Customer Development
No business plan survives first contact with customers.
Customer Development is Steve Blank's four-step methodology for discovering and validating the market for a new product before wasting resources building the wrong thing. Designed for early-stage founders, intrapreneurs, and product managers, it replaces assumption-driven roadmaps with a structured, hypothesis-testing process grounded in direct customer conversations. Unlike generic 'talk to customers' advice, it provides specific frameworks for what to test, how to interpret what you hear, and when to pivot versus press forward.
“We're building a project management tool for architecture firms. I think the customer is the project manager or principal at small firms, 5–20…”
Stop building what nobody wants — get out of the building and find out first
Customer Development runs four sequential steps in parallel with product development: (1) Customer Discovery — founders 'get out of the building' (GOOB) to personally test problem, solution, and business model hypotheses through structured interviews, deliberately NOT selling; (2) Customer Validation — the team attempts to sell to a small group of 'earlyvangelists' to prove a repeatable, scalable sales process exists; (3) Customer Creation — proven demand is scaled into the sales channel, with strategy differentiated by market type (new, existing, re-segmented, or clone); (4) Company Building — the startup formalizes into a company, shifting from learning mode to execution mode. Each step produces specific artifacts: a tested Business Model Canvas, prioritized interview findings, an earlyvangelist profile, a validated sales script, and a demand-creation playbook. Pivot-or-proceed decision gates at the end of Discovery and Validation prevent teams from scaling a broken model.
Founders default to 'product development' mode — writing code, hiring, and spending — based on assumptions they've never tested with real customers. By the time a product launches, months of work are already locked into decisions that real customers would have invalidated on day one. The result is the most common startup failure pattern: a technically functional product that the market doesn't want.
Run your business model assumptions through a structured discovery process before committing to them. Come away with an interview script, a prioritized hypothesis list, and a clear pivot-or-proceed framework — so you spend the next month learning what's real, not building what isn't.
- Your current startup or product idea with its core assumptions
- Any existing customer conversations, user research, or market observations
- A sense of which step of Customer Development you're currently in (or stuck on)
- Willingness to have your hypotheses stress-tested rather than validated by default
- A prioritized list of business model hypotheses mapped to the Business Model Canvas, ranked by risk
- A ready-to-use Customer Discovery interview script that tests problems without pitching solutions
- An earlyvangelist profile defining the specific early adopter most likely to buy your unfinished product
- A structured pivot-or-proceed decision based on your interview findings, with explicit criteria for each path
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.
“You've been coding for three months on a project management tool for architecture firms, based on your own experience at one firm. You have strong conviction about the problem but no external customer interviews. Your roadmap is built on 15 assumptions you've never tested — who the buyer is, whether they'll pay, whether they've already solved it with Procore or Newforma. You have four customer calls on the calendar and you're planning to demo the prototype.”
“Before those four calls, you've replaced the planned demo with a structured learning conversation. Each call surfaces whether the submittal/RFI chaos is widespread, who actually owns the pain, and whether firms are actively seeking a solution. After 12 interviews, you discover that the real decision-maker is the firm owner, not the PM, and that half the firms you interviewed already use Newforma — but hate it. That's a re-segmentation opportunity, not a new market. You pivot your positioning and earlyvangelist profile before writing another line of code.”
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.
What it does, specifically.
Each capability is a distinct move drawn straight from the source methodology — not a generic assistant guessing.
Hypothesis Canvas Builder
Surfaces and structures all the assumptions embedded in your business model — customer segments, value propositions, channels, revenue streams, and more — by mapping them onto the Business Model Canvas. Each hypothesis is ranked by how much risk it carries if wrong, giving you a clear order of attack before you walk out the door.
Customer Discovery Interview Script
Builds a structured interview guide designed to learn, not pitch. Questions probe whether the problem is real, how customers currently solve it, and what they've already tried — without contaminating answers by mentioning your solution. Includes an opening script, ranked problem probes, and a wrap-up to assess willingness to pay.
Earlyvangelist Profiling
Identifies the specific type of early customer who has the problem acutely, has already tried to solve it, has a budget, and has enough authority to buy an unfinished product. Earlyvangelists are the linchpin of Customer Validation — without finding them, there is no one to sell to in Step 2.
Pivot-or-Proceed Decision Gate
Analyzes your Customer Discovery interview results against Blank's explicit pass/fail criteria and helps you decide whether to advance to Customer Validation or loop back to re-test revised hypotheses. Structures the decision around evidence, not founder optimism or investor pressure.
Market Type Classifier
Determines whether your startup is entering a new market, an existing market, a re-segmented market (low-cost or niche), or cloning a proven model from another geography. Market type determines the correct Customer Creation strategy in Step 3 and shapes the appropriate competitive positioning, sales cycle length, and marketing spend profile.
Graded before it shipped.
Every skill is scored against independent scenarios for methodology fidelity before it goes live — not vibes, a rubric.
Business Model Hypothesis Scorecard
A ranked list of every major assumption in your business model mapped to the Business Model Canvas, with a risk score (high/medium/low) and a specific interview question to test each one. Gives you a prioritized research agenda before your first customer conversation.
Customer Discovery Interview Script
A ready-to-use, non-selling interview guide with an opening framing, problem-probing questions, and a closing sequence — structured so the customer does the talking and you do the learning. Includes annotation guidance for capturing signals during the conversation.
Earlyvangelist Profile Card
A one-page profile of your ideal first customer, defined by the five earlyvangelist criteria: job title or segment, the specific pain they feel, the workaround they're currently using, and their ability to act as an internal champion to unlock a purchase decision.
Pivot-or-Proceed Analysis
A structured summary of what your discovery interviews confirmed, contradicted, or left uncertain — with a clear recommendation to pivot (revise hypotheses and re-test), proceed (move to Customer Validation), or pause (not enough data). Includes the specific evidence behind the recommendation.
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.
Steve Blank
Steve Blank is a Silicon Valley serial entrepreneur who founded or co-founded eight startups, including E.piphany (IPO, 1999). He developed the Customer Development methodology from hard-won experience across those companies and codified it in 'The Four Steps to the Epiphany' (2003). He has taught entrepreneurship at Stanford, UC Berkeley Haas, Columbia, and NYU, and his framework is the foundation of the NSF I-Corps program — the U.S. government's initiative to commercialize scientific research, through which thousands of teams have been trained.
The Four Steps to the Epiphany
Serial entrepreneur (8 startups including E.piphany IPO); adjunct professor at Stanford, Berkeley Haas, Columbia, and NYU; architect of the NSF I-Corps national entrepreneurship training program.
Be first to run it.
Customer Development is being built right now. Leave your email and we’ll tell you the moment it goes live.