… authorities of the folks, by the folks, for the folks …
— Abraham Lincoln, Gettysburg Tackle (1863)
The price of AI is dropping quickly. GPT-4-class capabilities value roughly $30 per million tokens in early 2023; immediately the identical runs underneath $1, and some suppliers are pushing prices under $0.10. Throughout benchmarks, inference costs have fallen between 9x and 900x per 12 months, with a median decline close to 50x. Even frontier fashions are getting dramatically cheaper every technology, with open-source fashions following carefully behind. And crucially, even when “Nobel-Prize-winning genius-level” intelligence isn’t right here but, the intelligence that suffices for the overwhelming majority of information work is right here immediately, and getting cheaper by the month. At this charge, we’re quickly coming into the period of nearly free intelligence—the sort that’s greater than sufficient for on a regular basis information work.
Disclosure: This publish is a perspective led by Aditya G. Parameswaran—an Affiliate Professor of EECS and co-director of the EPIC Knowledge Lab at UC Berkeley—collectively together with his collaborators. It’s half panorama survey and half perspective, and a number of other of the analysis instructions mentioned under (together with agentic hypothesis, structured reminiscence, and synthesizing customized knowledge programs from scratch) draw on the authors’ personal ongoing work.
So, what does this new period of near-free intelligence imply for knowledge programs? We consider three new challenges—and alternatives—stem from near-zero inference prices:
Knowledge Methods For Brokers. Brokers will quickly turn into the dominant workload for knowledge programs—with swarms of brokers spun up in response to every end-user request. Given variations in traits between brokers and people—or purposes performing on their behalf—how ought to we redesign knowledge programs for such agentic customers?
Knowledge Methods Of Brokers. As brokers begin taking over the majority of information work, a brand new substrate is required for 1000’s of brokers to handle state over long-running duties, coordinate and attain consensus, and take care of failures. What do knowledge programs that reliably and effectively run and handle agent swarms appear like?
Knowledge Methods By Brokers. Brokers are quickly changing into able to synthesizing whole knowledge programs in a single go—which means we are able to rebuild customized programs for every new workload. Verifying that such programs match supposed conduct is a problem. What does it take to let brokers synthesize knowledge programs we are able to truly belief?
Knowledge Methods For, Of, and By Brokers
Subsequent, we are going to talk about every in additional element, adopted by discussing the intertwined future of information programs and brokers, particularly because the three challenges intersect.
Knowledge Methods For Brokers
An agent querying a database doesn’t behave like an individual or a BI instrument. It performs what we name agentic hypothesis: a high-volume, heterogeneous stream of labor spanning schema introspection, columnar exploration, partial after which full question formulation. With a number of brokers every exploring parts of the speculation area, every person request might quantity to 1000s of particular person SQL queries. Now, customers can situation ‘high-level’ knowledge duties, e.g., root-cause evaluation—e.g., ‘why did espresso gross sales in Berkeley drop this 12 months’—or exploratory cohort evaluation—e.g., ‘which person segments are more than likely to churn subsequent quarter’—every involving a combinatorial area of potential joins, aggregations, and filter mixtures.
Knowledge Methods Redesigned to Extra Successfully Assist Agentic Hypothesis
The requests from these brokers have varied alternatives for optimization. For example, on a text-to-SQL benchmark with a number of brokers trying every process, solely 10-20% of the sub-plans are distinct. Thus, 80-90% of sub-queries carry out duplicate work. The identical experiments present process success charges considerably growing with extra agentic makes an attempt—so the redundancy is definitely useful. However from the info system perspective it’s wasted work.
An agent-first knowledge system can exploit such properties to assist brokers make progress quicker. It could reuse outcomes throughout overlapping sub-plans, drawing on concepts from decades-old literature on multi-query optimization and shared scans. Or the info system can attempt to satisfice, returning approximate solutions which are ok for brokers to make progress, leveraging work from the AQP literature—or streaming the outcomes of the ultimate or intermediate operators to assist brokers resolve if seeing the remainder is important or useful.
One other alternative right here is to rethink the question interface completely: as a substitute of brokers issuing a single SQL question at a time, they may as a substitute situation a batch of queries, every with its personal approximation necessities. Since enumerating an exponential search area (as within the root trigger or cohort evaluation examples above) isn’t a superb use of agentic reasoning skill, maybe knowledge programs ought to help higher-level primitives relatively than requiring brokers to record every SQL question explicitly. One thought right here is to attract on DBT-style Jinja macros to supply looping-based primitives for brokers to work together with knowledge programs.
A Caffeinated Military of Brokers Able to Tirelessly Full Your Knowledge Duties
A closing alternative right here is to cease considering of information programs as passive executors of queries; knowledge programs may very well be proactive, as they possess extra grounding in knowledge and system traits that brokers could lack a priori—they may steer brokers in numerous instructions, present outcomes for associated queries, and in addition present performance-level suggestions (e.g., as a substitute of executing an costly question, the system might first present the agent a latency estimate). The explanation we are able to do that now versus the previous is that an agent can settle for any type of textual suggestions and isn’t anticipating a strict SQL question consequence. In actual fact, the info system might additionally put together each materialized and digital views for an agent prematurely, offered to the agent as a part of context, as this can be cheaper or simpler than having an agent writer or use them.
Knowledge Methods Of Brokers
Beforehand, we centered on how brokers work together with knowledge programs. Now, we think about every part else brokers have to preserve working: the place they stay, how they keep in mind, how they coordinate with one another, and the way they take care of failures of one another. This agentic substrate is separate from the inference stack powering uncooked intelligence. Nonetheless, the inference stack itself is being abstracted away by way of APIs (e.g., from OpenAI or Anthropic), or, for open-weight fashions, by way of serving frameworks that cover low-level particulars. To this point, the agentic substrate has been managed by way of harnesses like Claude Code and Codex, coupled with varied mechanisms to retailer and retrieve reminiscence.
First, on the reminiscence entrance, the present knowledge is that information are all you want; brokers write to unstructured markdown (MD) information, which may then be searched utilizing grep, or by way of embedding-based retrieval. In actual fact, many argue that the answer to continuous studying is having brokers eat quite a bit (e.g., a complete codebase, slack, firm wikis, …) after which write their learnings into MD information, that are then retrieved selectively on demand. Certainly, file programs, bash scripting, and MD information are and can nonetheless be necessary for brokers. Nonetheless, at scale, when brokers are doing the overwhelming majority of information work, this method will now not be efficient.
Given restricted context home windows, retrieving all MD file fragments which may be related and stuffing it into the context will break down in some unspecified time in the future. Even when context home windows proceed to develop, there are latency advantages to not put all info into context — and in lots of instances, e.g., when information work entails interacting with massive databases or code bases, will probably be infeasible to serialize all related knowledge into context.
Knowledge Methods As A Substrate for Multi-Agent Swarms
One might use a information graph illustration, however information graphs undergo from the identical limitations as unstructured MD-based reminiscence attributable to their lack of structured search. What one wants is to have the ability to retrieve solely reminiscence that’s pertinent to the duty, throughout a number of attributes (or sides) of curiosity. For instance, an agent debugging a flaky take a look at ought to have the ability to pull solely the recollections tagged with the related module, language, framework, and failure mode—relatively retrieving primarily based on key phrases or embedding similarity. A separate situation is what to truly retrieve; uncooked agent traces with errors are usually not very helpful as they’ll induce brokers to repeat the identical mistake—as a substitute, we wish the retrieved reminiscence to be corrective.
We lately explored a associated notion of structured reminiscence, the place we set up reminiscence throughout varied attributes, every of which may very well be set as * to point common applicability, or set as an inventory of values to be matched. For a knowledge agent, the scale might embrace the columns and tables, kind of operation, and at last, open-ended natural-language corrective directions. So, we might embrace reminiscence that solely applies to a given kind of operation (e.g., ‘when performing date-time operations, use fiscal 12 months versus calendar 12 months conventions’), or a given desk (e.g., ‘column product_cleaned is most popular over column product when querying on product title’). One open query is defining an application-specific structured reminiscence—or what others have known as world fashions for reminiscence. We consider that is akin to defining a schema for every software—and maybe brokers themselves may also help us outline and refine it over time.
One Attainable Means To Retailer and Retrieve Structured Data [From Here]
Structured reminiscence shall be helpful additionally for evolutionary frameworks to successfully handle search areas. Certainly, storing, structuring, and mining massive volumes of single and multi-agent traces may also help future brokers turn into way more environment friendly—probably enabling efficient recursive self-improvement by way of structured memory-based mechanisms.
One other problem is to help concurrent edits to shared reminiscence, and concurrent edits usually, when there are numerous brokers performing transformations. Whereas there have been some helpful makes an attempt at supporting multiversioning and copy-on-write semantics, it isn’t clear that such strategies will suffice when 1000’s of brokers try to edit shared state on the identical time. For example, when brokers try varied potential transactions in response to a person request, the consequences of the overwhelming majority of those transactions must be rolled again—with solely the one ‘appropriate’ transaction’s consequence persisting. Work on supporting exactly-once semantics is related right here, as are underlying strategies primarily based on CRDTs and operational transformation. For updates to fuzzy mechanisms reminiscent of reminiscence, we could possibly sacrifice on consistency for good correctness within the curiosity of latency. Whereas brokers can purpose about semantics to compensate or roll again their actions to finally finalize most duties, the first problem lies within the diploma to which they step on one another’s toes in the course of the course of. An necessary failure mode to be averted is a type of “livelock,” the place incessant compensating actions forestall any significant progress.
Past shared state, different issues emerge when making an attempt to help a military of brokers, together with what to do when brokers fail, how brokers ought to talk with one another (instantly or by way of intermediate shared state), and the way we must always take care of straggler brokers. There have been some developments in supporting sturdy multi-agent execution, reminiscent of Temporal, but it surely stays to be seen if such options will apply at scale throughout 1000’s of brokers. On the subject of communication, we’d like mechanisms to allow brokers to barter with one another. Think about 4 developer brokers trying to succeed in consensus on a shared schema, with distinct however overlapping goals. In a human setting, this could contain iterative dialogue and compromise; for agentic swarms, we should outline the mechanisms that permit them to converge on a design that displays the underlying objectives of their respective principals. Or if brokers are all requiring entry to a restricted useful resource, once more communication shall be vital. It stays to be seen if that is finest accomplished by way of centralized coordination, or if a decentralized method is important.
Knowledge Methods By Brokers
Lastly, if intelligence is successfully free, then we are able to make use of this intelligence to synthesize new knowledge programs from scratch. Certainly, in lots of settings, general-purpose knowledge programs could also be overkill, as they need to help each schema, question, and {hardware} goal. Given a workload, current work, together with Bespoke OLAP and GenDB, has proven that one can use an agentic pipeline to synthesize an entire, workload-specific analytical engine—in minutes to some hours, at a price of some {dollars}. The engines are disposable: when the workload shifts, one can merely regenerate them. Analogously, our work has proven that one can synthesize customized key-value shops from scratch, focused to the workload. In actual fact, trendy IDEs, reminiscent of Kiro, elevate specs for programs growth to be a first-class citizen.
Brokers Can Synthesize Customized Knowledge Methods From Scratch
The primary situation, nevertheless, is that specs are usually imperfect, and don’t cowl all nook instances. Current-day brokers will exploit the lacking specs to reward-hack their option to a excessive efficiency metric. In our customized key-value retailer work, we discovered that one option to alleviate that is to have auxiliary verification brokers making an attempt to generate take a look at instances that catch the exploitation of nook instances, primarily increasing the specification. Yet one more method is to each generate a system and a proof for its correctness collectively, for which we now have discovered some early success, however extra must be accomplished to solidify the method. Additional, it stays to be seen what’s one of the simplest ways to solicit human-written specs for a system—can this be accomplished in an iterative, human-in-the-loop method, versus a one-shot, incomplete one. Certainly, human-written specs are incomplete even for manually authored software program, so one would anticipate that future brokers which are extra aligned will more and more train higher judgement when making design selections.
One Attainable Knowledge System Synthesis Pipeline [From Here]
Different questions right here contain testing whether or not ranging from a mature system (e.g., Postgres) and eradicating elements/performance can result in larger efficiency or extra person belief. Individually, is there a possibility to make the design composable, comprising varied verified elements which are combined and matched given a workload? For instance, maybe the workload hasn’t modified sufficient for the storage layer to be up to date, however maybe the question optimizer requires modifications. A maybe extra viable proposition entails using brokers coupled with proof programs to focus on crucial components of the code related to formal proofs, relatively than doing so for the complete system.
A closing alternative right here is to maneuver away from the normal knowledge programs stack with clearly-defined interfaces (e.g., parser, question optimizer, storage supervisor, …) — that have been every largely the prerogative of a single human group to handle. As an alternative, brokers can discover new methods to “mix” these elements collectively, maybe figuring out new optimization alternatives in consequence. Brokers also can fill in lacking gaps in performance to make present programs way more feature-complete, or attain feature-parity with different competing programs—or analogously, constantly refining open-source programs in response to function requests or points (maybe filed by different brokers!) Doing so in a approach that prioritizes correctness, long-term upkeep, and human interpretability shall be a problem.
Wanting Additional Forward
Within the period of near-free intelligence, knowledge programs matter greater than ever. As brokers tackle the majority of information work, the workload for knowledge programs will change, the substrate they should run on must be constructed, and more and more, they’ll take part in designing knowledge programs themselves. Every of those shifts opens up a brand new, thrilling analysis agenda.
Co-Evolution of Knowledge Methods and Brokers
Wanting additional out, the boundaries between brokers and knowledge programs will seemingly begin to blur. For example, brokers could design the info programs they themselves run on, defining each the interfaces in addition to the system elements beneath. Each the interfaces and internals might be advanced over time by brokers in a type of recursive self-improvement. There’s additionally a possibility to rethink knowledge programs as a holistic supply of fact for the whole lot of related state: together with uncooked knowledge, reminiscence, and coordination state, additional erasing the distinctions between the info that’s being queried by brokers and knowledge generated on account of agentic exercise. Lastly, knowledge programs could themselves incorporate agentic elements, essentially evolving from passive computation engines into clever, proactive, self-optimizing architectures. It’s exhausting to foretell what the longer term could maintain. We’re in for a wild journey!
Acknowledgments
The angle and ongoing work described on this publish are the product of joint analysis and plenty of discussions with great collaborators on the EPIC Knowledge Lab, Knowledge Methods & Foundations group, and the broader Berkeley AI-Methods group. Thanks all!
BibTex for this publish:
@misc{intelligence-is-free-blog,
title={Intelligence is Free, Now What? Knowledge Methods for, of, and by Brokers},
writer={Aditya G. Parameswaran and Shubham Agarwal and Kerem Akillioglu and Shreya Shankar
and Sepanta Zeighami and Rishabh Iyer and Matei Zaharia and Alvin Cheung
and Natacha Crooks and Joseph Gonzalez and Joseph Hellerstein and Ion Stoica},
howpublished={url{https://bair.berkeley.edu/weblog/2026/07/07/intelligence-is-free-now-what/}},
12 months={2026}
}
