← All 186 courses
AI-313 AI & Data

Agent Interoperability: A2A & Cross-Agent Protocols

Make agents built by different teams and different vendors cooperate safely: capability discovery, task delegation and negotiation, and identity that survives crossing an organisational boundary. Learners wire two independently built agents together over an agent-to-agent protocol, contain a runaway delegation loop, and trace a single user intent end to end across a multi-vendor mesh.

B5Advanced
5modules
35skill atoms
2role journeys
Curriculum

What this course covers.

5 modules, 35 named skill atoms. Expand any module to see them.

1The Interop Problem7 skill atoms
agent silos across vendors and teamsMCP for tools vs A2A for peersagent cards and capability advertisementdiscovery registriesprotocol version negotiationsynchronous vs long-running task shapeswhen a plain API beats a protocol
2Task Delegation and Negotiation7 skill atoms
task lifecycle and terminal statesstructured artifacts as task outputstreaming progress over SSEclarification and input-required turnscost and deadline negotiationpartial result handovercancellation semantics
3Identity and Trust Between Agents7 skill atoms
workload identity vs end-user identityOAuth token exchange and delegated scopeson-behalf-of chains and audience claimsmTLS between agent servicescapability scoping to least privilegeprompt injection crossing an agent boundaryallowlists and signed agent cards
4Failure Containment Across Boundaries7 skill atoms
cycle detection in delegation graphshop-count and depth limitsper-agent token and cost budgetstimeout and circuit breaker per peeridempotency keys on delegated taskspoison-task quarantinedegraded fallback to a single agent
5Observability of an Agent Mesh7 skill atoms
W3C trace context propagated across agentsOpenTelemetry GenAI span conventionscorrelation ID per user intentcost attribution per agent and tenantreplay of a cross-agent transcriptSLOs on delegated task completiontriage across vendor boundaries
Where it fits

AI-313 in the role journeys.

This course appears in 2 of our 45 role journeys. Here is what a learner takes immediately before and after it in each.

Agentic AI Engineer

Capstone stage
AI-510AI-313journey complete

AI Architect

Capstone stage
AI-305AI-313journey complete

Roles this course serves

The capability ladder

This course is authored to band B5.

Every course we run is written to one rung of the CASI ladder, so a plan can be assembled to take a team from where they are to where they need to be.

What do B1–B6 mean?The CASI Capability Ladder — click to expand

Every course targets a band on the CASI Capability Ladder — our six-band proficiency scale, anchored to open standards (O*NET, ESCO, NICE, NIST AI RMF, Bloom's). A band tells you how deep a course goes, and what evidence proves it.

What the learner can doTypical evidence
B1
AwareUnderstands concepts and vocabulary; uses tools with guidance
Knowledge checks
B2
FoundationPerforms standard tasks correctly in familiar contexts
Guided labs, autograded exercises
B3
PractitionerDelivers complete pieces of work independently
Scenario labs, proctored hands-on exams
B4
ProfessionalHandles production-grade complexity, trade-offs and failure modes
Break-fix drills, design defenses
B5
AdvancedEngineers systems end-to-end under constraints; leads others
Rubric-scored capstones, vivas
B6
ExpertSets direction; recognised authority across teams
Portfolio + panel evaluation

A note on B6. Courses in this catalog target B1–B5. B6 is not taught — it is recognised, through a portfolio and a panel, once someone is setting direction for others. Every journey here is built to land a learner at B5.

Next step

Run AI-313 for your team.

This course runs at several lengths depending on how deep you need to go and how much of it your people already have. Tell us who is being trained and we will scope it.

Add it to a training plan Talk to our team Check your team’s level free