Agent-to-agent interoperability

Cross-vendor agent integration

Integrate agents from different vendors around one accountable workflow

A vendor-specific agent must work with an existing platform. The decision is how to integrate agents from different vendors around one accountable workflow. 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 enterprise integration leads and product owners. A useful outcome is an explicit account of what was examined, what remains uncertain, and which decision the evidence can support.

The interaction contracts relationship

  1. Starting evidenceVendor interface documentation

    Establish the basis for portable task.

  2. Decision boundaryAdapter responsibility

    Map identity, state, and errors at each boundary.

  3. Decision artefactCross-vendor integration design

    Retain the scoped finding and its unresolved dependencies.

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

Decision

Frame the decision around portable task

Questions and the evidence they need

Criterion / evidencePortable task
Inspect vendor interface documentation for the relevant constraint or observation.
Criterion / evidenceAdapter responsibility
Inspect task contracts for the relevant constraint or observation.
Criterion / evidenceExit dependency
Inspect identity requirements 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 integrate agents from different vendors around one accountable workflow. This is relevant to enterprise integration leads and product owners when a vendor-specific agent must work with an existing platform. 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 vendor adapter translates successful transport into a success state without verifying business completion. 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

Cross-vendor integration needs a shared handoff contract

Relationships within interaction contracts

Source or conditionPortable task
Choose a representative business interaction.
Crossing or choiceAdapter responsibility
Map identity, state, and errors at each boundary.
Consequence or decisionExit dependency
Identify data and evidence that must remain portable.
Compare authority and state at the receiving boundary. Each relationship needs evidence in the actual scope.

What this specialty examines

Cross-vendor integration should keep the business contract outside vendor-specific assumptions where practical. Define task ownership, accepted results, authority and evidence retention. An adapter should have explicit responsibilities rather than silently repairing every difference between products.

The review should prototype the smallest representative handoff and evaluate state, errors, permission and evidence portability. 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, using specialized vendors may improve fit while proprietary assumptions increase integration and exit effort. 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 portable task

Illustrative working format

BasisVendor interface documentation
Match this description to the deployed or proposed boundary being examined.
ContextTask contracts
Check its relationship to the relevant workflow and expose missing context.
ObservationIdentity requirements
Confirm the applicable revision and who resolves disputed interpretation.
DependencyExit constraints
Identify provenance and the specific decision this material can inform.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with vendor interface documentation, task contracts, identity requirements and exit constraints. 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 vendor adapter translates successful transport into a success state without verifying business completion 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 portable task through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsVendor interface documentation

    Agree the task meaning at the sending boundary.

  2. Examine the relationshipAdapter responsibility

    Apply the scoped check to exit dependency.

  3. Retain the findingCross-vendor integration design

    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 vendor interface documentation, task contracts, identity requirements and exit constraints with enterprise integration leads and product 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

Prototype a narrow representative exchange before broad commitment. Examine failure handling, data export, identity mapping and observability. Vendor demonstrations can suggest capability, but the customer’s actual workflow needs its own evidence and operational owner.

Choose the contract or integration change

Summarise the comparison in a cross-vendor integration design with adapter responsibilities and unresolved dependencies. 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 cross-vendor integration design usable by its owner

Cross-vendor integration design

Illustrative working format

Annotated fieldCross-vendor integration design
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldAdapter responsibilities
Name the role, decision right, handoff, and unresolved ownership boundary.
Annotated fieldUnresolved dependencies
Name the missing evidence, responsible owner, and condition for revisiting the decision.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is a cross-vendor integration design with adapter responsibilities and unresolved dependencies. 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 exit dependency through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationPortable task

    A remote vendor reports completion before the customer's required state exists.

  2. Question to examineAdapter responsibility

    Compare remote completion with the customer's authoritative task state.

  3. Conditional next actionExit dependency

    Assign adapter or acceptance changes before relying on the handoff.

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

Consider a fictional situation: a service-desk agent delegates an inventory check to another vendor’s agent with different status conventions. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For the inventory check, compare what each vendor means by available and complete. If one returns a preliminary result, the adapter should preserve that qualification. Converting it into final success would create a business-state error rather than solve compatibility.

Scope and next action

Keep the conclusion within named implementations and revisions

Confirm fit before the next commitment

Included boundaryPortable task
This review is limited to named implementations and revisions.
PrerequisiteVendor interface documentation
The relevant owner must confirm access and the intended operating conditions.
Claim limitCross-vendor integration design
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 a vendor-specific agent must work with an existing platform; 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: AI Agent Protocol Interoperability Lab

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.

What should remain under the customer's control in a vendor integration?

Retain accountable business rules, evidence access, identity decisions and realistic exit options where required. Vendor-specific adapters may remain useful, but their responsibilities and dependencies should be explicit.

Which vendor contracts define the handoff outcome?

Start with vendor interface documentation, task contracts, identity requirements and exit constraints. 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 cross-vendor task state be validated?

Prototype the smallest representative handoff and evaluate state, errors, permission and evidence portability. 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 an integration dependency map?

The proposed output is a cross-vendor integration design with adapter responsibilities and unresolved dependencies. 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 should customer-owned logic remain outside an adapter?

Keep authoritative business rules and approval decisions outside an adapter when vendor translation should not own or silently change them. The adapter can carry context while the accountable system retains the decision.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from enterprise integration leads and product 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 vendor interface documentation, task contracts, identity requirements and exit constraints 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.

Connected disciplines