I was a manager at Microsoft for about 18 years and for quite a bit of it I was a ‘manager of managers’, which means I often spent time working with my team on how to properly handle annual rewards. I’m no longer at Microsoft, but I drafted this up back in 2021, so I thought I would try to finish it and get it live.

The TL;DR; of all of those discussions could be distilled down into “Rewards are a way to send a message to your team, what message do you want to send?”.

Small side note… At Microsoft folks often refer to managers as either M1, M2, or M3. I heard these terms for years without having any idea what they meant, until I became a M2 and it made sense. M1 is a manager with ICs (Individual Contributors or non-managers) under them, M2 is a manager of managers, and a M3 is a manager of managers of managers. This can continue up I assume, but M3 is where I was for the past few years, although I am now a M2. This could be a common term at other companies, but for me it was a mystery for a bit.

What are rewards? #

Depending on your particular company, employees will be rewarded with some mix of

  • a raise to their base pay
  • a bonus
  • some type of equity (stock grants or stock options)

This is often an annual event, but it could be more frequent. I could write pages on the difference between those three kinds of rewards and why you would increase/decrease one vs. another, but for the purpose of this article I believe we can just lump them all together as ‘rewards’.

There is a limited amount of money for each year’s rewards, so like any budgeting exercise the manager must decide how to distribute funds across their team. How much money there is in total is, like the types of rewards above, not particularly relevant to this discussion. We can go super simple here and imagine a situation where we had ten employees and a total rewards budget of one hundred dollars.

We could give every employee the same reward, ten dollars, or we could give one employee one hundred dollars and the other nine nothing. Assume there are no restrictions. Now, with our problem space defined, we are in the same spot as most managers. How do we determine the rewards for everyone?

Consider the message #

As an employee, you might not have much visibility into this process, you just know that last year you received a certain set of rewards and now you are about to find out this year’s. Looking at it from this point of view is critical.

If the amount is lower, you will feel like your manager (or your company) thinks you did a worse job than last year. If it is higher, they must feel you did a better job.

That is it. That is the key to understanding how this year’s rewards will be received. You can make this as complicated as you want, trying to quantify their impact and determine exactly what they did (and you should be able to document and explain their greater or lower impact to the team/company), but in the end you will be sending a message. They will receive that message no matter what other feedback you have delivered over the year. If you tell me I did awesome, but give me lower rewards, then I know you think I did not do as well as last year. If you tell me I had less impact this year and need to improve, but then give me increased rewards, I will be very confused.

As a manager, I suggest you go through your team many times, first assessing their impact (at Microsoft we explicitly liked to look at this as a holistic discussion, did they deliver on their work, did they help their peers or other teams, etc.), and then going back and considering the message you are sending. The two should line up. This is not suggesting that you make sure you are rewarding someone more than last year. Their rewards should be completely determined by the impact they had on the team this year, but if you want to know how these rewards will be received then look to see if it is more, less, or about the same as last year. In my experience, about the same is seen as ’less’ because people expect to see at least some increase year over year. The degree of difference matters as well, a little bit up or down is sending less of a message than a significant increase.

Peanut-buttering #

Most new managers immediately say to me ‘but everyone did a great job, can’t I just give them all high rewards?’. Given a fixed budget, what this will do is give them all the middle of the possible reward range. I heard this referred to once as ‘peanut buttering’ and that name has stuck with me for years, spreading the rewards equally across the team. There is a positive to this, treating the team like a real team, that rises and falls together, but only if the rewards budget is tied to the team’s impact. If more money is available when the team has done highly impactful work than when they do just ‘good’ work, everyone will be rewarded more when the team delivers. ‘A rising tide lifts all boats’. If, on the other hand, the rewards available are fixed, then equally distributing the rewards each year just means that everyone gets medium rewards all the time. To go back to the point of this article, what message does that send?

Using our earlier example of 100 dollars for 10 team members, if the 100 dollars is fixed, we give out equal rewards that is 10 dollars for everyone. Next year, the team really pulls together and ships an impressive set of features… and we give them 10 dollars again. Do you think they will be happy? I am honestly not sure, if I understood that my salary and rewards were fixed when I signed up, then I might be ok with this. It does remove rewards as a motivator to deliver more impact though, and while that is not everyone’s only motivation, it is part of it for most people.

Either way though, if you feel everyone did exactly as good a job (adjusting for their seniority, we should not expect the same things out of a year-one team member as the experienced lead), then equal rewards is the right answer. That is not usually the case though, some people have a more positive or negative impact on the team and the results than others, and we should make sure their rewards reflect that. It is also worth noting that at Microsoft, I would not have been allowed to give out equal rewards to the whole team, some differentiation between high and low performers was required.

High rewards for some require cuts to others #

This is where it starts to get hard though. Remember that we have a fixed total budget. So, if one person really contributed more to the team, and we want to reward them appropriately, that decreases the amount of money left for everyone else. But what if everyone else also did better than last year, but just not as good as that one person?

You may end up having to give them lower rewards, just to make the budget work out. Now you are not sending the message you want. With companies, such as Microsoft, getting rid of annual raises and/or decreasing bonuses, this is going to happen a lot. Everyone at these tech jobs is still being paid very well, but if there is slight change year over year, they will feel like they are doing poorly. If you factor inflation into this, they are having their compensation reduced, although I do not feel like inflation impacts high earners as much as most people.

Promotions as a proxy for rewarding high impact #

Ok, so we want to reward someone for their contributions, but if we give them super high rewards, we will have to give other people less than we feel they deserve. It is a tricky situation, and it can lead some managers to consider a promotion as a form of reward. The employee will feel recognized, they will get some amount of compensation boost, and often promos are part of a different budget than the individual ratings we give out. So, it will work, but is it the right thing to do? Promotions are about impact, but they are also about capability. We promote someone from a junior to a senior, not just because they did some excellent work, but because we feel they are contributing like a senior employee. For me, that means being very self-directed, able to break up and drive larger bodies of work, and most importantly to be able to guide other members of the team to produce better results. If an employee meets all the criteria for a higher level, it is perfectly reasonable to use that promotion as part of their recognition for the year; we must work with the budget we have after all. Ideally, they would also get a high rating for their impact because that would be accurate, but you could shoot a little lower knowing that they will be happy with the promotion. It is not perfect, but it happens.

What you should never do, is promote someone who is not ready for a higher level, just as a replacement for a regular performance reward.

At that point, you have created a problem for them, in that they will be judged in the future against criteria they are not ready to meet, and a problem for your team in that they are seeing someone in a senior role that does not seem to be playing that role. This can happen right at the time someone is hired, the interview process determines they are not ready to be a senior, but meeting their salary expectations requires that level. Personally, I wish salary ranges and titles were decoupled, but that would be a hard system to manage.

What does it all mean? #

My conclusion from all of this is not some clear guideline on how to reward employees, but that this type of review process has many fundamental flaws, so the goal is to work within it as best you can. Recognize the right people based on the results they produced, manage people’s levels based on their demonstrated behaviors, and reward everyone as fairly as you can.

While I do think one improvement would be to shift the budget based on the impact delivered by the whole team (therefore raising the pool of rewards for everyone on a high impact team), the danger would be that critical, but low visibility, teams doing operations, long-term maintenance, etc. would be unfairly penalized.

If anyone else has a better plan, you should author a book, and try to get it onto the desk of upper management at all these companies.