The Design
Intelligence Review
Sign in Join free
The Agentic Design Stack
UX is the future of AI
1.2M+
People in the UXM Community
112+
Invisible Machines episodes
20+
Years publishing UX thinking
Season 7—Spring 2026  ·  13 episodes  ·  Through-line: the human architecture of institutional change
Boring AI
is Good AI
Gordon
Why AI Scaffolding
Matters More than Use Cases
Flowers · S6
Decentralized
AI is the Future
Goertzel
Canonical
Knowledge is Key
DosSantos
What AI as
Cheap Prediction Means
Gans
Cheap Prediction,
Expensive Change
Goldfarb
Folk Law &
Fax Machines
Pahlka
Inside The
Infinity Machine
Mallaby
Crisis Is
Your Opening
Nitze
The Confabulation
Machine
Ratliff
No Strategy
Without Vision
Evergreen
When Agents Have
Wallets, Trust Is Currency
Cohen Freue
Nuclear Fusion,
No Power Lines
Frankle
The Checklist Your
Deck Is Missing
McMillan
Knowing Before
Doing
Hasbe ← Latest
New Ideation
New this week  ·  S7E13 · Sudhir Hasbe
Ideation

Knowing Before Doing

The industry is sprinting toward autonomous action while skipping the onboarding step every human gets: learn what matters before anyone hands you the scalpel. Sudhir Hasbe argues graph databases are the knowledge layer—relationships over rows, feature reduction over million-token dumps, shared semantic maps over siloed agent memory.

Originating episode · Knowing Before Doing · Invisible Machines  ·  Sudhir Hasbe  ·  S7E13  ·  June 2026
Read the full Ideation →

Before you start doing, start knowing.

—Robb Wilson on organizational AGI · Invisible Machines · S7E13
Related ideas: Organizational AGI Knowledge graphs Feature reduction Learning agents Neo4j
In this ideation
Episode
Free
Knowing Before Doing — Sudhir Hasbe · Invisible Machines
Sudhir Hasbe  ·  President & CPO, Neo4j
Knowing Before Doing · Invisible Machines
S7E13  ·  June 2026
UXM Article
Free  ·  10 min
UX Magazine Staff
The Graph Is Your Cortex
Companion essay on relationship-native knowledge, feature reduction, and why graphs are the reasoning substrate for agentic systems.
Read article →
Archive summary
Free  ·  8 min
Dr. Jim Webber · S2E4
Graph Databases Give LLMs Context
Neo4j’s chief scientist on graphs as LLM underlay—the through-line that lands in Sudhir’s S7E13 conversation.
Read summary →
Archive summary
Free  ·  9 min
Roger Forsgren · S3E14 · guest host Mike Lee
Lean Knowledge Management at NASA
Critical knowledge for specific audiences, return on mission success, and why the ROI of KM is the absence of disasters.
Read summary →

New Articles

All articles →
Organizational design

The People Who Will Not Be Replaced by AI

Peter Hinssen on builders, sellers, and measurers—why AI may amplify the first two while the third merges into a radically new operating model.

Peter Hinssen  ·  9 min
 UX × AI Series
Part 3 · Service design

Stop Calling It Empathy: AI Does Not Feel Anything

Tushar Deshmukh on why AI pattern-matching is not empathy—and why calling it that can displace the human understanding design is supposed to protect.

Tushar Deshmukh  ·  12 min
Interaction design

Why AI Agent Sprawl Is a UX Problem

When every team ships its own agent, customers feel fragmented CX and designers lose the system—sprawl is a governance and UX design problem, not only an IT one.

UX Magazine Staff  ·  8 min
Service design

Broken Telephone: Why AI Fixed the Wrong End of the Conversation

Sirte Pihlaja on the consumer-side gap—organizations built inbound AI at speed, but Gartner says machine customers who initiate service requests are coming fast.

Sirte Pihlaja  ·  8 min
 UX × AI Series
Part 2 · Conversation design

The Prompt Is the New Brief

Tushar Deshmukh on why prompting isn’t prompt engineering—it’s brief-writing applied to a new surface, and designers already know how to do it.

Tushar Deshmukh  ·  12 min
Interaction design

Beyond Vibe Coding: A Designer’s Case for Directed Generation

Jim Gulsen on why “vibe coding” misnames serious AI-assisted design—and why directed generation puts judgment, references, and constraints before the model responds.

Jim Gulsen  ·  7 min
 UX × AI Series
Part 1 · Organizational design

AI Is Your New Intern, Not Your Replacement

Tushar Deshmukh dismantles the replacement myth—AI is fast and tireless, but completely dependent on your judgment and accountability.

Tushar Deshmukh  ·  14 min
Service design

The Agile Trap Designers Fall into: Feeding the Beast

Päivi Salminen on why agile teams trap designers in endless mockups—and how design systems front-load decisions so teams can focus on how interfaces actually work.

Päivi Salminen  ·  4 min
Ideations—Season 7 All ideations →
Future-Solving
Naming the human-feeling outcome before the tool parade begins: map what must become true, let exploration stay fuzzy while the vision stays sharp, and refuse to substitute vendor matrices for strategy.
↳ Evergreen, S7E9
Also in: vendor bake-off essays, members kickflip arc
◉ Episode ◉ UXM article ◉ Members essay ◉ Transcript
Canonical Knowledge
One governed layer of meaning everyone agrees to treat as source-of-truth—so agents and humans aren’t improvising incompatible copies of the same policy, pricing rule, or clinical pathway.
↳ DosSantos, S7E2
Also in: scaffolding episodes on operational truth
◉ Episode ◉ Guest article ◉ Transcript ○ Members essay
Cheap Prediction, Expensive Judgment
When prediction drops toward zero marginal cost, the binding constraint stops being “can the model guess right?” and becomes “who is accountable for acting on it inside messy institutions?”
↳ Goldfarb & Gans, S7E3–4
Also in: complements to prediction economics
◉ Episode ◉ UXM article ◉ Transcript ○ Members essay
The Confabulation Machine
LLMs as conviction engines: fluent, plausible, and prone to completing narratives that never happened—a design problem for verification layers, not just model knobs.
↳ Ratliff, S7
Also in: Shell Game cluster essays
◉ Episode ◉ UXM essays ◉ Members essay ◉ Transcript
Latest Episode Episode page →
Read now  ·  Invisible Machines S7E13
Knowing Before Doing—Sudhir Hasbe · Invisible Machines S7E13
Knowing Before Doing
Sudhir Hasbe on graphs as the agent knowledge layer
Sudhir Hasbe  ·  President & CPO, Neo4j
Organizational AGI, feature reduction, decision traces, and a live demo of a Neo4j-powered learning agent—knowing before doing when autonomous systems act at scale.
Recent Episodes
S7 · Sudhir Hasbe
Knowing Before Doing
Graph databases as the agent knowledge layer—knowing before doing.
S7 · Jeff McMillan
The Checklist Your Deck Is Missing
Knowledge before agents at enterprise scale.
S7 · Jonathan Frankle
Nuclear Fusion, No Power Lines
Fusion-grade models without the grid—and specification beyond benchmarks.
S7 · Brian Evergreen
No Strategy Without Vision
Vision-first strategy and procurement theater.
S7 · Federico Cohen Freue
When Agents Have Wallets, Trust Is Currency
Knowledge before action at enterprise scale.
S7 · Evan Ratliff
The Confabulation Machine
Truth, narrative completion, and verification design.
S7 · Marina Nitze
Crisis Is Your Opening
Sensemaking failure and crisis engineering practice.
S7 · Sebastian Mallaby
Inside The Infinity Machine
Capital, concentration, and frontier models.
S7 · Jennifer Pahlka
Friction Is the Feature
Folk law, implementation gaps, and civic systems.
S7 · Avi Goldfarb
Cheap Prediction, Expensive Change
Complements, judgment, and organizational cost stacks.
S7 · Joshua Gans
What AI as Cheap Prediction Means
Enterprise workflows when inference gets cheap.
Members Essays Member essays →
Members only  ·  Josh Tyson
The “Do a Kickflip” Era of Agentic AI

In the rush to adopt AI agents, many organizations are acting like beginners attempting a kickflip—eager, ambitious, but unprepared. Strategy, runtimes, and verified knowledge turn repetition into progress; hype alone turns it into pavement.

Republication  ·  Paired with Brian Evergreen S7E9
Vision-first strategy Agent runtimes Knowledge bases Future-solving
Josh Tyson  ·  7 min read  ·  Cluster republication 2026
Read members essay →
Also in members
Invisible Machines Social contract
Did We Agree to This?
🔒 Members essay · Josh Tyson · May 6, 2026 · 9 min