Softlander Book a call
Agent-to-agent interoperability

Agent message-schema governance

Control message changes without breaking agent interactions

Multiple teams add fields or change message meanings independently. The decision is how to control message changes without breaking agent interactions. The work begins with your actual workflow and looks for the evidence that separates intended behaviour from a consequential exception. It is particularly relevant to protocol platform teams and schema owners. A useful outcome is an explicit account of what was examined, what remains uncertain, and which decision the evidence can support.

Book a 30 minute readiness callBrowse this capability group

The interaction contracts relationship

  1. Starting evidenceSchema registries

    Establish the basis for schema owner.

  2. Decision boundaryChange category

    Distinguish compatible additions from semantic changes.

  3. Decision artefactMessage governance proposal

    Retain the scoped finding and its unresolved dependencies.

Proposed working model. Untested peers require their own compatibility evidence.

Decision

Frame the decision around schema owner

Questions and the evidence they need

Criterion / evidenceSchema owner
Inspect schema registries for the relevant constraint or observation.
Criterion / evidenceChange category
Inspect consumers for the relevant constraint or observation.
Criterion / evidenceMigration case
Inspect version policies for the relevant constraint or observation.
Read each criterion against the available evidence before deciding that additional work is needed.

The decision is how to control message changes without breaking agent interactions. This is relevant to protocol platform teams and schema owners when multiple teams add fields or change message meanings independently. Name the affected workflow, the consequence of a wrong decision, and the owner who can act on the result. The initial discussion should establish which evidence is already available and which uncertainty is material enough to investigate.

The specific failure hypothesis is that a field retains its name but changes its units or business interpretation. It remains a hypothesis until examined in the deployment. Existing internal tests or operating records may already resolve it; identify the uncovered question before commissioning additional work.

Mechanism

Schema evolution should preserve consumer meaning

Relationships within interaction contracts

Source or conditionSchema owner
Assign definition and validation responsibility.
Crossing or choiceChange category
Distinguish compatible additions from semantic changes.
Consequence or decisionMigration case
Exercise old and new consumers with retained examples.
Compare authority and state at the receiving boundary. Each relationship needs evidence in the actual scope.

What this specialty examines

Schema governance covers meaning as well as structural validation. Assign ownership to message types and define how fields evolve. Names, units, optionality and business definitions should be documented together so a syntactically compatible change does not silently alter behaviour.

The review should review schema ownership, validation, evolution rules and consumer compatibility. Identify the normal route, relevant exceptions and the authoritative record of the outcome. Inspect the relevant business-system record, enforcement event or process evidence alongside any reported status. Keep incomplete cases visible, with an explanation of what their absence prevents the owner from concluding.

The tradeoff to make explicit

For this decision, strict schemas improve predictability while extensions need a controlled evolution path. Compare the available design or operating choices against the same intended outcome. If one option removes a required control or changes the task boundary, describe that difference before treating its apparent simplicity, speed or lower effort as an improvement. The decision should expose the tradeoff instead of burying it in an aggregate score.

Preparation

Connect the working inputs to the boundary being examined

Evidence packet for schema owner

Illustrative working format

BasisSchema registries
Match this description to the deployed or proposed boundary being examined.
ContextConsumers
Check its relationship to the relevant workflow and expose missing context.
ObservationVersion policies
Confirm the applicable revision and who resolves disputed interpretation.
DependencyMessage examples
Keep expected behaviour and the limits of the constructed example explicit.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with schema registries, consumers, version policies and message examples. Identify the owner, revision and operating context of each source. Sanitised examples may support initial design, but differences from actual conditions should remain explicit. Where direct access is unsuitable, a customer-controlled evidence or execution route may be considered, with agreed handling and retention.

The scope also needs the integration owner, agreed expectations for a representative interaction case, and the authority to inspect the relevant boundary. Specify what evidence would distinguish the failure in which a field retains its name but changes its units or business interpretation from acceptable behaviour. If stakeholders disagree about intended behaviour, resolve the interpretation before classifying the observed difference as a defect.

How the work proceeds

Carry schema owner through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsSchema registries

    Agree the task meaning at the sending boundary.

  2. Examine the relationshipChange category

    Apply the scoped check to migration case.

  3. Retain the findingMessage governance proposal

    Record the evidence, open dependencies, and the owner’s next decision.

Proposed sequence; resolve interpretation or access gaps before relying on the next step.

Fix the interaction contract and versions

Assemble schema registries, consumers, version policies and message examples with protocol platform teams and schema owners. Identify the participating implementations, interface revisions, authority assumptions and intended business result. Prepare messages and task-state examples from both sides, including an interrupted exchange and a disputed or incomplete outcome. The preparation output is a paired contract fixture showing what each participant expects and which differences would prevent the workflow from completing correctly.

Run and compare both sides of the exchange

Review changes against known consumers and representative cases. Distinguish additive fields from changed interpretation or state semantics. Keep migration and deprecation decisions traceable, including the period during which different versions coexist. Retain paired examples of old and new messages so reviewers can see the intended interpretation change alongside the schema diff.

Choose the contract or integration change

Summarise the comparison in a message governance proposal with change categories and migration cases. Classify each mismatch as interface validation, business meaning, identity, task state or operating behaviour. Decide whether to change a participant, add an explicit adapter rule, narrow supported combinations or defer the connection. Validate the affected pair again and preserve limitations that translation cannot resolve, especially around cancellation, authority and partial completion.

Indicative artefact

Make the message governance proposal usable by its owner

Message governance proposal

Illustrative working format

Annotated fieldMessage governance proposal
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldChange categories
Link supporting and contrary observations to inspectable evidence.
Annotated fieldMigration cases
Name the unresolved condition, next action, and accountable owner.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is a message governance proposal with change categories and migration cases. Supporting material may include selected cases, configuration or process records, evidence references, a disagreement log and prioritised actions. Retain the case selection rationale and material disagreements alongside the result; otherwise the result may be mistaken for complete coverage.

Illustrative scenario

Examine migration case through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationSchema owner

    A field keeps its name while its business interpretation changes.

  2. Question to examineChange category

    Test old and new field interpretations using retained consumer fixtures.

  3. Conditional next actionMigration case

    Treat a meaning change as a governed migration rather than a cosmetic edit.

Fictional example. No executed test, customer engagement, or measured outcome is implied.

Consider a fictional situation: an agent’s priority field changes from urgency to business importance while consumers still route using the old meaning. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For the priority field, preserve the old meaning or introduce an explicit new concept with migration guidance. A consumer routing by urgency should not receive business importance under the same undocumented assumption. The correction is semantic, not merely a parser change.

Scope and next action

Keep the conclusion within named implementations and revisions

Confirm fit before the next commitment

Included boundarySchema owner
This review is limited to named implementations and revisions.
PrerequisiteSchema registries
The relevant owner must confirm access and the intended operating conditions.
Claim limitMessage governance proposal
Untested peers require their own compatibility evidence.
Bring the triggering change and existing evidence; resolve the dependency that could alter the decision.

Compatibility is assessed for named implementations, versions, features and workflows. It does not establish universal conformance, vendor endorsement or interoperability with untested peers. Any engagement depends on an agreed scope, qualified team, authorised access and confirmed availability. Bring the affected workflow, its current configuration or process, the triggering change and the evidence already available. The immediate scope question is prompted by the situation in which multiple teams add fields or change message meanings independently; confirm which missing observation would change the owner’s next action.

Ways to engage

Related engagement scopes

AI Agent Protocol Interoperability Lab

Find where connected agents disagree. Exercise message contracts, identity propagation and failure recovery across your selected integrations.

Read about this offer

Continue exploring

Related insights and resources

Evaluation & assurance6 MIN READ

How to design a joint AI evaluation lab

A joint lab should be a governed way to create decision evidence across organisations, with shared methods but explicit ownership of systems, data and conclusions.

Agent security6 MIN READ

Agent protocols are creating a new control surface

Protocols make tools and agents interoperable, but they also standardise discovery, delegation and context exchange. Those interfaces need explicit trust and policy controls.

Agent security6 MIN READ

A practical security review for an MCP server

Review an MCP server as a privileged protocol adapter: verify tool semantics, OAuth boundaries, token audience, downstream delegation, input handling, isolation, logging and consent.

A little more clarity

Questions to consider.

Start with the questions that shape a better decision.

Is backward-compatible JSON enough to preserve business meaning?

No. Structural compatibility does not establish unchanged units, status meaning or business interpretation. Govern semantic changes and test representative consumer behaviour alongside schema validation.

Which schema records preserve business meaning?

Start with schema registries, consumers, version policies and message examples. Record their revision, owner and relationship to the intended workflow. Missing context should be identified before interpreting outcomes; a sanitised fixture is useful only when its relevant differences from the operating case are understood.

How should consumer compatibility be reviewed after change?

Review schema ownership, validation, evolution rules and consumer compatibility. Compare both participants' accepted inputs, task states and results under a named interface revision. Include interrupted or delayed interactions. Parser acceptance should not be treated as agreement about business meaning, authority or completion.

What belongs in a message governance policy?

The proposed output is a message governance proposal with change categories and migration cases. Include the selected conditions, supporting observations, unresolved differences and next decision. A reviewer should be able to follow each important conclusion back to its evidence and understand the limits without depending on an undocumented explanation from the author.

When does an additive field still require migration?

An additive field needs migration when consumers interpret it, defaults change or business meaning shifts. Schema acceptance alone does not establish that existing behaviour remains correct.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from protocol platform teams and schema owners may already be sufficient. In that case, capture the decision, unresolved limitations and the change that would require another review. Additional assessment should address a real gap.

What would make the findings inconclusive?

Missing schema registries, consumers, version policies and message examples can prevent a reliable interpretation, depending on the case. Record the specific missing observation and its implication. The owner can supply evidence, narrow the claim or defer the dependent decision; an incomplete case should not silently be counted as a pass.

Start with the decision you need to make.

Tell us about the agent workflow you want reviewed, and where you need greater clarity. Scope and availability are confirmed together.

Book a 30 minute readiness call Get the agent release checklist

Connected disciplines

Protocol authentication review

Verify who is connecting through an agent protocol. The review connects issuer configuration, audience expectations, peer identity rules and transport setup to a bounded review of agent interaction contracts, giving the integration owner a clearer basis for the next action.

Protocol authorisation review

Define what an authenticated agent may request through a protocol. The review connects task action catalogues, peer roles, resource scopes and enforcement records to a bounded review of agent interaction contracts, giving the integration owner a clearer basis for the next action.

Trust negotiation between agents

Establish what evidence is required before agents rely on each other. The review connects trust policies, identity evidence, capability attestations and exception handling to a bounded review of agent interaction contracts, giving the integration owner a clearer basis for the next action.