My response to "Should I spend X hours on this?"

Yesterday, a client wrote me with this question. She discovered a bug in a CiviCRM extension, and the extension author has given her an hourly estimate of “5-6 hours” to fix it.

So she asked me:

I’m not sure if we want to spend this many hours on this. What are your thoughts?

Here’s my response, edited lightly for a more general audience:

Hello [dear client],

It's a good question — a great question, really!

Most importantly I would say: Don't get caught up in the number of hours here.

The more important question is to identify the business value of getting this fixed — which is probably equal to the business liability of not fixing it.

In other words, how painful is it to just leave this alone as it is? How often does this problem come up? What does it cost you (e.g. user goodwill, lost event fees, staff time, etc.) on average, each time it happens? You may not know exactly, but you might be able to make some kind of rough estimate of this cost.

If that cost is greater than what you'd pay to get it fixed, then you've got a good business case to fix it.

If it's not, then you have a good business case to just leave it alone and deal with any related problems as they comes up.

One more thing:

Hourly estimates are notoriously fuzzy. He may get it done in 5-6 hours as he said, or it may be less, or it may go over. If it would help you by reducing uncertainty, I'd be happy to make sure he fixes it for a fixed total price equivalent to his 8 hours, whether it takes more than that or not. This might be a desirable way for you to reduce the risks of additional cost if it should go far over the estimate.

I hope this helps! Let me know if you have more questions.

Thanks,
Allen