Main Takeaway- Continuous Experimentation Well Beyond The Startup Stage
Contrary to the generally held belief that lean startup principles advice experiments in early stages of a startup; many speakers at the conference showed how they are experimenting continuously at all stages of their ventures.
Eric Ries in said that “Product market fit and experimentation is not a one time activity. It’s a continuous flow of activities. There are no discrete big jumps! Think of these steps in continuous flow that lend themselves to go back if an experiment fails”
Hiten Shah of Kissmetrics reiterated that a meaningful metric leads to a hypothesis and then to an experiment to validate it. Startups should always be A/B testing. Empirically 1 out of 5 tests succeed. Strive to win 1.67 out of 5.
A/B testing can help not only at different stages of a startup; but also for various activities including website traffic, app installs, welcome emails, Web/Mobile onboarding, E-mail digests, Triggered notifications, dormant/churned users.
Des Traynor also said that having continuous feedback is more valuable than one time event driven feedback.
Experiments helped even established brands like Rally, Google and Vox Media to validate hypotheses at later stages of their product lifecycle
- Rally launched a dummy brand waffle.io targeted towards developers to protect the parent brand from the impressions created by the experiments. Finally Rally decided to have both brands.
- Google Adsenses team validated Partner Problems using Lean Startup Principles. Blair Beverly said that they faced problem with new projects scaling too early and failing as they lacked historical data to go by. He got coworkers at Google ad senses team to use the Lean Startup. They scheduled office time to read the book, being helpful and not pushy. They also gave them a reading guide with questions. In the end they identified three hypotheses; put together templates like the partner problem hypothesis. People felt good about invalidating their own hypotheses as it saved them work that would’ve been wasted.
- Vox Media launched Vox.com in 9 weeks using analytics to guide customer validation. Melissa Bell got her co founders and others from Vox media in the same room to get everyone on the same page about her vision. Many editorial staff came from Washington Post whereas Vox was an agile technology company. They used card stacks for flexibility. They had problems with the way editors used card stacks, as it was difficult to navigate-hence they analytics were used to solve the problem. Now Vox.com has 22m users. Delivering content to users where they are-on social channels such as Facebook or YouTube instead of own URL.
Lean Startup- Dos & Don’ts
- Pivoting statistics- 80% of failures didn’t pivot, 65% of successes Pivoted but 85% of Huge Successes (>$1B exit) didn’t pivot. Those didn’t pivot felt that evolution is safer than betting on intelligent design.
- You need to eat your own dog food. Use your product to solve your own problems. If not you are at an enormous disadvantage.
- Invert the org chart :customers & customer facing team should be on top. They should be heard and not told what to do.
- Force yourself to pretend at the earliest possible moment what you want to be- to learn whether its worth being what you want to be. Landing pages, Concierge or Wizard of Oz are ways to pretend.
- Don’t speed up for the sake of it. For startups not going fast enough is not the main risk. False summit is the reality. Journey of a startup is slow like that of a mountaineer. A new goal appears once you have reached what seemed like the ultimate goal.
- According to Grace Ng success criterion for any experiment is the weakest outcome that will give you enough confidence to move forward.
- Testing the riskiest assumption on buy side in a two-sided market place could be deceptive in a sellers’ market. Sellers may not automatically follow even if you find many buyers.
- Validated hypothesis doesn’t necessarily lead to a viable business. Grace Ng tested a hypothesis whether birdwatchers will post photos to ask questions. The Hypothesis was valid but the problem turned out to be too small – not a big pain-point.
- Don’t validate the solution before validating the problem. As in the case above; the problem was not big enough though the solution was right.
- When it takes too long to learn as end results take time, use proxy metric like number of likes or start a cohort.
- Don’t depend on one experiment to determine the product market fit. Keep testing and validating along the way as you grow. Growing too fast by taking product-market fit for granted is dangerous.
- Don’t get misled by corporate America’s habit to underinvest or overinvest. “All Hands On Deck” sounds great but surely is a sign of overenthusiasm.
- Avoid handing off innovation between silos. Handoffs kill innovation. What is learnt in one silo can’t be handed off to another silo.
- Don’t add features for the sake of it. Its better to err on the side of being too minimal to get early feedback and learning. Its easy to add a missing feature later.
- Pay more attention to paid users’ feedback than free users’ feedback. Free users ask for more; paid users ask for better.
- Don’t use vanity metrics- Eric’s law: At any time no matter how badly you are doing there is at least one Google analytic graph that’s up into the right
- As you go through build-measure-learn cycles for product the same way you should be going thru build-measure-learn cycles for process compliance.
- Beware of developers’ tendency to focus on how to do things than on outcomes. Developers tend to ignore security as they are dazzled by technology, so they focus on doing things faster-not safer. Security testing, threat model and risk metrics should be included right from the beginning and not at the end.
- Don’t take idle pleasantries as positive feedback. People tend to be polite and cordial even though they are least interested.
- Don’t choose to see what fits in a narrative that sounds good and makes you look awesome. That is self-deception. Realize that a startup is a series of unpleasant encounters with reality.
- Don’t own a plan. Own questions. Plans will change.
- Test small changes- Google sign on and changes to verbiage improved acquisition by 314% for KissMetrics.
- Don’t as two questions that kill breakthrough innovation – what is the roi? When do we get it? In order to answer these questions we have to look at existing markets which kills innovation -innovator’s dilemma. We need to build cultures or safety net for innovators.
Most of the takeaways and dos and don’ts are common sense for any practicing entrepreneur. According to Eric Ries The Lean Startup process is more widely practiced than talked about. Most entrepreneurs are agents of long term change. They don’t think The Lean Startup is a big deal. As with most profound thoughts- it seems obvious after its well thought through, well organized and well presented.