Collaborative Agents

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.

Figure 1. Collaboration is aligning independent deciders on one aim. Shared intent points everyone roughly the same way; communication and common knowledge are what let them converge on a single joint plan rather than several incompatible 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.

Key idea

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."

The series, end to end

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.

What it means in practice

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.

Handbook application: from concept to controlled practice

Purpose. This expanded section turns the original page into a practical handbook. It preserves the supplied material and adds a repeatable way to apply, check and review Collaborative Agents. It does not replace a contract, legislation, a controlled standard, competent engineering judgement or specialist advice.

The operating aim is to convert the subject into a governed decision, owned work, usable evidence and a reviewable outcome. Read the original explanation first, then use the workflow and checks below to convert knowledge into evidence.

Use Collaborative Agents as a decision instrument rather than an administrative form. The subject terms—shared, objective, coordination, common, knowledge—need an explicit connection to the project objective, business value and stakeholder commitments. Before completing the artefact, write one sentence stating who will use it, what decision it supports and when that decision is required.

Apply a disciplined information model. Separate facts supported by evidence, forecasts derived from a method, assumptions awaiting validation, constraints that limit choice, risks that may occur, issues that already exist and actions assigned to people. Each material entry should have an owner, date, status and next review point. Where probability or impact scores are used, define the scale so different reviewers interpret it consistently.

A baseline is useful only when changes are visible. Give the artefact an identifier, version, approval state and effective date. Define which changes require reapproval, how superseded versions are retained and where supporting evidence is stored. During reviews, focus on exceptions, decisions and trends rather than reading every field aloud. Record the decision and rationale, not merely that a meeting occurred.

Close the loop beyond delivery. Confirm acceptance criteria, unresolved items, transferred responsibilities and operational ownership. Where benefits are expected, identify the outcome measure, baseline, target, observation period and owner who remains accountable after the project team disbands. Lessons should describe the condition, consequence and reusable action; a generic statement such as “communicate better” cannot improve the next project.

Step-by-step operating method

Clarify the decision. Name the outcome, sponsor, affected stakeholders and decision that this work must enable.
Set boundaries. Record scope, assumptions, constraints, dependencies, tolerances and escalation conditions.
Plan the evidence. Define deliverables, measures, owners, due dates and acceptance criteria before execution.
Control delivery. Compare actual performance with the baseline, assess changes and manage risks and issues explicitly.
Close the loop. Confirm acceptance, transfer ownership, capture lessons and track benefits beyond handover.

Completion and governance protocol

Start with a short drafting workshop involving the accountable owner and the people who hold the evidence. Complete high-consequence fields first: objective, scope, owner, baseline, acceptance, dependencies and escalation. Mark unknowns as assumptions or actions rather than hiding them behind vague prose. Circulate a review draft, resolve conflicting interpretations, baseline the approved version and place the next review date in an owned schedule.

Information type	Minimum useful content	Review test
Outcome	Observable change and intended recipient	Not merely a deliverable or activity
Measure	Definition, baseline, target, frequency and source	Two reviewers would calculate it the same way
Ownership	One accountable role plus contributors and approver	Authority matches responsibility
Uncertainty	Assumption, risk or issue with response and trigger	Status reflects current reality
Control	Version, approval, review date and change rule	Current baseline is identifiable

Common failure modes and recovery actions

1. Watch for

Producing a document with no named decision or accountable owner.

Recovery: Return to the governing definition or requirement and restate the decision in one sentence.

2. Watch for

Mixing risks, current issues, assumptions and actions in one unstructured list.

Recovery: Separate evidence from assumption, assign an owner and set a date for validation.

3. Watch for

Measuring activity or output while leaving the intended outcome undefined.

Recovery: Run a small counterexample, boundary test, pilot or independent check before proceeding.

4. Watch for

Accepting changes without evaluating effects on value, scope, schedule, cost and risk.

Recovery: Record the consequence, decision and rationale, then update the controlled baseline.

5. Watch for

Closing the project at delivery even though benefit ownership has not transferred.

Recovery: Escalate when the issue affects safety, compliance, acceptance, material value or an agreed tolerance.

Review checklist

Which decision or commitment does this artefact support?
Who owns each action, risk, acceptance and post-project benefit?
What is the baseline and what variance triggers escalation?
Where is the evidence that the result was accepted and transferred?
Are mandatory requirements distinguished from recommendations and illustrative values?
Are sources, assumptions, units, dates and versions recorded closely enough to reproduce the decision?
Have safety, legal, ethical, stakeholder and operational consequences been considered at the appropriate level?
Is there a named owner and a trigger for review, escalation, change or retirement?

Questions for deeper application

What is the most important distinction a practitioner must preserve when applying Collaborative Agents?