The long version

We stopped asking the chat box.

For twelve months we tried to design with AI the way everyone else was: prompt, copy, paste, retry. It worked for blog posts. It broke for everything that required structure, memory, and human judgment in the middle of the process.

The conversation scrolled away. Methods we'd practised for years didn't fit into a text box. The model's reasoning was invisible. Our outputs were good prose and bad product.

Plooi is what we built instead. A canvas where research, methods, and AI agents are objects you arrange, not turns you take. Where every method shows its working, every workflow keeps a human in the loop, and the graph itself becomes the artefact you ship.

This page is the long answer — the philosophy, the architecture, the trade-offs, the methods, the people we built it for. If the overview made you curious, you're in the right room.

— Dominik & the Plooi team
Spatial zoom

One Plooi. Three altitudes.

The canvas zooms semantically. Pull back for the whole shape of the work; lean in for one cluster of methods; lean further to read a single method's prompt. Same surface, three levels of detail.

100% overviewsee the shape

Whole-workflow shape. You read the topology — branches, fan-outs, dead-ends — without reading any labels.

200% clusterread the labels
METHODEmpathyMETHODHMWMETHODCrazy 8sAGENTPersonaAGENTCritic

Cluster scale. Names visible. You decide which branch to dive into.

400% methodread the prompt
AGENT · PERSONASarah, 34PROMPTYou are Sarah, a power user.React to {{ wireframe.frame_3 }}MODELClaude 4.7CONFIDENCE● 92%OUTPUT"It's pretty? I guess?"

Inside a single method — prompt, model, confidence, output. Full glass-box.

Our philosophy

Three values. No shortcuts.

Plooi is built on three principles we refuse to compromise on. None of them are about AI doing more — all three are about you doing more with AI, on a surface your brain was actually built for.

Craft

You make it well

We refuse the boilerplate AI-generated soup. Every method in Plooi was hand-built from research literature, tested with practitioners, tuned to support thinking — not replace it.

Clarity

You see every step

Every fold is visible. Every transformation is auditable. No black-box outputs — you can trace any insight back through the methods that produced it. Glass-box reasoning, not magic.

Curation

You decide what stays

AI proposes; you decide. Plooi generates variations, alternatives, refinements — and waits for your call on which to keep. Human-in-the-loop is non-negotiable.

White paperArchitecturally, that translates into a Spatial · Agentic · Glass-Box interface — read the technical foundation →
Anatomy of a Plooi

Four folds. One workflow.

Folding is the metaphor; methods and connections are the mechanism. Each fold adds discipline; each connection adds a path your insight can travel down.

01
Sheet

Start with a blank canvas.

Drop your brief, your research dump, or your half-finished spreadsheet. Plooi reads it and suggests methods — empathy work for users, JTBD for unmet needs, Simulation for service flows.

Brief
"Help us understand why power users churn after month two."
↓ Suggested
02
Crease

Add a single method.

Drop in an Empathy Map. Or Jobs-to-be-Done. Each method is a self-contained agent — feed it inputs, get structured outputs you can keep building on.

Says
"It used to be faster."
Thinks
"Did I miss an update?"
Does
Opens settings to investigate.
Feels
Friction. Then resignation.
03
Pleat

Wire methods into agents.

Pleat findings into a Synthesizer. Pleat the synthesis into a Critic. Plooi handles the data passing; you watch the structure emerge.

Empathy Map5 insightsSynthesizer3 framingsCritic92% conf.
04
Plooi

Save and reuse the stack.

A Plooi is a reusable workflow — sheet music for research. Run the same stack on a new brief; the structure stays, only the inputs change.

My Plois
Onboarding research5 methods · last run 3d ago
Churn investigation5 methods · running…
Concept-to-test pipeline8 methods · last run 1w ago
What you'll build

Three workflows. Day-one shippable.

These aren't tutorials — they're the canvases real teams use Plooi for, every week. Each is a starter template you can fork and remix.

01UX / UI design

Walk a Persona through your wireframes — before you ship.

Drop your screens in. A Persona agent walks the flow exactly as the user would. A Heuristics agent flags violations. You get a ranked friction list — and never debate 'is this a problem?' in the design crit again.

Result: 12 friction points · ranked by persona × severity · linked to the exact frame
SOURCEWireframesAGENTPersona simulatorCRITICHeuristics checkOUTPUTFriction map
02Service design

Build a service blueprint and simulate the unhappy paths.

Customer Journey → Service Blueprint → branch into Happy / Unhappy paths → run a Simulator agent over each. The blueprint is no longer a static deliverable — it iterates with your data.

Result: 1 blueprint · 3 failure scenarios · prioritized improvement backlog
SOURCEResearch notesMETHODCustomer JourneyLOGICBlueprint splitterAGENTPath simulatorOUTPUTImprovement list
03Concept → Pitch

Branch one brief into five concepts — keep only what survives.

Brief → "How Might We" reframes → Splitter fans out 5 strategy directions in parallel → Storyboard methods render each → a Critic agent ranks them against your brand guidelines. You arrive at the deck with options, not opinions.

Result: 5 concepts · 1 Critic-ranked top concept · auto-built pitch outline
SOURCEBriefMETHODHow Might WeSPLITTER5× Strategy direc…METHODStoryboard per di…CRITICBrand critic
How a Plooi grows

Plois evolve. Like sheet music.

A Plooi isn't a one-shot output — it's a workflow that gets better with every run. Refinements, feedback loops, and branches accumulate. Below: the same Plooi at four stages of its life.

01 · Template
day 0

A skeleton you fork from the library. Connections in place, methods empty.

02 · First run
day 1

Filled with project brief and one set of source documents. Output: rough but real.

03 · 10th run
month 1

You added a Critic agent, a feedback loop, and a branch for edge cases. Output: trusted.

04 · Mature Plooi
month 6

Team-owned, branched per project type, exports to JSON for CI. Now reusable.

Composition patterns

Four patterns. Infinite workflows.

Every Plooi canvas — no matter how big — is made of the same four primitive shapes. Once you can read them, you can build anything.

ABC

Chaining

One method feeds the next. The simplest discipline: A produces, B refines, C delivers.

A?BC

Routing

Pick the right next step based on the input. Negative sentiment? Send to escalation. Positive? File and move on.

A

Parallelization

One brief, five concepts at once. Fan out the work, let agents run in parallel, gather and rank the results.

GenCritic

Evaluator-Optimizer Loop

Generate → Critique → Generate again. The output keeps refining until the Critic agent gives a green light.

Anatomy of a pleat

Three kinds of connection. Each tells a different story.

Connections in Plooi aren't just lines — they carry meaning. A solid line says "this data flows directly here". A dotted line says "this influences that conceptually". A curved-back line says "iterate until this is good enough".

METHODEmpathyAGENTSynthesizerdata

Hard link

Direct data transfer

The output of A becomes the input of B. Strict type-check, no ambiguity. The bread-and-butter of any workflow.

e.g. Empathy Map → Insight Synthesizer
ZONEBrandAGENTCriticcontext

Semantic link

Conceptual influence

B is influenced by A but doesn't consume its raw output. Used for shared context, themes, or system-prompt inheritance.

e.g. Brand guidelines ⟿ all Critic agents
AGENTGeneratorAGENTCriticgeneratecritique

Feedback loop

Iterative refinement

B's output cycles back to A. Used in evaluator-optimizer loops — keep generating until the Critic approves.

e.g. Critic ↩ Generator (loop until score ≥ 80)
The Glass-Box principle

Open any method. See the seams.

Every Plooi method is a glass box. Hover it to see what prompt it's running, which model is wired to it, what its confidence score is, and where the output came from. No black-box magic — just legible craft.

  • ·Visual provenance. Trace every output back to its source quote.
  • ·Confidence-aware. Low-confidence methods wear an amber dashed border.
  • ·Human gates. Mark any method "requires approval" — the canvas pauses.
Agent · Reasoning
Persona simulator
● 92% confident⏵ running
1 · Prompt
You are Sarah, 34, a power user of {{ product.name }}. React to this onboarding screen as yourself: {{ wireframe.frame_3 }}
2 · Model
Claude 4.7 Sonnet
temp · 0.5·top-p · 0.9
3 · Output
"It's pretty? I guess?" I'd want to skip the onboarding tour — I've used this product before. The big "Welcome back!" pop-up is in my way.
↑ traced from interview transcript· session #84 · L 23-28
Live traceHuman-in-loop↳ click to inspect chain
Sub-agents in parallel

One orchestrator. Three minds at once.

Service-design example. The Orchestrator spins up three sub-agents — User, Backend, Support — to simulate a "lost credit card" journey in real time. Their messages stream into a single timeline so you can see exactly where the failure modes happen.

Orchestrator
Lost-card simulator
User Agent
Sarah, 34 · stressed
+0s
I just lost my card. I need to block it. Now.
+18s
Where is the "block card" button? The app is so confusing…
+1m 24s
(switches to phone, dials support)
Backend Agent
API + DB simulator
+0s
GET /api/cards/me → 200 OK · 47ms
+18s
POST /cards/.../block → 503 · DB locked
+1m 24s
Fallback path: customer service ticket auto-created
Support Agent
Tier 1 rep + tooling
+0s
(idle — no incoming ticket)
+18s
(idle)
+1m 24s
Ticket #4928 received. Customer on hold 2m 14s.
Friction surfaced: User waited 1m 6s for the block-card action to fail before discovering the phone fallback. Add: instant push-notification reassurance after 5s of locked-DB retry.
Confidence states

Trust, by the colour. No hidden hallucinations.

Every method wears its confidence on its border. Green for high, coral for medium, amber dashed for low. Locked methods pause the workflow until a human signs off. You always know when to trust, when to read, and when to intervene.

METHOD
● 92%
High
92%

Ship it.

METHOD
◐ 78%
Medium
78%

Worth a glance.

METHOD
◐ 51%
Low
51%

Read carefully.

METHOD
○ 23%
Very low
23%

Re-prompt or replace.

METHOD
paused
Awaiting review

Human pending.

METHOD
gated
Locked gate

Must approve.

Methods library

Fifty design methods.
Each a single crease.

Eight of them shown — Discover, Synthesize, Define, Ideate. The full library is in the app.

Discover

Empathy Map

Says / Thinks / Does / Feels — assumptions stripped to facts.

Discover

Jobs-to-be-Done

Features reframed as jobs people hire you to do.

Synthesize

Affinity Mapping

Cluster qualitative data; Plooi proposes, you sharpen.

Synthesize

Persona

Evidence-grounded archetypes — no stock photos.

Define

Customer Journey

Emotions, frictions, opportunities along the spine.

Define

Value Proposition

Jobs/pains/gains matched against your offering.

Ideate

Crazy 8s

Eight sketches in eight minutes. Discipline of quantity.

Ideate

Storyboard

Six frames; a user, a moment, an arc.

+31 moreResearch, ideation, validation, business modelling.
See the method library →
Methods constellation

The whole library, in one glance.

Plooi's methods cluster naturally into four phases — Discover, Synthesize, Define, Ideate. Common workflows trace a path through several phases. Some methods belong to two clusters; the constellation shows their gravitational pull.

01
Phase 01

Discover

Generate, capture, observe — raw material in.

Interview GuideEmpathy MapDesk ResearchCompetitor Scan
Cultural ProbesDiary StudyField NotesQ-ZeroCard Sort
02
Phase 02

Synthesize

Cluster, label, surface patterns — sense out of noise.

Affinity MappingPersonaJobs-to-be-DoneInsight Synthesis
SentimentTheme TaggerPain/Gain MapQuote Clusters
03
Phase 03

Define

Frame the problem, scope the bet — sharp questions.

How Might WeCustomer JourneyValue PropositionService Blueprint
User StoryGoal TreeKPI TreeJTBD Map
04
Phase 04

Ideate

Generate concepts, sketch futures — quantity then craft.

Crazy 8sStoryboardWireframesBrainstorm
MoodboardFuture ScenarioConstraint SetPrototype Brief
Bridge methods

Span more than one phase

Seven methods don't belong to a single cluster — they pleat across phases and act as hinges in most workflows.

User StoryStakeholder MapKano ModelSWOTStoryboardUse CasesUser Flow

Drag any method onto your canvas — Plooi reads the context of where it landed and auto-fills the prompt template.

39 methods4 phases+23 in backlog
Method taxonomy

Every method has a job. Four categories cover it.

The Plooi method library splits into four functional categories. Mix them like Lego — most workflows use one or two of each.

01Category

Data & Input

Where raw stuff enters

  • ·Source · PDFs, URLs, CSV
  • ·Persona · captured archetype
  • ·Goal · what to optimize for
02Category

Processor & Reasoning

The thinking layer

  • ·LLM · GPT-5, Claude, Llama
  • ·Chain-of-Thought · visible reasoning
  • ·Critic · adversarial check
03Category

Action & Tool

Side effects on the world

  • ·Search · web research
  • ·Generative UI · text → wireframe
  • ·Simulator · scenario testing
04Category

Logic & Control

The conductor

  • ·Router · conditional flow
  • ·Aggregator · gather + sort
  • ·Human-Approval · the pause
Who Plooi is for

Built for the people who design systems,
not just screens.

Plooi is unapologetically for the expert-generalist — the role that owns the bridge between research, design, and product strategy. If that's the cap you wear, this is your tool.

UX

UX Architect & Researcher

Today

Research lives in Dovetail, ideation in Miro, drafts in Figma, copy in ChatGPT. Every transfer is a context loss.

With Plooi

One canvas: transcripts cluster into themes, themes hatch into personas, personas critique your wireframes — all linked back to the original quote.

SD

Service Designer

Today

Static service blueprints go stale before they ship. Stakeholders argue about edge cases we never modeled.

With Plooi

Living blueprints. Branch into Happy / Unhappy paths and run a Simulator agent over each — fail-modes surface before launch, not after the postmortem.

PI

Product Innovation Lead

Today

Generating five concepts in parallel costs a week of team time. By the time we pitch, the market has moved.

With Plooi

Brief in, five concepts out — each with a storyboard, each Critic-ranked against your brand. Walk into Monday with options, not a single half-cooked direction.

Chat vs canvas

The chatbox scrolls away.
The canvas stays put.

Conversational AI is excellent for ad-hoc queries. For professionals doing iterative, multi-step work, it breaks down. Plooi is built for the work the chatbox can't hold.

Dimension
Linear chat
Spatial canvas (Plooi)
Information
Chronological, ephemeral
Topological, persistent
Cognitive load
High — you remember context
Low — canvas remembers
Interaction
Reactive (Q&A)
Constructive (build workflows)
Transparency
Black box (result without path)
Glass box (visible logic)
Iteration
Hard (context drift)
Native (branch & version)

from the Plooi white paper — "Beyond the Chatbot: The Era of Spatial Agentic Interfaces."

Your stack, simplified

Six tools become one canvas.

Today's research-to-product handoff bounces through five or six tools. Each handoff loses context. Plooi keeps all of it on one surface.

Before

Fragments.

Research lives in Dovetail. Ideation in Miro. Prompts in ChatGPT. Wireframes in Figma. Specs in Notion. Tickets in Linear. The "stack" is mostly copy-paste.

Dovetail·Research
Miro·Ideation
ChatGPT·Synthesis
Figma·Wireframes
Notion·Specs
Linear·Tickets
Context dies between every arrow.
After

One Plooi.

Every task above becomes a method on a single canvas. The connections between them carry the context automatically — no exports, no re-pastes, no stale links.

ResearchDovetail-inSynthesisAffinity agentIdeationCrazy 8sWireframesFigma-linkSpecsMarkdown outTicketsLinear-outPitchStoryboard
Context follows the connection. Always.
Pricing

Pay for what unfolds.

Credits cover AI-assisted methods. The canvas, the methods, the collaboration — those are free.

Free
€0
/ forever
  • ·1,000 credits / month
  • ·3 active projects
  • ·16 core methods
  • ·Single user
Start free
Starter
€15
/ month
  • ·15,000 credits / month
  • ·5 active projects
  • ·The full method library
  • ·Method versioning
  • ·PDF export
Choose Starter
Most chosen
Plus
€39
/ month
  • ·50,000 credits / month
  • ·Unlimited projects
  • ·Collaboration (3 seats)
  • ·Custom method authoring
  • ·Priority support
Choose Plus
Pro
€99
/ month
  • ·150,000 credits / month
  • ·Unlimited projects
  • ·Collaboration (10 seats)
  • ·SSO, audit log
  • ·Workspace branding
  • ·Dedicated success
Choose Pro
Made in Germany
Frankfurt + remote
GDPR compliant
EU data residency
Glass-box by design
Every answer shows its work
Your data, your canvas
Export as JSON, code or PDF