Let’s begin with the time period “agent” itself. Proper now, it’s being slapped on the whole lot 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 way more superior. That form of “agentwashing” doesn’t simply confuse clients; it invitations disappointment. We don’t essentially want a inflexible commonplace, however we do want clearer expectations about what these programs are presupposed to do, how autonomously they function, and the way reliably they carry out.
And reliability is the subsequent large problem. Most of right this moment’s brokers are powered by massive language fashions (LLMs), which generate probabilistic responses. These programs are highly effective, however they’re additionally unpredictable. They will make issues up, go off monitor, or fail in delicate methods—particularly after 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 instructed by an automatic help agent that they couldn’t use the software program on a couple of system. There have been widespread complaints and reviews of customers cancelling their subscriptions. Nevertheless it turned out the coverage didn’t exist. The AI had invented it.
In enterprise settings, this type of mistake might create immense harm. 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 can assist be sure that the output adheres to the necessities expressed by the consumer, obeys the corporate’s insurance policies relating to entry to info, respects privateness points, and so forth. Some firms, together with AI21 (which I cofounded and which has acquired funding from Google), are already transferring in that course, wrapping language fashions in additional deliberate, structured architectures. Our newest launch, Maestro, is designed for enterprise reliability, combining LLMs with firm information, public info, 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, completely 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 ideal thought.
In observe, A2A nonetheless falls brief. It defines how brokers discuss to one another, however not what they really imply. If one agent says it might present “wind circumstances,” one other has to guess whether or not that’s helpful for evaluating climate on a flight route. With out a shared vocabulary or context, coordination turns into brittle. We’ve seen this downside earlier than in distributed computing. Fixing it at scale is much from trivial.
