The series began with a single decision-maker putting a number on a belief. It ends with many decision-makers — who all want the same thing — trying to act as one. That, it turns out, is its own hard problem.
When agents share a common goal, the adversarial tension of earlier chapters falls away, but a different challenge remains: coordination. Even parties who genuinely want the same outcome can fail to achieve it if they don't align their actions — and aligning independent decision-makers, each acting on their own view, is the final piece of decision-making under uncertainty.
1Wanting the same thing isn't enough
The surprising lesson of collaborative settings is that shared intent does not guarantee shared action. There are often several equally-good joint plans, and the agents must somehow agree on which — a problem of equilibrium selection. Two teams both waiting for the other to move, two workstreams each assuming the other owns an interface, two partners both holding back a decision pending the other's: none of this requires conflicting goals. It only requires a failure to coordinate on one plan among several good ones.
2What makes alignment work
Two ingredients turn shared intent into coordinated action. Communication lets agents exchange what they see and intend, collapsing the ambiguity about which plan everyone will follow. And common knowledge — not just that everyone knows the plan, but that everyone knows that everyone knows — is what makes a joint plan self-enforcing: I commit to my part because I'm confident you're committing to yours, and you're confident of the same about me. Establishing that shared, mutually-understood picture is the real work of coordination, and it's why explicit alignment beats hopeful assumption.
Shared goals do not produce shared action on their own. Independent decision-makers still have to converge on one joint plan among many — and communication plus common knowledge is what carries them from "we all want the same thing" to "we're all doing the same thing."
We began with a single decision-maker learning to represent uncertainty as probability, and we end with many decision-makers learning to align. Along the way: quantifying belief and choosing well (Part I); deciding across time (Part II); learning the odds while acting (Part III); acting on beliefs about an unseen state (Part IV); and reasoning among others who decide too (Part V). One thread runs through all twenty-six chapters — how do I decide well when I cannot see the whole board? — and the answer has steadily grown from a single rational choice into a coordinated one.
Most project failures among willing partners are coordination failures, not conflicts of interest — everyone wanted success and still missed each other. Guard against it deliberately: over-communicate intent, make ownership of every interface unambiguous, and build genuine common knowledge of the plan so each party acts confident the others are acting too. When several good ways forward exist, the job isn't finding the best one in the abstract — it's getting everyone to commit to the same one, together.