Sign inGet started
Skills / Innovation-creativity

Design Thinking

Design thinking is a human-centered approach to innovation that draws from the designer's toolkit to integrate the needs of people, the possibilities of technology, and the requirements for business success.

Design Thinking is IDEO's five-phase human-centered innovation framework — Empathize, Define, Ideate, Prototype, Test — that transforms fuzzy challenges into testable solutions. Developed by Tim Brown and codified with Stanford's d.school, it gives product teams, entrepreneurs, and innovators a repeatable process for generating ideas grounded in actual user research rather than guesswork. What makes it distinct is its insistence on desirability first: solutions must be wanted by real people before asking whether they're feasible or viable.

By Tim Brown · Free
Specimen 01 · Live diagnosisDesign Thinking
Input

“We're trying to improve onboarding for our B2B software. Customers sign up, get a product tour, and then we see huge drop-off in the first two weeks.…”

Diagnosis
Let's put Design Thinking to work on your challenge.
Full transcript ↓
Calibrated referenceagent-skills.ai
The gap

Solve the right problem by starting with real human needs, not assumptions

Design Thinking operates through five phases, each with defined activities and outputs. Empathize uses ethnographic tools — interviews, observation, shadowing — to surface unmet needs. Define synthesizes those observations into a crisp Point-of-View (POV) statement structured as 'User / Need / Insight,' then reframes the problem as a bank of How Might We (HMW) questions that open up solution space. Ideate applies structured divergent-thinking techniques — brainstorming rules, SCAMPER, analogies — to generate a wide range of candidate solutions without premature judgment. Prototype builds the lowest-fidelity representation needed to make an idea testable — the 'build to think' principle. Test collects real user feedback against the prototype, producing iteration triggers that send the team back into any earlier phase. Underlying the whole process is Brown's evaluation triangle: every solution is ultimately assessed against desirability (do people want it?), feasibility (can we build it?), and viability (should we?). In practice the phases are non-linear — test findings often reframe the original POV — but each phase has clear entry criteria and named deliverables that make the process encodable and repeatable.

The problem

Most innovation projects fail not because teams lack ideas but because they're solving the wrong problem — one defined by internal assumptions rather than real user needs. Teams jump from a fuzzy brief to solution-mode, skipping the hard work of understanding who they're designing for and what those people actually need. The result is well-executed solutions to the wrong problem, or prototypes that never make it past a first user test.

The solution

Work through the five Design Thinking phases with a guided co-facilitator: surface real user insights, reframe your problem with precision, generate ideas against the right criteria, and produce a prototype brief ready to build and test — all grounded in Tim Brown's IDEO framework rather than generic brainstorming.

You bring
  • Your problem space or design challenge (rough or refined)
  • Raw observations, interview notes, or user research you've collected
  • Constraints you're aware of (time, budget, technology, organization)
  • Any ideas or directions you've already considered
You get
  • A crisp Point-of-View statement pinning the real user need your solution must address
  • A bank of How Might We questions that reframe your problem as opportunity space
  • An empathy map or user persona synthesized from your research notes
  • A prioritized idea shortlist evaluated against desirability, feasibility, and viability
  • A prototype brief specifying what to build, what question it must answer, and how to test it
In action

Watch the methodology work.

Three specimens from a single real session: the same situation, unaided and calibrated, the full transcript, and the skill answering live in the channel where the work happens.

Fig.01The same situation, two ways
Specimens A · B
Specimen AVague
Unaided

“You have 47 sticky notes from three customer interviews, a feature drop-off chart showing 60% churn in week two, and a team arguing between 'redesign the tour' and 'add a checklist.' The next sprint starts Monday and nobody agrees on what the actual problem is.”

×Vague — nothing concrete to act on.
Specimen BCalibrated
With Design Thinking

“You have a single, crisp Point-of-View statement your whole team signed off on, a bank of eight How Might We questions ranked by opportunity size, a shortlist of six ideas scored against desirability / feasibility / viability, and a prototype brief for the top candidate — specifying exactly what to build, what question it must answer, and how to run a five-user test by end of week.”

Specific, grounded, and ends with one clear next step.
Fig.02A real session, unedited
In-app · assistant
Design ThinkingClaude
Design Thinking
Let's put Design Thinking to work on your challenge. Before we generate any ideas, I want to make sure we're solving the right problem — that's the most common failure mode in innovation. Tell me: what's the challenge you're working on, and do you have any observations or research about the people you're designing for? Even rough notes or interview impressions are useful at this stage.
We're trying to improve onboarding for our B2B software. Customers sign up, get a product tour, and then we see huge drop-off in the first two weeks. We've done a few customer interviews but I'm not sure what to do with what we heard.
Perfect — drop-off after a tour is a classic symptom of a Define problem: the product is explaining itself rather than helping users make progress on something they care about. Before we jump to solutions, let's run your interview data through the Empathize phase. Share what you heard — even paraphrased quotes or your impressions of what customers said, thought, did, or felt during those first two weeks. I'll help you build an empathy map and pull out the latent needs beneath the surface complaints.
Most customers said the tour was 'fine' but they struggled to figure out how to do their first real task. One person said 'I knew what the buttons did but I didn't know where to start.' Another mentioned that they needed to pull in a colleague to help configure it, which felt like a blocker. A few said they went back to their old spreadsheet while waiting for their IT team.
Those observations are gold — and they're pointing to something more specific than 'bad UX.' Let me map this out:
Empathy Map:- Says: 'The tour was fine' / 'I didn't know where to start' / 'I needed someone else to configure it'- Does: Returns to old spreadsheet; pulls in colleague; waits for IT- Thinks: (implied) 'I understand the features but I can't see how this fits my workflow'- Feels: Stuck, dependent on others, uncertain whether the investment is worth it
The tension here is between feature comprehension (tour worked) and job-to-be-done clarity (they can't see how to make progress on their actual work). The 'first task' isn't defined for them.
Based on this, here's a draft POV statement:
'A new B2B customer needs to achieve a meaningful first outcome in their actual workflow, because understanding product features doesn't create momentum — completing a real job does.'
Does this capture what you're seeing? Or is there a user segment or job-to-be-done I should adjust?
Yes, that's exactly it. They know what the product does but don't feel like they've actually done anything with it yet.
Good — let's lock that POV and move into Define → Ideate. I'll generate a How Might We question bank from your POV, at a few different levels of abstraction:
Narrow (close to the surface problem):- HMW help new users identify and complete their first meaningful task in under 30 minutes?- HMW remove the configuration blocker so users don't need IT to make their first outcome happen?
Mid-range:- HMW make the user's existing workflow the entry point instead of the product tour?- HMW design onboarding around job completion milestones rather than feature exposure?
Expansive:- HMW make the first two weeks feel like wins rather than a learning curve?- HMW onboard the team, not just the individual signing up?
For an Ideate session, I'd recommend the mid-range questions — they're specific enough to generate actionable ideas but broad enough to avoid locking in a solution too early. Want me to run a structured brainstorm against one of these, using SCAMPER or analogical stimulus to push past obvious answers?
Let's brainstorm on 'make the user's existing workflow the entry point.' That one feels most interesting.
Great choice — it reframes onboarding from 'teach the product' to 'serve the job.' Here are 10 ideas generated across divergent techniques:
Direct (SCAMPER — Substitute): Replace the generic tour with a 'what are you trying to do this week?' onboarding wizard that configures the product around the user's stated task.
Adapt (analogical — from gym onboarding): Like a personal trainer who starts with your fitness goal before showing you equipment, assign a 'first outcome coach' who guides the user through one real task on day one.
Eliminate: Remove the product tour entirely; show only the one screen relevant to the user's first declared job.
Build on others (from TurboTax): Import the user's existing data (spreadsheet, CRM export) so their actual work is already in the product on arrival — the first task is already partially done.
Amplify: Make the first milestone visible company-wide ('Acme Corp just completed their first workflow!') to create social accountability.
Reverse: Instead of teaching users the product, have power users record 30-second 'how I did my first task' videos by role — and play those instead of a feature tour.
Constrain: Lock all other features for 48 hours and only unlock them after the user completes one defined first-outcome task.
Let's evaluate the top candidates against desirability, feasibility, and viability — or I can generate a prototype brief for the one that excites you most. Which direction do you want to go?
Reply to Design Thinking
What the skill is doing
01POV Statement Synthesis
02How Might We Question Bank
03Empathy Map Builder
Fig.03The same skill, in the channel you already use
WhatsApp · live
9:41
DTDesign Thinkingtyping…
Messages are end-to-end encrypted. No one outside of this chat can read them.
Today
We're trying to improve onboarding for our B2B software. Customers sign up, get a product tour, and then we see huge drop-off in the first two weeks.…9:14✓✓
Let's put Design Thinking to work on your challenge.9:14
Before we generate any ideas, I want to make sure we're solving the right problem — that's the most common failure mode in innovat…9:15
Tell me: what's the challenge you're working on, and do you have any observations or research about the people you're designing fo…9:15
Message

The same skill, where the work happens.

No new app to learn. The methodology runs over the WhatsApp Business API, so the answer lands as a reply in the thread you’re already in — same rigour, zero context-switch.

Reads the situation, names the pattern, returns one concrete next move.
Delivered in seconds, inside a conversation that already exists.
Specimen · WhatsApp Business API · live
Capabilities

What it does, specifically.

Each capability is a distinct move drawn straight from the source methodology — not a generic assistant guessing.

CapabilityC-01

POV Statement Synthesis

Transforms messy empathy notes, interview transcripts, or observations into a single, actionable Point-of-View statement. The POV anchors the entire project by naming the specific user, their unmet need, and the underlying insight that makes this need surprising or important. A sharp POV prevents the team from chasing the wrong solution space.

Based on Brown and the d.school's 'User / Need / Insight' POV template — the canonical output of the Define phase in IDEO's framework.
CapabilityC-02

How Might We Question Bank

Reframes the POV statement as a set of How Might We (HMW) questions that open possibility rather than close it. The skill generates multiple framings at different levels of abstraction — some narrow, some broad — so teams can choose an ideation aperture that suits their constraints.

HMW questioning is a signature Define-to-Ideate bridge tool developed at IDEO and formalized in the d.school curriculum, designed to make problem reframing a collaborative, generative act.
CapabilityC-03

Empathy Map Builder

Takes raw field notes, interview quotes, or user observations and organizes them into a structured empathy map — what the user Says, Thinks, Does, and Feels. This reveals gaps between stated preferences and actual behavior, which is where the best design opportunities live.

Based on IDEO's HCD toolkit empathy mapping templates, which are a standard Empathize-phase synthesis tool for identifying latent needs beneath surface-level observations.
CapabilityC-04

Structured Ideation Facilitator

Runs a text-based divergent ideation session using Design Thinking's brainstorming rules (defer judgment, build on ideas, go for quantity) combined with structured stimulus techniques including SCAMPER and analogical thinking. The skill generates idea prompts calibrated to the HMW question, then helps the team converge on a prioritized shortlist.

Encodes Brown's Ideate phase rules from 'Change by Design,' including the explicit separation of divergent (generative) and convergent (evaluative) thinking to prevent premature closure.
CapabilityC-05

Prototype Brief Generator

Produces a structured brief specifying what prototype artifact to build, what specific question it must answer, what fidelity is needed, and how to recruit and run a test session. This prevents over-building and keeps prototypes focused on the single most important uncertainty.

Based on Brown's 'build to think' principle and IDEO's prototype-scoping practice: every prototype should answer exactly one question about desirability, feasibility, or viability — not validate a fully formed solution.
CapabilityC-06

Desirability / Feasibility / Viability Evaluator

Assesses a set of candidate ideas or a proposed solution against Brown's three-lens evaluation framework. The skill surfaces the tension points — ideas that score high on desirability but low on feasibility, or viable but not desirable — and guides prioritization decisions accordingly.

Directly implements Brown's core Design Thinking evaluation triangle, the primary decision tool used by IDEO to determine which ideas are worth prototyping and in what sequence.
Tested

Graded before it shipped.

Every skill is scored against independent scenarios for methodology fidelity before it goes live — not vibes, a rubric.

What it produces
OutputD-01

Point-of-View Statement

A single precision-written sentence in 'User / Need / Insight' format that anchors your project to a real human need. Functions as a filter for every subsequent decision: does this idea serve this POV?

OutputD-02

How Might We Question Bank

A ranked list of reframed problem questions, from narrow to expansive, ready to use as Ideate phase prompts in a team workshop or solo brainstorm.

OutputD-03

Empathy Map

A structured four-quadrant synthesis of user Says / Thinks / Does / Feels, with key tensions and latent needs called out — the primary Define-phase input for POV writing.

OutputD-04

Prioritized Idea Shortlist

A scored matrix of candidate ideas evaluated against desirability, feasibility, and viability, with a recommended prototype candidate and rationale.

OutputD-05

Prototype Brief

A one-page specification: what to build, what single question it must answer, what fidelity is appropriate, and a test plan with suggested participant profile and feedback prompts.

The source

Grounded in the original work.

Every answer traces back to a real source and the practitioner who wrote it — not a secondhand summary. Here is the source of record.

Source authorA-01

Tim Brown

Tim Brown is the CEO and president of IDEO, the global design and innovation firm credited with pioneering human-centered design. He is the author of 'Change by Design' (2009) and wrote the landmark 2008 Harvard Business Review article 'Design Thinking' that brought the methodology to mainstream business audiences worldwide. His TED talks on design thinking have been viewed millions of times, and he co-founded the Stanford d.school (Hasso Plattner Institute of Design) curriculum that now trains engineers, MBAs, and designers in the framework.

Status · Inspired by Tim Brown’s work — not yet claimed. Are you Tim Brown?
Primary sourceS-01

Change by Design (2009) and 'Design Thinking' Harvard Business Review (2008)

by Tim Brown

CEO of IDEO; author of 'Change by Design'; landmark 2008 HBR article; co-founder of Stanford d.school curriculum; TED speaker with millions of views.

Read the original ↗
Citationideo.com
In the build queue

Be first to run it.

Design Thinking is being built right now. Leave your email and we’ll tell you the moment it goes live.

Notify meEmail
At launchI have a design challenge and some user research, but I'm not sure if I'm solving the right problem. Can we start with the Empathize phase — I'll share my interview notes and you help me turn them into an empathy map and POV statement?