the catalog when no online sessions are available.
User flow · Reconstructed for this case study Mapped as one path because the audience spans every age and level of digital comfort.
Read as text
  • 1 Discovery and catalog: search, filters (topic, audience, region, language, format) and cards with date, time, seats and cost.
  • If no online sessions are available: an empty state keeps the member oriented and offers a way back to step 1.
  • 2 Workshop page: session details, the session list, a booking summary and a single path to register.
  • 3 Sign-in and registration.
  • 4 Summary and confirmation: personal details, consent and one clear action.
  • 5 Success: an on-brand thank-you with Clalit's mascot.
  • The same flow on desktop and mobile.

Sources: the case text and Daniel's notes. No invented data.

{{ g.t }}{{ g.c }}
Craft & consistency

A style guide to keep it whole

{{ activeCase.styleNote }}

Style guide{{ activeCase.styleCap }}
Responsive

Built for every screen

{{ activeCase.mobileIntro }}

{{ mb.t }}
MobileBrowse the catalog, filter by region and open a workshop, all designed for touch and small screens.
{{ t.cd_l_outcomes }}

{{ activeCase.outcomesNote }}

{{ o.v }}
{{ o.l }}
Overview

Product to brand, with a studio I built

Scully lets large companies run AI agents inside their ERP and CRM, under their own rules. I designed every surface people see: the back office operators work in, the brand, the website buyers land on and the films that explain it. This case follows the work mostly in order.

Prefer to watch? The product tour, 3:06.
Jump to the Films chapter
Start

It began as a name and a simple S

In Mar 2026, Scully was a name and a simple S. The idea was clear: AI agents doing real work inside the ERP and CRM a company already runs. Nothing a user, a buyer or a developer could look at existed yet. That was the job.

My studio

I built a design studio of AI agents, and I make every call

These are my tools, not Scully's product. Scully's AI agents, like Clara, show up later, in the back office.

Being the only designer on a product this wide, I couldn't do every job by hand. So I built my own design studio: specialist AI design agents, each with one role, from UX and UI to motion, sound, copy, QA and development. I direct it. Every task starts as a brief and a plan, and nothing moves until I approve the plan. Studio agents do the work, the QA agent checks it and I sign off the result or send it back. That's how one designer ran research, product, brand and film side by side.

Director

Daniel

Briefs, approves, signs off

Advisor

Creative director

  • Product and web

    • UX
    • UI
    • Design system
    • Web
  • Brand and visual

    • Graphic
    • Illustration
    • Icons
    • Marketing design
  • Motion and sound

    • Motion
    • Sound
  • Copy and strategy

    • Copy
    • Strategy
  • Build and QA

    • QA
    • Development

The loop

  1. Brief
  2. Plan
  3. I approve
  4. Studio agents execute
  5. QA
  6. I sign off

The product pipeline

  1. Prototype
  2. MCP into Figma
  3. Two linked Figma files
  4. Developers
My design studio · How I work My tools, not Scully's product. Nothing moves until I approve the plan.
Research

Map the market first, then pick the gap

abra wasn't entering an empty market, so I mapped it before drawing a screen. My studio made the competitor research and the prototype's user testing fast; the calls stayed mine. Wonderful sells outcomes and hides the machinery. Jeen.ai governs AI agents for IT. Blocks lets anyone build one in plain language. None gives one operator outcomes, spend and retrieval in one place. That gap became the brief. With no live users yet, I based the product's people on its real roles. Later, the website got its own competitor scan before any new page.

Competitor landscape. Wonderful, Jeen.ai and Blocks each cover one part of the job. None gives one operator outcomes, spend and retrieval in one place, and that gap became Scully's brief.
Competitor landscape · Reconstructed for this case study Mapping the market first showed what Scully had to be: the one place none offered.
Read as text
  • Wonderful: sells outcomes and hides the machinery.
  • Jeen.ai: an AI operating layer sold to IT.
  • Blocks: lets anyone build an agent in plain language.
  • The gap: one hides the machine, one governs it for IT, one opens building to everyone. None of them gives one operator outcomes, spend and retrieval in one place.
  • Scully's brief: outcomes, spend and retrieval in one place, for one operator. That gap became the brief.
  • Method: competitor research, run fast with my design studio.

Sources: the case text and Daniel's notes. No invented data.

Back office

A complex system that stays calm to operate

The back office came first, and it's the most complex thing in this case. Operators run a fleet of Scully's AI agents from it: connect them to company systems, build workflows, watch every action and cap every cost. The fleet view opens with outcomes, then the one alert worth opening. Cost got its own page, because an over-budget agent is an incident, not a setting. It took a slot in a short navigation, and it's the call I'd defend hardest. Hebrew is built in, with full RTL. I prototyped it live in Claude Design, every state clickable, and developers get each feature as a numbered script with empty, loading and error states settled.

Workflow editor · 0:24 · No sound · Demo dataRecorded in the prototype. Problems surface where they're fixed, before anything goes live.
What you see

An Execution step is added to a workflow. Validate flags 3 problems and the inspector lists them. An agent, an instruction and a tool are chosen, and Validate passes: 7 steps. Run Test then shows each step with its timing, all ticks green.

{{ fs.t }} {{ fs.c }}

Under it: Scully-DS

Scully-DS holds 478 variables and 5 color modes, three dark and two light. Every value is a variable binding, so a new mode is a token change, not a repaint. Not everything became a component: drawer and modal bodies differ per feature.

Five color modes · 0:17 · No sound · Demo dataOne set of components serves every mode, so no screen is designed twice.
What you see

The same dashboard in Dark Graphite, Dark Emerald and Dark. The theme toggle switches to Light Snow, then Light, then back to Dark and Dark Graphite. Layout and components stay the same; only color changes.

Brand

From a simple S to a brand with its own language

With the product taking shape, Scully needed to look and sound like one company. I explored more than 20 logo directions, and management kept the S. So I rebuilt it: redrawn on a 4 px grid, 77 by 72 modules, so every edge lands on the grid. Around it, a cream ground, navy ink and amber as the only accent. Switzer for headlines, Inter for reading. Then Fluid took over the imagery: quiet grounds, each carrying one real piece of the product UI.

The Scully S mark in navy on cream, redrawn on a 4 px module grid.
The S · 4 px gridRebuilt, not replaced: management kept the S, so precision did the work.
Brand board, This is the Scully brand, on one page: the lockup in navy on cream and white on navy, four colors (cream ground, navy ink, warm gray text, amber as accent only), Switzer 400 for headlines, Inter for reading and the voice: plain, specific and calm.
Identity · On one pageThe whole identity on one board, so nobody has to dig for it.
Scully website hero mockup in Fluid: a soft cream and pale blue ground with a real workflow from the product, three connected steps each with a green check, beside the headline AI agents built for enterprise scale.
Fluid · Mockup · AI-generated groundA quiet ground and one real product layer, never a drawing of the product.
Design system

One system every surface draws from

The brand needed the same discipline as the product, so it got its own design system, separate from Scully-DS in the back office. Brand DS v1.8.0 holds every value and file: color, type, layout per surface, imagery, motion, print and accessibility, with color pairs rated to WCAG 2.2 AA. I wrote it so a person or an AI tool can use it, and the team builds decks, flyers, email, social and video from it. When the imagery moved to Fluid, every piece followed.

Components
36
Themes
Cream and Navy
Accessibility
WCAG 2.2 AA
Version
Brand DS v1.8.0
Sheet of nine real Scully pieces, each shown twice, in the retired Silk look and in Fluid: website hero, section slide, title slide, event cover, flyer, feed post, story, email and business card. Layouts match; only the imagery changes. Flyer figures are example data.
Nine pieces · Silk and Fluid · AI-generated groundsSame layouts, new ground. The system carried the switch to all nine pieces.
Color pairs with contrast ratios
PairRatioLevel
Ink on creambrand-navy on brand-cream16.6:1AAA
Text body on creamtext-body on brand-cream7.1:1AAA
Accent text on creamaccent-text on brand-cream5.3:1AA
Amber on navybrand-amber on brand-navy9.1:1AAA
White on navybrand-white on brand-navy18.7:1AAA
Text muted on creamtext-muted on brand-cream3.3:1Large only
Amber on creambrand-amber on brand-cream1.8:1Never text
Rated pairsWhen words need the accent, darker accent-text stands in and passes AA.
Brand book

A book for the rules, a portal for the team

The rules and wording live in brand book v2.4, cut per reader: an Extended edition of 136 boards, a Slim edition of 31 and a Management version for decisions. Extended and Slim ship as accessible PDF/UA-1, tagged so a screen reader can follow them.

Cover of the Scully brand book, Extended edition v2.4, Nov 2026: the lockup and the line How Scully looks, sounds and moves, on a soft cream ground.
Brand book v2.4 · Extended editionTagged for screen readers, because a brand book is a document too.
Brand book index, 13 chapters, one system: start here, story and voice, logo, color, typography, grid and layout, applications, imagery, agent portraits, motion, the brand meets the product, governance, downloads and contacts.
Index · 13 chaptersStory and voice come first, so the why arrives before the rules.
Brand book board 10.1, In the product, the agents look the same. Beside it, the dark back office with demo data shows Amit, a Scully AI agent, with its portrait, Live status and session dashboard.
Board 10.1 · Demo data · AI-generated portraitsWhere brand meets product: the UI keeps its own theme.
  • Extended

    136 boards · rules and wording

  • Slim

    31 boards · for teams and partners

  • Management

    for decisions

  • Accessible

    PDF/UA-1 · Extended and Slim

The portal

The portal gives the Scully team the slim edition and the files in one place. Book, design system and portal each have one job, and all three carry one version line.

Brand book v2.4 · DS v1.8.0 · Nov 2026

Scully brand portal, Use it section: One brand holds on every surface, with four shared cues and the website and a deck slide as examples.
Brand portal · Private, screenshot only · AI-generated groundRules arrive with examples, so the team sees the brand in use.
Website

A site an executive gets in 30 seconds

The back office is dense, made for someone who lives in it. scully-ai.com does the opposite job: an executive who will never log in should get it in 30 seconds. So the hero shows operations, not an illustration. Each sector gets its own terms, Scully's AI agents have faces and jobs and Clara, the voice agent, has its own Voice OS page, now live. Every path leads to one action: Book a demo. Underneath: SEO metadata, performance, reduced motion and accessible forms.

See it live: scully-ai.com (opens in a new tab)

scully-ai.com home hero: a man at two monitors in a warehouse office, the headline AI Agents Built for Enterprise Scale, Book a demo and Explore Voice OS buttons and a top bar introducing Voice OS.
Home hero · Live site · AI-generated imageThe buyer runs operations, so the hero shows operations.
Voice OS hero on navy: Meet Clara. The voice agent that gets business done. Four benefits, a Book a demo button and a Talk to Clara button marked live. Clara, Scully's voice agent, is shown as a woman with a headset. AI-generated image.
Voice OS · Scully AI agent · AI-generated imageClara gets her own page, with a live call one tap away.
Voice OS hero on a 390 px phone: Clara, Scully's voice agent, shown as a woman with a headset, above the headline Meet Clara. The voice agent that gets business done. Below, four benefits and the Talk to Clara and Book a demo buttons. AI-generated image.
390 px phone · Scully AI agent · AI-generated imageOn a phone, the live call and the demo sit side by side.
Films

Three films, from product tour to booth

Three films, three jobs: the product tour walks one process end to end, the Clara film makes the case to a buyer and the booth film stops people at an event. All three follow one film direction: a protagonist, the camera as narrator, very little text and the real product on screen, with demo data. Clara, a Scully AI agent, is the same AI-generated character in each. My studio's motion and sound agents built picture and mix; I directed every cut and signed off the final one.

Product tour · 3:06 · Has sound · AI-generated cast · Demo dataClara walks one purchase request into a purchase order, inside the real back office.
What happens in the film

Clara, a Scully AI agent, turns purchase requests into purchase orders, but agents like her stay in pilots because connecting to an ERP is slow and risky. Then the real back office takes over, with demo data. Clara is deployed in one window. A guided wizard connects the ERP: AI proposes the tools, the team removes what it doesn't want and publishing writes one signed contract, not code. A workflow limit is changed, validated and test-run on a draft while the live version keeps running. Amit's record shows a failed call and the retry. FinOps caps Clara's cost, and roles set who can change what. Clara goes live: "That's one process. Let me run yours."

Transcript

I'm Clara. I turn purchase requests into purchase orders. That work lives in your ERP. Getting an agent in there usually means a long integration project, and a security review of every line. So agents like me stay in pilots.

This is Scully. Where agents do the real work, inside your systems. And you see every step. One window: a name, the provider and model you trust, and the tools you allow. Then I joined the fleet, as a new hire.

Connecting me to your ERP is a guided flow, not a project. You tell it what I'm there to do. AI proposes the tools for that job, with a reason for each. Your team decides what stays, and can make any connector read-only. Publishing writes one signed, versioned contract. No code is generated, so security reviews a contract, not a codebase. A test in chat shows every call.

Here's the process I run. Max reads each purchase request and flags budget risks. Under the auto-approve limit, I create the purchase order. Otherwise, Max tells the requester. Say finance changes the limit. On a live process, that's the risky part. So the change is checked first, then tested on the draft, step by step. You decide when the new version goes live. Until then, the current one keeps running.

Amit is a teammate of mine. Its record shows what was said, which system it called, the call that failed, and the retry that worked. Nothing left to guess.

Cost is forecast against budget, with a limit on each agent. When I hit mine, you're notified, my model switches, or I stop. Your call. And who can change what is set per role, feature by feature: no access, view or edit.

I'm live now. Connected by contract. Changed safely. Every step, every cost, every permission, in view. That's one process. Let me run yours.

Clara film · 3:06 · Has sound · AI-generated cast · Demo dataMade for buyers: the problem first, then Scully, told by the agent it manages.
What happens in the film

Monday morning. A company counts its AI agents: dozens, each built somewhere else. The AI bill is over budget again, an agent reached into the CRM without approval and every vendor plays by its own rules. Then Clara introduces Scully and shows the real product: budgets and policies per agent, a managed data layer, connectors that expose only approved tools, roles and permissions, a sales agent built without code and the same agent on a website, WhatsApp or a phone line. She closes: "All your agents, from any vendor. One place, under your control. Including me."

Transcript

Hi, I'm Clara, Scully's AI agent. Someone should manage me. Decide what I touch, cap what I spend and stop me when I go over.

It's Monday morning. You count your agents. It's already dozens. Each one built somewhere else. Nobody sees the whole picture.

First, the money. The AI bill just landed and it's over budget. Again. Which agent spent it? On which model? Nobody can say. And nothing stopped it.

Then, the data. An agent reached into your CRM without anyone saying yes. And your core systems? Every agent leans on them, all at once.

And the rules? Agents from every vendor, each playing by its own rules. No single owner. No shared policies. Honestly? If I were you, I'd worry too.

So, meet Scully. One platform to build, connect and manage every agent.

Budget control first. FinOps shows what every agent costs, by model and by tokens. Here's my row. Yes, I'm on there too. You give each agent a monthly budget and policies. My policy? Go over budget, and I'm blocked. Automatically.

Next, a managed data layer. Open a knowledge base and you'll see its schema. For every field, you decide: searchable, filterable or sortable.

Your core systems plug in through Connectors. Each one shows me only the tools you approved. Nothing more.

And enterprise-grade security. Manage users and roles. For each role, you set what it sees, what it edits and where it has no access. Here's mine. Strict, but fair.

Now let's build one together. A new sales agent. Name it, pick a model and a speech mode. Write its instructions in plain language, the way you'd brief a new hire. Connect its tools. Click Deploy, and it's live. No code.

Want it on your website? Picture it with Scully App. Pick the agent, style the chat, paste one line of code. Just the one. And it's already answering your customers.

Or put it on WhatsApp. Or a phone line. Same agent, every channel.

All your agents, from any vendor. One place, under your control. Including me. Book a demo at scully-ai.com

Contact-center film · 1:09 · Has sound · AI-generated cast · Demo dataBuilt for a booth: Clara answers every caller, except the one that needs you.
What you see

Monday morning in a contact center: every line ringing, customers on hold. Clara, Scully's voice agent, answers right away, runs the process step by step in the ERP and logs a replacement order. One caller is over the limit, so Clara leaves that decision to a person. She introduces her Scully colleagues, Amit, Noya and Sophie, and ends at scully-ai.com.

Transcript

Monday morning. You know this one. Every line ringing. Every desk busy. Your people dig, screen after screen. The customer holds. And holds. They ring again. From the top. And it's not even ten.

That's where I come in. I'm Clara, Scully's voice agent. I answer right away. Nobody holds. I run your process, step by step, in your ERP. Order replaced. Logged. Done. Every caller in your queue, answered.

Except one. Over the limit? That's your call. I've done the legwork. My Scully colleagues: Amit, Noya and Sophie. Want to hear me work? I'm at scully-ai.com.

Journey

How it came together, month by month

The product came first. The brand, the book, the portal and all three films followed in Oct and Nov 2026, on top of the product work.

  1. I start on Scully: a name and a simple S.

  2. Back office: RAG Config Builder, full theming and the product design system.

  3. Back office: a light Snow theme, a keyboard accessibility guard and new error screens.

  4. Logo exploration ends with the S kept. Website competitor scan. Brand design system v1. Clara film begins.

  5. The S redrawn on a 4 px grid, Switzer, brand book v2, the portal and Fluid. Back office workflows rebuilt. Contact-center film, product tour and Clara film v6. Brand book v2.4 as accessible PDF/UA-1, Brand DS v1.8.0.

I estimate I now work about 5x faster than I did before AI, and without it the films would have been out of reach.

Outcomes

Shipped, in use and honest about what isn't measured

The prototype is what abra shows prospects, and development builds from the design system and the feature scripts, not from screenshots. On the brand side, the book ships in three editions, the portal is up for the team and scully-ai.com is live with its Voice OS page. The product isn't in production yet, so there are no adoption or cost figures to report, and I won't invent any.

{{ so.v }}
{{ so.l }}
{{ activeRec.name }}
{{ activeRec.role }}
{{ activeRec.tag }}
{{ activeRec.quote }}
{{ recCounter }}
Daniel Motza
Page not found

Error 404

Lost in deep space.

This page doesn't exist, or it has moved.

Report a broken link
404 · Page not found · Daniel Motza
Daniel Motza
Server error
!

Error 500

Houston, we have a problem.

Something broke on my side. Try again in a moment, or email me if it keeps happening.

Email me
500 · Server error · Daniel Motza
{{ lbCount }}
{{ lbLabel }} {{ lbCap }}
Playground
Off-duty orbit
Side quests, experiments and small joys between projects.
Drag to explore · select an item to zoom in