Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Agent2Agent Protocol (A2A)

developers.googleblog.com

Post reply on HN
Print view View original

271–280 of 293 posts

Re: The Agent2Agent Protocol (A2A)

#271

Post by atonse »

coredog64 wrote: post #67
rogerthis wrote: post #24

Looking at partners of this effort, I wonder what problems does A2A create to serve as a solution.

Partner list includes Accenture, Capgemini, Cognizant, HCL, InfoSys, KPMG, and Wipro. I think it’s fair to say that the generative capability of A2A is the generation of billable hours.

Yeah seeing that list is a red flag for me. Seems like a vehicle to attach their names to so those companies can pretend that they’re actually innovating in this space, rather than the usual mediocre services offerings.

Re: The Agent2Agent Protocol (A2A)

#272

Post by latentsea »

TeMPOraL wrote: post #243
Xelynega wrote: post #145

Earlier quoted context omitted.

Not only extends them, but compounds them because you have a non-deterministic human making changes to a non-deterministic computer system which is making changes to an existing computer system.

That's basically the problem of employing and managing people.

Yup. And this is why I think the "last mile" problem in AI is basically unsolvable.

Re: The Agent2Agent Protocol (A2A)

#273

Post by mellosouls »

thebytefairy wrote: post #245
a_wild_dandan wrote: post #161

Earlier quoted context omitted.

I suppose Google wants us to pretend that "agents" can't be "resources." MCP is already well established (Anthropic, OpenAI, Cursor, etc), so Google plastering their announcement with A2A endorsements just reeks of insecurity. I figure this A2A idea will wind up in the infamous Google graveyard within 8 months.

Creating new standards is not easy, largely because everyone has to agree that they will use this particular one. Plastering it with endorsements attempts to show that there is consensus and give confidence in adoption. If they didn't put them in, you'd instead say nobody is using or going to use this.

True, but look at those "partners"; most of them are lame BigCo/consultancy types with no history of technological innovation or collaboration, in fact generally anti.

The list is aimed at bureaucratic manager types (which may be the correct approach if they are generally the decision makers), its not a list that will impress engineers too much I think.

Re: The Agent2Agent Protocol (A2A)

#274

Post by kc10 »

jacobs123 wrote: post #103
zellyn wrote: post #3

It’s frustratingly difficult to see what these (A2A and MCP) protocols actually look like. All I want is a simple example conversation that includes the actual LLM outputs used to trigger a call and the JSON that goes over the wire… maybe I’ll take some time and make a cheat-sheet. I have to say, the endorsements at the end somehow made this seem worse…

It's shown in the link below. It's kind of crazy that they have this huge corporate announcement with 50 logos for something that under the hood seems sort of arbitrary and very fragile, and is probably very sensitive to things like exact word choice and punctuation. There will be effects like bots that say "please" and "thank you" to each other getting measurably better results. https://google.github.io/A2A/#/docume…

Can you please expand on this?

The sensitivity to prompts and response quality are related to an agent's functionality, A2A is only addressing the communication aspects between agents and not the content within.

Re: The Agent2Agent Protocol (A2A)

#275

Post by TS_Posts »

zellyn wrote: post #3

It’s frustratingly difficult to see what these (A2A and MCP) protocols actually look like. All I want is a simple example conversation that includes the actual LLM outputs used to trigger a call and the JSON that goes over the wire… maybe I’ll take some time and make a cheat-sheet. I have to say, the endorsements at the end somehow made this seem worse…

Hi there! If you load the CLI demo in the github repo (https://github.com/google/A2A/tree/main/samples/python/hosts...) you can see what the A2A servers are returning. Take a look!

Re: The Agent2Agent Protocol (A2A)

#276

Post by TS_Posts »

jacobs123 wrote: post #103
zellyn wrote: post #3

It’s frustratingly difficult to see what these (A2A and MCP) protocols actually look like. All I want is a simple example conversation that includes the actual LLM outputs used to trigger a call and the JSON that goes over the wire… maybe I’ll take some time and make a cheat-sheet. I have to say, the endorsements at the end somehow made this seem worse…

It's shown in the link below. It's kind of crazy that they have this huge corporate announcement with 50 logos for something that under the hood seems sort of arbitrary and very fragile, and is probably very sensitive to things like exact word choice and punctuation. There will be effects like bots that say "please" and "thank you" to each other getting measurably better results. https://google.github.io/A2A/#/docume…

Hi there (I work on a2a) - can you explain the concern a bit more? We'd be happy to look.

A2A is a conduit for agents to speak in their native modalities. From the receiving agent implementation point of view, there shouldn't be a difference in "speaking" to a user/human-in-the-loop and another agent. I'm not aware of anything in the protocol that is sensitive to the content. A2A has 'Messages' and 'Artifacts' to distinguish between generated content and everything else (context, thoughts, user instructions, etc) and should be robust to formatting challenges (since it relies on the underlying agent).

Re: The Agent2Agent Protocol (A2A)

#277

Post by TS_Posts »

phillipcarter wrote: post #197

A key difference between MCP and A2A that is apparent to me after building with MCP and now reading the material on A2A: MCP is solving specific problems people have in practice today. LLMs need access to data that they weren't trained on, but that's really hard because there's a millions different ways you could RAG something. So MCP defines a standard by which LLMs can call APIs through clients. (and more). A2A sol…

Hi there (I work on a2a) - A2A works at a different level than MCP. We are working with partners on very specific customer problems. Customers are building individual agents in different frameworks OR are purchasing agents from multiple vendors. Those agents are isolated and do not share tools, or memory, or context.

For example, most companies have an internal directory and internal private APIs and tools. They can build an agent to help complete internal tasks. However, they also may purchase an "HR Agent" or "Travel Assistant Agent" or "Tax Preparation Agent" or "Facilities Control Agent". These agents aren't sharing their private APIs and data with each other.

It's also difficult to model these agents as structured tools. For example, a "Tax Preparation Agent" may need to evaluate many different options and ask for specific different documents and information based on an individual users needs. Modeling this as 100s of tools isn't practical. That's where we see A2A helping. Talk to an agent as an agent.

This lets a user talk to only their company agent and then have that agent work with the HR Agent or Travel Booking Agent to complete complex tasks.

Re: The Agent2Agent Protocol (A2A)

#278

Post by TS_Posts »

simonw wrote: post #121

OK, I have to ask: isn't this agents to agents idea kind of Science Fiction? I absolutely get the value of LLMs calling tools and APIs. I still don't see much value in LLMs calling other LLMs. Everyone gets really excited about it - "langchain" named their whole company over the idea of chaining LLMs together - but aside from a few niche applications (Deep Research style tools presumably fire off a bunch of sub-promp…

Hi there (I work on a2a) - reposting from above.

We are working with partners on very specific customer problems. Customers are building individual agents in different frameworks OR are purchasing agents from multiple vendors. Those agents are isolated and do not share tools, or memory, or context.

For example, most companies have an internal directory and internal private APIs and tools. They can build an agent to help complete internal tasks. However, they also may purchase an "HR Agent" or "Travel Assistant Agent" or "Tax Preparation Agent" or "Facilities Control Agent". These agents aren't sharing their private APIs and data with each other.

It's also difficult to model these agents as structured tools. For example, a "Tax Preparation Agent" may need to evaluate many different options and ask for specific different documents and information based on an individual users needs. Modeling this as 100s of tools isn't practical. That's where we see A2A helping. Talk to an agent as an agent.

This lets a user talk to only their company agent and then have that agent work with the HR Agent or Travel Booking Agent to complete complex tasks when they cannot be modeled as tools.

Re: The Agent2Agent Protocol (A2A)

#279

Post by TS_Posts »

a_wild_dandan wrote: post #161
mellosouls wrote: post #133

How it claims to complement/differentiate from MCP here: https://google.github.io/A2A/#/topics/a2a_and_mcp Basically (google claims): MCP enables agents to use resources in a standard way. A2A enables those agents to collaborate with each other.

I suppose Google wants us to pretend that "agents" can't be "resources." MCP is already well established (Anthropic, OpenAI, Cursor, etc), so Google plastering their announcement with A2A endorsements just reeks of insecurity. I figure this A2A idea will wind up in the infamous Google graveyard within 8 months.

Hi there (I work on a2a) - reposting from above.

We are working with partners on very specific customer problems. Customers are building individual agents in different frameworks OR are purchasing agents from multiple vendors. Those agents are isolated and do not share tools, or memory, or context.

For example, most companies have an internal directory and internal private APIs and tools. They can build an agent to help complete internal tasks. However, they also may purchase an "HR Agent" or "Travel Assistant Agent" or "Tax Preparation Agent" or "Facilities Control Agent". These agents aren't sharing their private APIs and data with each other.

It's also difficult to model these agents as structured tools. For example, a "Tax Preparation Agent" may need to evaluate many different options and ask for specific different documents and information based on an individual users needs. Modeling this as 100s of tools isn't practical. That's where we see A2A helping. Talk to an agent as an agent.

This lets a user talk to only their company agent and then have that agent work with the HR Agent or Travel Booking Agent to complete complex tasks when they cannot be modeled as tools.

Re: The Agent2Agent Protocol (A2A)

#280

Post by TS_Posts »

bryan_w wrote: post #216
chipgap98 wrote: post #122

They are pitching this as complementary to the MCP [0], but I don't see it. What is the value in agents communicating in agents as opposed to just treating other agents as tools? [0]: https://google.github.io/A2A/#/topics/a2a_and_mcp

They are thinking about Enterprises. Shirley from accounting isn't going to install an mcp service to pull the receipt photos from Dropbox and upload them to SAP/Concur (expense reimbursement)

Yes, that is our assumption. reposting from above:

We are working with partners on very specific customer problems. Customers are building individual agents in different frameworks OR are purchasing agents from multiple vendors. Those agents are isolated and do not share tools, or memory, or context.

For example, most companies have an internal directory and internal private APIs and tools. They can build an agent to help complete internal tasks. However, they also may purchase an "HR Agent" or "Travel Assistant Agent" or "Tax Preparation Agent" or "Facilities Control Agent". These agents aren't sharing their private APIs and data with each other.

It's also difficult to model these agents as structured tools. For example, a "Tax Preparation Agent" may need to evaluate many different options and ask for specific different documents and information based on an individual users needs. Modeling this as 100s of tools isn't practical. That's where we see A2A helping. Talk to an agent as an agent.

This lets a user talk to only their company agent and then have that agent work with the HR Agent or Travel Booking Agent to complete complex tasks when they cannot be modeled as tools.

Post reply on HN