… authorities of the individuals, by the individuals, for the individuals …
— 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; in the present day the identical runs beneath $1, and some suppliers are pushing prices beneath $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 era, with open-source fashions following intently 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 in the present day, and getting cheaper by the month. At this charge, we’re quickly coming into the period of nearly free intelligence—the type that’s greater than sufficient for on a regular basis data work.
Disclosure: This submit is a perspective led by Aditya G. Parameswaran—an Affiliate Professor of EECS and co-director of the EPIC Information Lab at UC Berkeley—collectively along with his collaborators. It’s half panorama survey and half perspective, and a number of other of the analysis instructions mentioned beneath (together with agentic hypothesis, structured reminiscence, and synthesizing customized knowledge techniques from scratch) draw on the authors’ personal ongoing work.
So, what does this new period of near-free intelligence imply for knowledge techniques? We consider three new challenges—and alternatives—stem from near-zero inference prices:
Information Techniques For Brokers. Brokers will quickly turn into the dominant workload for knowledge techniques—with swarms of brokers spun up in response to every end-user request. Given variations in traits between brokers and people—or functions appearing on their behalf—how ought to we redesign knowledge techniques for such agentic customers?
Information Techniques 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 techniques that reliably and effectively run and handle agent swarms seem like?
Information Techniques By Brokers. Brokers are quickly turning into able to synthesizing whole knowledge techniques in a single go—which means we are able to rebuild customized techniques for every new workload. Verifying that such techniques match supposed conduct is a problem. What does it take to let brokers synthesize knowledge techniques we are able to really belief?
Information Techniques For, Of, and By Brokers
Subsequent, we are going to focus on every in additional element, adopted by discussing the intertwined future of information techniques and brokers, particularly because the three challenges intersect.
Information Techniques For Brokers
An agent querying a database doesn’t behave like an individual or a BI device. 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 consumer request may quantity to 1000s of particular person SQL queries. Now, customers can concern ‘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 consumer segments are almost certainly to churn subsequent quarter’—every involving a combinatorial area of potential joins, aggregations, and filter combos.
Information Techniques Redesigned to Extra Successfully Help 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 making an attempt 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 sooner. It may possibly 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 might be 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 critical or useful.
One other alternative right here is to rethink the question interface fully: as an alternative of brokers issuing a single SQL question at a time, they may as an alternative concern 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 very good use of agentic reasoning means, maybe knowledge techniques ought to help higher-level primitives quite than requiring brokers to record every SQL question explicitly. One thought right here is to attract on DBT-style Jinja macros to offer looping-based primitives for brokers to work together with knowledge techniques.
A Caffeinated Military of Brokers Able to Tirelessly Full Your Information Duties
A remaining alternative right here is to cease considering of information techniques as passive executors of queries; knowledge techniques may very well be proactive, as they possess extra grounding in knowledge and system traits that brokers might lack a priori—they may steer brokers in several instructions, present outcomes for associated queries, and likewise present performance-level suggestions (e.g., as an alternative of executing an costly question, the system may 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 outcome. Actually, the info system may additionally put together each materialized and digital views for an agent upfront, offered to the agent as a part of context, as this can be cheaper or simpler than having an agent creator or use them.
Information Techniques Of Brokers
Beforehand, we targeted on how brokers work together with knowledge techniques. Now, we contemplate every little thing else brokers have to preserve working: the place they reside, 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. Nevertheless, the inference stack itself is being abstracted away by means of APIs (e.g., from OpenAI or Anthropic), or, for open-weight fashions, by means of serving frameworks that disguise low-level particulars. To date, the agentic substrate has been managed by means 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 recordsdata are all you want; brokers write to unstructured markdown (MD) recordsdata, which may then be searched utilizing grep, or by way of embedding-based retrieval. Actually, many argue that the answer to continuous studying is having brokers devour quite a bit (e.g., a whole codebase, slack, firm wikis, …) after which write their learnings into MD recordsdata, that are then retrieved selectively on demand. Certainly, file techniques, bash scripting, and MD recordsdata are and can nonetheless be essential for brokers. Nevertheless, at scale, when brokers are doing the overwhelming majority of information work, this method will 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 sooner or later. Even when context home windows proceed to develop, there are latency advantages to not put all info into context — and in lots of circumstances, e.g., when data work includes interacting with giant databases or code bases, will probably be infeasible to serialize all related knowledge into context.
Information Techniques As A Substrate for Multi-Agent Swarms
One may use a data graph illustration, however data graphs undergo from the identical limitations as unstructured MD-based reminiscence resulting from 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 aspects) of curiosity. For instance, an agent debugging a flaky take a look at ought to have the ability to pull solely the reminiscences tagged with the related module, language, framework, and failure mode—quite retrieving based mostly on key phrases or embedding similarity. A separate concern is what to really retrieve; uncooked agent traces with errors will not be very helpful as they may induce brokers to repeat the identical mistake—as an alternative, we wish the retrieved reminiscence to be corrective.
We lately explored a associated notion of structured reminiscence, the place we manage reminiscence throughout varied attributes, every of which may very well be set as * to point common applicability, or set as a listing of values to be matched. For an information agent, the scale may embody the columns and tables, kind of operation, and at last, open-ended natural-language corrective directions. So, we may embody 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 well-liked 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 can assist us outline and refine it over time.
One Potential Manner To Retailer and Retrieve Structured Information [From Here]
Structured reminiscence will likely be helpful additionally for evolutionary frameworks to successfully handle search areas. Certainly, storing, structuring, and mining giant volumes of single and multi-agent traces can assist future brokers turn into far more environment friendly—doubtlessly enabling efficient recursive self-improvement by means of structured memory-based mechanisms.
One other problem is to help concurrent edits to shared reminiscence, and concurrent edits generally, 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 methods will suffice when 1000’s of brokers are trying to edit shared state on the similar time. For example, when brokers try varied potential transactions in response to a consumer request, the results of the overwhelming majority of those transactions have to be rolled again—with solely the one ‘right’ transaction’s outcome persisting. Work on supporting exactly-once semantics is related right here, as are underlying methods based mostly on CRDTs and operational transformation. For updates to fuzzy mechanisms corresponding to reminiscence, we could possibly sacrifice on consistency for good correctness within the curiosity of latency. Whereas brokers can motive about semantics to compensate or roll again their actions to ultimately finalize most duties, the first problem lies within the diploma to which they step on one another’s toes throughout the course of. An essential failure mode to be averted is a type of “livelock,” the place incessant compensating actions stop any significant progress.
Past shared state, different considerations emerge when attempting to help a military of brokers, together with what to do when brokers fail, how brokers ought to talk with one another (straight or by means of intermediate shared state), and the way we should always take care of straggler brokers. There have been some developments in supporting sturdy multi-agent execution, corresponding to Temporal, nevertheless it 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 making an attempt to succeed in consensus on a shared schema, with distinct however overlapping aims. In a human setting, this might 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 will likely be crucial. It stays to be seen if that is greatest achieved by way of centralized coordination, or if a decentralized method is critical.
Information Techniques By Brokers
Lastly, if intelligence is successfully free, then we are able to make use of this intelligence to synthesize new knowledge techniques from scratch. Certainly, in lots of settings, general-purpose knowledge techniques could also be overkill, as they should 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 a whole, workload-specific analytical engine—in minutes to a couple hours, at a value 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. Actually, trendy IDEs, corresponding to Kiro, elevate specs for techniques growth to be a first-class citizen.
Brokers Can Synthesize Customized Information Techniques From Scratch
The principle concern, nevertheless, is that specs are usually imperfect, and don’t cowl all nook circumstances. Current-day brokers will exploit the lacking specs to reward-hack their technique to a excessive efficiency metric. In our customized key-value retailer work, we discovered that one technique to alleviate that is to have auxiliary verification brokers attempting to generate take a look at circumstances that catch the exploitation of nook circumstances, basically 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 achieved to solidify the method. Additional, it stays to be seen what’s the easiest way to solicit human-written specs for a system—can this be achieved 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 might be extra aligned will more and more train higher judgement when making design selections.
One Potential Information System Synthesis Pipeline [From Here]
Different questions right here contain testing whether or not ranging from a mature system (e.g., Postgres) and eradicating parts/performance can result in increased efficiency or extra consumer belief. Individually, is there a possibility to make the design composable, comprising varied verified parts which might be 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 adjustments. A maybe extra viable proposition includes using brokers coupled with proof techniques to focus on essential components of the code related to formal proofs, quite than doing so for the whole system.
A remaining alternative right here is to maneuver away from the standard knowledge techniques stack with clearly-defined interfaces (e.g., parser, question optimizer, storage supervisor, …) — that had been every largely the prerogative of a single human staff to handle. As a substitute, brokers can discover new methods to “mix” these parts collectively, maybe figuring out new optimization alternatives because of this. Brokers also can fill in lacking gaps in performance to make present techniques far more feature-complete, or attain feature-parity with different competing techniques—or analogously, constantly refining open-source techniques in response to characteristic requests or points (maybe filed by different brokers!) Doing so in a manner that prioritizes correctness, long-term upkeep, and human interpretability will likely be a problem.
Wanting Additional Forward
Within the period of near-free intelligence, knowledge techniques matter greater than ever. As brokers tackle the majority of information work, the workload for knowledge techniques will change, the substrate they should run on should be constructed, and more and more, they may take part in designing knowledge techniques themselves. Every of those shifts opens up a brand new, thrilling analysis agenda.
Co-Evolution of Information Techniques and Brokers
Wanting additional out, the boundaries between brokers and knowledge techniques will probably begin to blur. For example, brokers might design the info techniques they themselves run on, defining each the interfaces in addition to the system parts beneath. Each the interfaces and internals could be advanced over time by brokers in a type of recursive self-improvement. There may be additionally a possibility to rethink knowledge techniques as a holistic supply of reality for the whole thing 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 because of agentic exercise. Lastly, knowledge techniques might themselves incorporate agentic parts, essentially evolving from passive computation engines into clever, proactive, self-optimizing architectures. It’s onerous to foretell what the long run might maintain. We’re in for a wild journey!
Acknowledgments
The attitude and ongoing work described on this submit are the product of joint analysis and plenty of discussions with great collaborators on the EPIC Information Lab, Information Techniques & Foundations group, and the broader Berkeley AI-Techniques neighborhood. Thanks all!
BibTex for this submit:
@misc{intelligence-is-free-blog,
title={Intelligence is Free, Now What? Information Techniques for, of, and by Brokers},
creator={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}
}
