Not like conventional AI fashions that reply to single prompts (like ChatGPT’s primary Q&A mode), AI brokers can plan, purpose, and execute multi-step duties by interacting with instruments, knowledge sources, APIs, and even different brokers.
Sounds summary? That’s as a result of it’s. Whereas most would possibly agree with this definition or expectation for what agentic AI can do, it’s so theoretical that many AI brokers accessible at this time wouldn’t make the grade.
As my colleague Sean Falconer famous lately, AI brokers are in a “pre-standardization part.” Whereas we’d broadly agree on what they ought to or may do, at this time’s AI brokers lack the interoperability they’ll have to not simply do one thing, however truly do work that issues.
Take into consideration what number of knowledge methods you or your functions have to entry every day, akin to Salesforce, Wiki pages, or different CRMs. If these methods aren’t presently built-in or they lack appropriate knowledge fashions, you’ve simply added extra work to your schedule (or misplaced time spent ready). With out standardized communication for AI brokers, we’re simply constructing a brand new kind of knowledge silo.
Regardless of how the business modifications, having the experience to show the potential of AI analysis into manufacturing methods and enterprise outcomes will set you aside. I’ll break down three open protocols which can be rising within the agent ecosystem and clarify how they may aid you construct helpful AI brokers—i.e., brokers which can be viable, sustainable options for advanced, real-world issues.
The present state of AI agent improvement
Earlier than we get into AI protocols, let’s evaluation a sensible instance. Think about we’re occupied with studying extra about enterprise income. We may ask the agent a easy query through the use of this immediate:
Give me a prediction for Q3 income for our cloud product.
From a software program engineering perspective, the agentic program makes use of its AI fashions to interpret this enter and autonomously construct a plan of execution towards the specified purpose. How it accomplishes that purpose relies upon completely on the checklist of instruments it has entry to.
When our agent awakens, it would first seek for the instruments below its /instruments listing. This listing could have guiding recordsdata to evaluate what’s inside its capabilities. For instance:
/instruments/checklist
/Planner
/GenSQL
/ExecSQL
/Decide
You can too take a look at it based mostly on this diagram:
Confluent
The primary agent receiving the immediate acts as a controller. The controller has discovery and administration capabilities and is chargeable for speaking immediately with its instruments and different brokers. This works in 5 basic steps:
- The controller calls on the planning agent.
- The planning agent returns an execution plan.
- The decide critiques the execution plan.
- The controller leverages GenSQL and ExecSQL to execute the plan.
- The decide critiques the ultimate plan and supplies suggestions to find out if the plan must be revised and rerun.
As you possibly can think about, there are a number of occasions and messages between the controller and the remainder of the brokers. That is what we’ll discuss with as AI agent communication.
Budding protocols for AI agent communication
A battle is raging within the business over the correct technique to standardize agent communication. How can we make it simpler for AI brokers to entry instruments or knowledge, talk with different brokers, or course of human interactions?
At present, we’ve Mannequin Context Protocol (MCP), Agent2Agent (A2A) protocol, and Agent Communication Protocol (ACP). Let’s check out how these AI agent communication protocols work.
Mannequin Context Protocol
Mannequin Context Protocol (MCP), created by Anthropic, was designed to standardize how AI brokers and fashions handle, share, and make the most of context throughout duties, instruments, and multi-step reasoning. Its client-server structure treats the AI functions as purchasers that request info from the server, which supplies entry to exterior assets.
Let’s assume all the info is saved in Apache Kafka subjects. We will construct a devoted Kafka MCP server, and Claude, Anthropic’s AI mannequin, can act as our MCP consumer.
In this instance on GitHub, authored by Athavan Kanapuli, Akan asks Claude to hook up with his Kafka dealer and checklist all of the subjects it incorporates. With MCP, Akan’s consumer software doesn’t have to know entry the Kafka dealer. Behind the scenes, his consumer sends the request to the server, which takes care of translating the request and operating the related Kafka operate.
In Akan’s case, there have been no accessible subjects. The consumer then asks if Akan want to create a subject with a devoted variety of partitions and replication. Identical to with Akan’s first request, the consumer doesn’t require entry to info on create or configure Kafka subjects and partitions. From right here, Akan asks the agent to create a “nations” matter and later describe the Kafka matter.
For this to work, you could outline what the server can do. In Athavan Kanapuli’s Akan venture, the code is within the handler.go file. This file holds the checklist of capabilities the server can deal with and execute on. Right here is the CreateTopic instance:
// CreateTopic creates a brand new Kafka matter
// Non-compulsory parameters that may be handed by way of FuncArgs are:
// - NumPartitions: variety of partitions for the subject
// - ReplicationFactor: replication issue for the subject
func (okay *KafkaHandler) CreateTopic(ctx context.Context, req Request) (*mcp_golang.ToolResponse, error) {
if err := ctx.Err(); err != nil {
return nil, err
}
if err := okay.Consumer.CreateTopic(req.Subject, req.NumPartitions, req.ReplicationFactor); err != nil {
return nil, err
}
return mcp_golang.NewToolResponse(mcp_golang.NewTextContent(fmt.Sprintf("Subject %s is created", req.Subject))), nil
}
Whereas this instance makes use of Apache Kafka, a broadly adopted open-source expertise, Anthropic generalizes the tactic and defines hosts. Hosts are the massive language mannequin (LLM) functions that provoke connections. Each host can have a number of purchasers, as described in Anthropic’s MCP structure diagram:
Anthropic
An MCP server for a database could have all of the database functionalities uncovered by means of the same handler. Nonetheless, if you wish to turn out to be extra refined, you possibly can outline present immediate templates devoted to your service.
For instance, in a healthcare database, you would have devoted capabilities for affected person well being knowledge. This simplifies the expertise and supplies immediate guardrails to guard delicate and personal affected person info whereas making certain correct outcomes. There may be far more to study, and you may dive deeper into MCP right here.
Agent2Agent protocol
The Agent2Agent (A2A) protocol, invented by Google, permits AI brokers to speak, collaborate, and coordinate immediately with one another to resolve advanced duties with out frameworks or vendor lock-in. A2A is expounded to Google’s Agent Improvement Package (ADK) however is a definite part and never a part of the ADK bundle.
A2A ends in opaque communication between agentic functions. Which means interacting brokers don’t have to reveal or coordinate their inner structure or logic to alternate info. This offers completely different groups and organizations the liberty to construct and join brokers with out including new constraints.
In observe, A2A requires that brokers are described by metadata in identification recordsdata often known as agent playing cards. A2A purchasers ship requests as structured messages to A2A servers to devour, with real-time updates for long-running duties. You possibly can discover the core ideas in Google’s A2A GitHub repo.
One helpful instance of A2A is this healthcare use case, the place a supplier’s brokers use the A2A protocol to speak with one other supplier in a distinct area. The brokers should guarantee knowledge encryption, authorization (OAuth/JWT), and asynchronous switch of structured well being knowledge with Kafka.
Once more, take a look at the A2A GitHub repo should you’d wish to study extra.
Agent Communication Protocol
The Agent Communication Protocol (ACP), invented by IBM, is an open protocol for communication between AI brokers, functions, and people. In line with IBM:
In ACP, an agent is a software program service that communicates by means of multimodal messages, primarily pushed by pure language. The protocol is agnostic to how brokers operate internally, specifying solely the minimal assumptions essential for easy interoperability.
For those who check out the core ideas outlined within the ACP GitHub repo, you’ll discover that ACP and A2A are related. Each have been created to remove agent vendor lock-in, velocity up improvement, and use metadata to make it straightforward to find community-built brokers whatever the implementation particulars. There may be one essential distinction: ACP permits communication for brokers by leveraging IBM’s BeeAI open-source framework, whereas A2A helps brokers from completely different frameworks talk.
Let’s take a deeper take a look at the BeeAI framework to know its dependencies. As of now, the BeeAI venture has three core elements:
- BeeAI platform – To find, run, and compose AI brokers;
- BeeAI framework – For constructing brokers in Python or TypeScript;
- Agent Communication Protocol – For agent-to-agent communication.
What’s subsequent in agentic AI?
At a excessive degree, every of those communication protocols tackles a barely completely different problem for constructing autonomous AI brokers:
- MCP from Anthropic connects brokers to instruments and knowledge.
- A2A from Google standardizes agent-to-agent collaboration.
- ACP from IBM focuses on BeeAI agent collaboration.
For those who’re occupied with seeing MCP in motion, take a look at this demo on querying Kafka subjects with pure language. Each Google and IBM launched their agent communication protocols solely lately in response to Anthropic’s profitable MCP venture. I’m wanting to proceed this studying journey with you and see how their adoption and evolution progress.
Because the world of agentic AI continues to develop, I like to recommend that you simply prioritize studying and adopting protocols, instruments, and approaches that prevent effort and time. The extra adaptable and sustainable your AI brokers are, the extra you possibly can deal with refining them to resolve issues with real-world affect.
Adi Polak is director of advocacy and developer expertise engineering at Confluent.
—
Generative AI Insights supplies a venue for expertise leaders—together with distributors and different outdoors contributors—to discover and focus on the challenges and alternatives of generative synthetic intelligence. The choice is wide-ranging, from expertise deep dives to case research to knowledgeable opinion, but in addition subjective, based mostly on our judgment of which subjects and coverings will finest serve InfoWorld’s technically refined viewers. InfoWorld doesn’t settle for advertising collateral for publication and reserves the correct to edit all contributed content material. Contact [email protected].
