This image was lost some time after publication.

The problem with "17 mistakes startups make," is that the guy behind them, John Osher didn't make that many. He started Dr. John's SpinBrush and sold it to Proctor & Gamble for $475 million. Jonathan Tang, who writes "Diary of a Failed Startup," not only founded a company, GameClay, he actually failed because of his mistakes. His advice on how to not be like him, pared down to 100 words, below.

  • Solve a problem, not a class of problems. It's okay to not have your product do everything, as long as it does something well. Many platforms started that way. Linux, The web, Rails Django, PHP.
  • Set things up so you get that rush of accomplishment as you finish things. Pick a problem that's worth addressing and doesn't require a lot of support code to address it.
  • I'd read the initial idea wasn't important. Thing is, the initial idea determines how the initial idea will change. An example is the choice to go into gaming at all. Out of college, that was what we were familiar with and passionate about. But gaming is overcrowded.
  • Developing in a vacuum never works. Prove yourself wrong as soon as possible.
  • Have a product that is useful on its own. Del.icio.us, for example - it's just a bookmark manager that happens to be more useful as more people use it.
  • Prototype any 3rd-party libraries.
  • If you're doing anything other than building your project and getting users, it's premature.
  • The product will take longer than you expect.
  • People have an incentive not to crush your dreams. Take everything they say with a grain of salt.
  • Know your limitations. Apple, or Sun, or Google — founders of those companies concentrated on the areas that they were experts in.

(Photo by dierken)