Field Notes, page 2 — Design Outcomes

BUILDING NUBANK

LDLR DESIGN FIELD NOTES

Skills are dependencies

Palma and Martins gate the marketplace: 2,000 skills vetted, 1,600 risks flagged, before one reached a developer.

BY LUCAS PALMA AND PAULO MARTINS / SEP 2, 2026

When AI skills become supply-chain dependencies

A prompt can suggest behavior, but a control outside the model can enforce it.

Why it matters

— Skills read like documentation, but their operational effect is a dependency

— Skill Vetter gates the marketplace: 2,000 scanned, 1,600 risks, 1,000 remediated

— Deterministic rules catch known patterns; an LLM reads intent across instructions

— Ask-before-running lives in the prompt, so the model approves its own action

— Local checks plus CI make the safe path the easiest path

Read on Building Nubank →

Systems & primitives Cross-functional & process

DESIGN SYSTEMS COLLECTIVE

LDLR DESIGN FIELD NOTES

Who checks the checker

Williams reads seven August writers landing on one gap: enforcement graduated into furniture, which nobody owns.

BY SHANE P WILLIAMS / SEP 11, 2026

Who Checks the Thing That Checks

A recorded reason with no owner is just a better-documented assumption.

Why it matters

— Custody evaporates when a rule hardens into infrastructure; pipelines become furniture

— Negreiros, in a comment thread: refuse to let enforcement graduate into infrastructure

— Encoded governance looks identical to working governance until someone checks

— Ovcharenko: drift surfaces when someone new asks why docs and file disagree

— The apprenticeship that produces that noticing person is being automated away

Read on Design Systems Collective →

Systems & primitives Critique & decision-making

UX COLLECTIVE

LDLR DESIGN FIELD NOTES

The confidant, logged

Brêtas follows surveillance into the thought before the thought: drafts confided to AI, logged, scored, discoverable.

SEP 10, 2026

Your first draft now has a log

We invented a confidant the law never recognized as a confidant.

Why it matters

— Trust No Bot, 2024: disclosures surface in translation requests and code edits

— ActivTrak splits one dataset: self-care screen for you, named ranking for your manager

— Ravid’s 94-sample review finds no performance gain from monitoring, transparency helps attitudes

— February’s Heppner ruling: Claude conversations went to a third party, unprivileged

— Judge collection by its worst plausible use, and who walks data back

Read on UX Collective →

Research & validation Critique & decision-making

DESIGN SYSTEMS COLLECTIVE

LDLR DESIGN FIELD NOTES

Make breaking it hard

Kumar’s five layers for agent-built UI: tokens, components, context, discovery, and enforcement wired into CI.

BY RAKESH KUMAR / SEP 11, 2026

AI-Generated UI Needs a Design System That Can Enforce It

Don’t ask AI to remember your design system. Make violating it difficult.

Why it matters

— The agent’s dashboard compiled, then shipped a second table component anyway

— Context tells AI what the system is; enforcement tells it what it cannot violate

— An MCP server exposes the contracts; compliance still lives in the pipeline

— Raw hex, arbitrary spacing, and duplicate components all fail the build

— Compliance becomes a metric: token usage, custom components per agent PR

Read on Design Systems Collective →

Systems & primitives Cross-functional & process

UX COLLECTIVE

LDLR DESIGN FIELD NOTES

Eras keep the wrong half

Neeman walks five eras since Bell Labs, each keeping the disposable habit and forgetting the durable lesson.

SEP 11, 2026

Five eras of UX design and the lessons to keep in the AI era

Information architecture didn’t die. It went underground and waited for the machines to need it.

Why it matters

— Karlin’s touchtone keypad and Deininger’s 1960 grid study open the lineage

— Norman’s 1993 Apple title covered industrial design, interface, even the manual

— Design system ceremony only made sense while execution stayed expensive

— UXPA logs the worst net staffing reduction on its record, below the 2009 trough

— Leverage moved upstream to rules, structure, and the data agents execute against

Read on UX Collective →

Systems & primitives Storytelling & narrative

NIELSEN NORMAN GROUP

LDLR DESIGN FIELD NOTES

Three keys, one lock

Fessenden names the challenges and five moves, simplicity through co-creation, that raise the floor for every user.

BY THERESE FESSENDEN / SEP 7, 2026

Neurodivergence: What is it and Why Does it Matter

Neuroinclusive design helps all users: simplicity, clarity, control, support, and co-creation.

Why it matters

— Executive function, communication, and sensory processing name the challenge areas

— Five moves: simplicity, clarity, control, support, and co-creation with users

— Co-creation puts neurodivergent users in the process, not just the tests

— Six minutes, sized for the next team accessibility review

Watch on Nielsen Norman Group →

Research & validation Craft & detail

NIELSEN NORMAN GROUP

LDLR DESIGN FIELD NOTES

Plausible is no one

Krause draws the AI line in empathy mapping: a sticky note you can’t trace to a real person is an assumption in costume.

BY RACHEL KRAUSE / AUG 28, 2026

AI Can't Replace Real Research in Empathy Mapping

What it produces could describe a frustrated user of almost any product, which means it describes no one in particular.

Why it matters

— The pairs tell it: “I wish the app would ask before swapping items” vs the oat milk swapped for whole milk and charged before the notification landed

— Real quote, banking: “I always transfer $1 first to make sure I typed the account number right”

— Legitimate: clustering, cleanup, and summarizing data you collected. Compromising: generating any of it

— The trace test: can this sticky note be walked back to actual research evidence?

— Uncomfortable answers mean the map needs more research, not more prompting

Read on Nielsen Norman Group →

Research & validation Critique & decision-making

NIELSEN NORMAN GROUP

LDLR DESIGN FIELD NOTES

A thousand words, still

Dykes defends long-form copy: three jobs fragments can’t do, from explaining complexity to earning search visibility.

BY TAYLOR DYKES / AUG 31, 2026

We Still Need Long-Form Copy

Some things are complex, require trust, and need SEO & AEO benefits.

Why it matters

— Three jobs short copy can’t do: explain complexity, establish credibility, earn search visibility

— AEO joins SEO: answer engines cite substantive pages, and fragments don’t get cited

— The natural homes: technical docs, legal writing, help and support, product descriptions, about pages

— Formatting is the concession to attention: summaries, callouts, bolding, visuals for anything past a thousand words

Watch on Nielsen Norman Group →

Storytelling & narrative Craft & detail

NIELSEN NORMAN GROUP

LDLR DESIGN FIELD NOTES

Sweep once, teach twice

Kaley and Budiu name the custodial era: production got cheaper than evaluation, so UX triages what already exists.

BY ANNA KALEY AND RALUCA BUDIU / AUG 28, 2026

The Custodial Era of UX: Cleaning Up After AI

It can now take less time to create an experience than to decide whether that experience is useful, usable, trustworthy, or coherent.

Why it matters

— The custodial pattern, five steps: new idea, rapid production, lagging evaluation, user problems, UX cleanup

— Triage before polishing: evidence of need, mental-model fit, integration cost, opportunity cost

— The outcome isn’t always “redesign it” — keep, simplify, integrate, postpone, or remove

— Match evidence to risk: quick tests for low-stakes features, rigor reserved for high-stakes workflows

— Feed cleanup lessons back into generation: UX-context files, design systems, content standards

Read on Nielsen Norman Group →

Critique & decision-making Cross-functional & process Research & validation

LINEAR

LDLR DESIGN FIELD NOTES

Three of every four PRs

Ramp built Inspect with six years of Linear as its memory. The agent now writes three of every four merged PRs.

AUG 31, 2026

The coding agent behind 75% of Ramp’s merged PRs

The speed has moved Ramp’s bottleneck from writing code to reviewing it, a constraint any company running agents at this scale will meet.

Why it matters

— Inspect started as a casual idea; three engineers shipped the first version in two weeks

— Built in-house so it fits Ramp’s lifecycle exactly: one API key, their own log schemas, their sandboxes

— A designer takes a dashboard rework most of the way from Figma, then hands the live session to an engineer

— In Slack, “@Inspect, fix this” is often all it takes to open a PR

— A central team defines what agents can access, so functional teams automate safely on shared rails

Read on Linear →

Cross-functional & process Systems & primitives

MURPHY TRUEMAN

LDLR DESIGN FIELD NOTES

Forks look like adoption

Import counts can’t tell reuse from copying, and AI made forks cheap. Trueman watches prop shapes and wrappers instead.

BY MURPHY TRUEMAN / AUG 21, 2026

Every fork looks like adoption

Forking has always looked like adoption. It just used to be expensive enough that someone actually noticed.

Why it matters

— GitClear, 623M code changes: cross-file reuse down 35%, refactoring down 70%, duplication up 81% since 2023

— A ProductCard wrapping Card counts as adoption while quietly becoming a parallel API

— Signal one: a long tail of one-off prop combinations means teams work around the API, not with it

— Signal three is the one he wants most: a Button that never imports Button, caught by structural similarity

— The check doesn’t need to block the merge — it needs to make the twenty-minute conversation happen

Read on Murphy Trueman →

Systems & primitives Critique & decision-making

FIGMA

LDLR DESIGN FIELD NOTES

The prototype pitched

King vibe-coded the WebGPU canvas he’d imagined for years, recruited the team it earned, and shipped in two months.

BY ROGIE KING / SEP 1, 2026

Behind the build: Generative plugins and shaders at Figma

While it had taken us months to build progressive blur in Figma Draw, I could now create the same shader effect with one simple prompt — maybe two to nail it.

Why it matters

— Show, don’t tell: the “FigGPU” prototype did what a years-old obsession and a Loom in Slack never could

— Yassir Solomah validated it for real, replacing WebGL 2 fragment shaders with sandboxed WebGPU pipelines

— Two months to Config: no PRDs, no crits, demos over formal reviews, one massive Slack channel

— The reversal: vibe-coded prototypes served designers but failed developers and PMs — static mocks realigned the team, then code took over

— PropsKit, a web-components Figma UI kit, exists so agent-built plugins look and feel native

Read on Figma →

Prototyping & exploration Craft & detail Cross-functional & process