Let’s begin with the time period “agent” itself. Proper now, it’s being slapped on every little thing from easy scripts to classy AI workflows. There’s no shared definition, which leaves loads of room for firms to market primary automation as one thing rather more superior. That sort of “agentwashing” doesn’t simply confuse prospects; it invitations disappointment. We don’t essentially want a inflexible commonplace, however we do want clearer expectations about what these programs are imagined to do, how autonomously they function, and the way reliably they carry out.
And reliability is the following large problem. Most of at this time’s brokers are powered by giant language fashions (LLMs), which generate probabilistic responses. These programs are highly effective, however they’re additionally unpredictable. They’ll make issues up, go off monitor, or fail in delicate methods—particularly once they’re requested to finish multistep duties, pulling in exterior instruments and chaining LLM responses collectively. A latest instance: Customers of Cursor, a preferred AI programming assistant, have been advised by an automatic help agent that they couldn’t use the software program on a couple of machine. There have been widespread complaints and experiences of customers canceling their subscriptions. Nevertheless it turned out the policy didn’t exist. The AI had invented it.
In enterprise settings, this sort of mistake may create immense injury. We have to cease treating LLMs as standalone merchandise and begin constructing full programs round them—programs that account for uncertainty, monitor outputs, handle prices, and layer in guardrails for security and accuracy. These measures will help be certain that the output adheres to the necessities expressed by the person, obeys the corporate’s insurance policies relating to entry to data, respects privateness points, and so forth. Some firms, together with AI21 (which I cofounded and which has obtained funding from Google), are already shifting in that path, wrapping language fashions in additional deliberate, structured architectures. Our newest launch, Maestro, is designed for enterprise reliability, combining LLMs with firm knowledge, public data, and different instruments to make sure reliable outputs.
Nonetheless, even the neatest agent gained’t be helpful in a vacuum. For the agent mannequin to work, totally different brokers must cooperate (reserving your journey, checking the climate, submitting your expense report) with out fixed human supervision. That’s the place Google’s A2A protocol is available in. It’s meant to be a common language that lets brokers share what they will do and divide up duties. In precept, it’s an awesome concept.
In apply, A2A nonetheless falls brief. It defines how brokers discuss to one another, however not what they really imply. If one agent says it could possibly present “wind situations,” one other has to guess whether or not that’s helpful for evaluating climate on a flight route. With no shared vocabulary or context, coordination turns into brittle. We’ve seen this downside earlier than in distributed computing. Fixing it at scale is way from trivial.
