Field Notes — Design Outcomes

BOOTCAMP

LDLR DESIGN FIELD NOTES

Prompts are a thin layer

Stripe, Fin, Anthropic, Vercel, and Linear turn design knowledge into context agents can act on, graded on a maturity scale.

OCT 5, 2026

how design gets done in 2026, part 3 / inside the AI infrastructure of Stripe, Fin (formerly Intercom), Anthropic, Vercel + Linear

The chats are disposable. The brief is the institution.

Why it matters

— Four maturity levels: human-readable, machine-accessible, machine-actionable, and self-evaluating

— Stripe's Protodash wraps AI prototyping in Sail so generated UI matches shipped product

— Linear's CEO built a custom skill drawing on 40,000 customer requests

— Fin committed every designer to shipping production code, then codified it in a framework

— Her warning: governance is lagging adoption across every org she profiled

Read on Bootcamp →

Systems & primitives Cross-functional & process

JULIAN OCZKOWSKI

LDLR DESIGN FIELD NOTES

The meter is running

Figma's agent left free beta on October 6 and now draws from the same credit budget as Make: AI spend is a design budget line now.

OCT 10, 2026

Figma Just Put a Meter on Its AI Agent

Execution gets cheap. Judgment, standards and knowing what good looks like get expensive.

Why it matters

— Agent prompts now draw from the same credit budget as Figma Make

— Admins can pull a CSV of beta usage to forecast team spend

— Write guidelines first: an agent that knows your standards burns fewer credits on rework

— Run one real task through Figma's agent, Claude Design, and Claude Code, then compare

— Figma's cost of revenue grew 117 percent, mostly AI infrastructure and hosting

Read on Medium →

Cross-functional & process Critique & decision-making

DIVE CLUB

LDLR DESIGN FIELD NOTES

Where craft concentrates

Katie Dill on design at Stripe: Protodash prototyping, the hiring signals she reads, and where craft concentrates as AI spreads.

FEB 23, 2026

Katie Dill - The new era of design at Stripe

Why it matters

— Protodash changed how Stripe designers prototype, inside the real design system

— The 'Call for a new aesthetic' grant is shaping how Stripe thinks about beauty

— The hiring signals she reads in designers as the tools shift

— Craft concentrates rather than disappears as AI takes over more production work

Watch on YouTube →

Craft & detail Hiring & team Prototyping & exploration

SMASHING MAGAZINE

LDLR DESIGN FIELD NOTES

A name everyone can use

Friedman tours naming conventions for tokens, components, layers, and features, built on the systems other teams already use.

OCT 6, 2026

A Practical Guide To Naming Things

The right name is the one that's well-understood and used by the team and users.

Why it matters

— Good names are short, meaningful, known by everyone, and free of visual properties

— Vodafone's token taxonomy climbs from primitives to semantic names that reveal their purpose

— Ask users to describe a feature in their own words, then adopt their words

— Check the Component Gallery before coining a name other teams already settled

— Low adoption can be a naming conflict, so log it in the backlog

Read on Smashing Magazine →

Systems & primitives Craft & detail

DISHANT SHARMA

LDLR DESIGN FIELD NOTES

Design systems as files

Google's Stitch team shipped DESIGN.md, an open alpha spec pairing tokens with prose intent so coding agents inherit visual rules.

OCT 4, 2026

Why DESIGN.md Broke the Internet in Under 24 Hours

Design systems are becoming text files.

Why it matters

— YAML tokens for color, type, spacing, and radii, with Markdown explaining the intent

— A CLI lints the file for broken references and contrast failures

— One open format could travel across tools instead of living inside one vendor

— The announcement reached 2.2 million views within a day of shipping

— Skeptics: a file generated from appearance records the visible choices, not the design intent

Read on DEV Community →

Systems & primitives

DIVE CLUB

LDLR DESIGN FIELD NOTES

Systems at Google scale

Rhiannon Bell, VP of UX for Google Search, on the decisions behind AI Mode, dynamic component systems, and the skills gaining value.

OCT 6, 2026

Systems & primitives Hiring & team

PROOF OF CONCEPT

LDLR DESIGN FIELD NOTES

A mode, not a mood

Hoang’s week runs in three deliberate modes — Push, Triage, Focus — because a system is a set of decisions about attention, not apps.

OCT 4, 2026

How I work

I try to treat triage as a mode, not a mood.

Why it matters

— A productivity system is a set of decisions about attention, not apps

— Three modes in dedicated blocks: Push creates momentum, Triage clears loops, Focus goes deep

— Push runs on pre-written messages, contextual pass-downs, and decisions made legible

— Slack bookmarks route into Trello so responsiveness never becomes the default

— Deep work gets four-hour blocks, earned by doing Push and Triage well first

Read on Proof of Concept →

Cross-functional & process Craft & detail

DOUG POWELL

LDLR DESIGN FIELD NOTES

Bengaluru’s next leaders

Powell’s dispatch from UXINDIA: measuring design’s value, an Experience Orchestrator role, and India’s next design leaders.

OCT 5, 2026

The Future of Design Leadership is Taking Shape in India

The next generation of global designers and design leaders will be heavily rooted in India.

Why it matters

— His workshop frames design value as inputs, throughputs, and outputs tied to priorities

— New research finds no playbook into leadership and real gaps in mentorship

— Google and Amazon panelists: cross-functional relationships matter as much as the team

— BayOne floats an Experience Orchestrator role and a Conviction Score metric

— A student forum spanning twenty universities shows where the next cohort forms

Read on Substack →

Hiring & team Cross-functional & process

DOC

LDLR DESIGN FIELD NOTES

A prompt is a confession

Braga watches the box read him back: a prompt discloses your clarity, your references, and the questions you didn’t think to ask.

OCT 5, 2026

Prompting as Self-Portrait

The chat window is the only place I can be completely uncertain and receive something completely confident back.

Why it matters

— Before the model answers, the prompt has already read you back

— Models return flattering certainty, turning creators into consumers of their own ideas

— The chat window: complete uncertainty in, complete confidence out, nowhere else

— His counterweight: the blank page, silence, and conversations that push back

Read on DOC →

Storytelling & narrative Critique & decision-making

SHOPIFY ENGINEERING

LDLR DESIGN FIELD NOTES

Reliable convergence

Naqvi gates LLM migration work checkpoint by checkpoint: prove behavior, review the pixels, then a human signs.

BY TALHA NAQVI / SEP 21, 2026

Helix: The internal tool powering our Shopify app’s native migration

We stopped optimizing for a perfect first attempt and started working towards reliable convergence.

Why it matters

— A 300-screen React Native app, rebuilt native by LLMs in small checkpoints

— Four gates in order: CLI-proven behavior, visual review, adversarial code review, engineer approval

— Gemini plays perfectionist design reviewer, comparing screenshots against the React Native reference

— Engineer feedback feeds a memory that grows autonomy as the migration advances

Read on Shopify Engineering →

Cross-functional & process Critique & decision-making

MICROSOFT DESIGN

LDLR DESIGN FIELD NOTES

The empty room

Jiang brings Sunyata to Copilot: automation as emptying, removing mechanical labor to make room, not adding more.

BY QIAN JIANG / SEP 22, 2026

Create Ways of Being

Emptiness is the space in which reality can reveal itself.

Why it matters

— An AI designer on Copilot who has shown work at the Louvre and Tate Modern

— From Zhuangzi and Kant to Alipay sweet potatoes: hyper-digitization exhausts what it connects

— Sunyata as design principle: automation removes mechanical labor instead of adding features

— Her Garden of Synthetic Eden reimagines Bosch through AI’s birth and failure modes

Read on Microsoft Design →

Storytelling & narrative Craft & detail

PROOF OF CONCEPT

LDLR DESIGN FIELD NOTES

Be the stakeholder

Hoang’s case for the design GM: own a P&L, run the roster, stop appeasing the stakeholder and be one.

SEP 20, 2026

The Design GM

It’s time to go from appeasing stakeholders to being the stakeholder.

Why it matters

— The GM builds the roster and owns the outcome; the coach wins the games

— Three areas: business outcomes, operations that earn their calendar, a cross-disciplinary roster

— At Replit he owned marketing and the self-serve funnel, signup through renewal

— Few GMs come from design; Bruce Bell at Square is the known exception

Read on Proof of Concept →

Hiring & team Cross-functional & process