Overcome Failing Document Ingestion & RAG Strategies with Agentic Knowledge Distillation

Stay Ahead, Stay ONMINE

Overcome Failing Document Ingestion & RAG Strategies with Agentic Knowledge Distillation

Introduction Many generative AI use cases still revolve around Retrieval Augmented Generation (RAG), yet consistently fall short of user expectations. Despite the growing body of research on RAG improvements and even adding Agents into the process, many solutions still fail to return exhaustive results, miss information that is critical but infrequently mentioned in the documents, require multiple search iterations, and generally struggle to reconcile key themes across multiple documents. To top it all off, many implementations still rely on cramming as much “relevant” information as possible into the model’s context window alongside detailed system and user prompts. Reconciling all this information often exceeds the model’s cognitive capacity and compromises response quality and consistency. This is where our Agentic Knowledge Distillation + Pyramid Search Approach comes into play. Instead of chasing the best chunking strategy, retrieval algorithm, or inference-time reasoning method, my team, Jim Brown, Mason Sawtell, Sandi Besen, and I, take an agentic approach to document ingestion. We leverage the full capability of the model at ingestion time to focus exclusively on distilling and preserving the most meaningful information from the document dataset. This fundamentally simplifies the RAG process by allowing the model to direct its reasoning abilities toward addressing the user/system instructions rather than struggling to understand formatting and disparate information across document chunks. We specifically target high-value questions that are often difficult to evaluate because they have multiple correct answers or solution paths. These cases are where traditional RAG solutions struggle most and existing RAG evaluation datasets are largely insufficient for testing this problem space. For our research implementation, we downloaded annual and quarterly reports from the last year for the 30 companies in the DOW Jones Industrial Average. These documents can be found through the SEC EDGAR website. The information on EDGAR is accessible and able to be downloaded for free or can be queried through EDGAR public searches. See the SEC privacy policy for additional details, information on the SEC website is “considered public information and may be copied or further distributed by users of the web site without the SEC’s permission”. We selected this dataset for two key reasons: first, it falls outside the knowledge cutoff for the models evaluated, ensuring that the models cannot respond to questions based on their knowledge from pre-training; second, it’s a close approximation for real-world business problems while allowing us to discuss and share our findings using publicly available data. While typical RAG solutions excel at factual retrieval where the answer is easily identified in the document dataset (e.g., “When did Apple’s annual shareholder’s meeting occur?”), they struggle with nuanced questions that require a deeper understanding of concepts across documents (e.g., “Which of the DOW companies has the most promising AI strategy?”). Our Agentic Knowledge Distillation + Pyramid Search Approach addresses these types of questions with much greater success compared to other standard approaches we tested and overcomes limitations associated with using knowledge graphs in RAG systems. In this article, we’ll cover how our knowledge distillation process works, key benefits of this approach, examples, and an open discussion on the best way to evaluate these types of systems where, in many cases, there is no singular “right” answer. Building the pyramid: How Agentic Knowledge Distillation works Image by author and team depicting pyramid structure for document ingestion. Robots meant to represent agents building the pyramid. Overview Our knowledge distillation process creates a multi-tiered pyramid of information from the raw source documents. Our approach is inspired by the pyramids used in deep learning computer vision-based tasks, which allow a model to analyze an image at multiple scales. We take the contents of the raw document, convert it to markdown, and distill the content into a list of atomic insights, related concepts, document abstracts, and general recollections/memories. During retrieval it’s possible to access any or all levels of the pyramid to respond to the user request. How to distill documents and build the pyramid: Convert documents to Markdown: Convert all raw source documents to Markdown. We’ve found models process markdown best for this task compared to other formats like JSON and it is more token efficient. We used Azure Document Intelligence to generate the markdown for each page of the document, but there are many other open-source libraries like MarkItDown which do the same thing. Our dataset included 331 documents and 16,601 pages. Extract atomic insights from each page: We process documents using a two-page sliding window, which allows each page to be analyzed twice. This gives the agent the opportunity to correct any potential mistakes when processing the page initially. We instruct the model to create a numbered list of insights that grows as it processes the pages in the document. The agent can overwrite insights from the previous page if they were incorrect since it sees each page twice. We instruct the model to extract insights in simple sentences following the subject-verb-object (SVO) format and to write sentences as if English is the second language of the user. This significantly improves performance by encouraging clarity and precision. Rolling over each page multiple times and using the SVO format also solves the disambiguation problem, which is a huge challenge for knowledge graphs. The insight generation step is also particularly helpful for extracting information from tables since the model captures the facts from the table in clear, succinct sentences. Our dataset produced 216,931 total insights, about 13 insights per page and 655 insights per document. Distilling concepts from insights: From the detailed list of insights, we identify higher-level concepts that connect related information about the document. This step significantly reduces noise and redundant information in the document while preserving essential information and themes. Our dataset produced 14,824 total concepts, about 1 concept per page and 45 concepts per document. Creating abstracts from concepts: Given the insights and concepts in the document, the LLM writes an abstract that appears both better than any abstract a human would write and more information-dense than any abstract present in the original document. The LLM generated abstract provides incredibly comprehensive knowledge about the document with a small token density that carries a significant amount of information. We produce one abstract per document, 331 total. Storing recollections/memories across documents: At the top of the pyramid we store critical information that is useful across all tasks. This can be information that the user shares about the task or information the agent learns about the dataset over time by researching and responding to tasks. For example, we can store the current 30 companies in the DOW as a recollection since this list is different from the 30 companies in the DOW at the time of the model’s knowledge cutoff. As we conduct more and more research tasks, we can continuously improve our recollections and maintain an audit trail of which documents these recollections originated from. For example, we can keep track of AI strategies across companies, where companies are making major investments, etc. These high-level connections are super important since they reveal relationships and information that are not apparent in a single page or document. Sample subset of insights extracted from IBM 10Q, Q3 2024 (page 4) We store the text and embeddings for each layer of the pyramid (pages and up) in Azure PostgreSQL. We originally used Azure AI Search, but switched to PostgreSQL for cost reasons. This required us to write our own hybrid search function since PostgreSQL doesn’t yet natively support this feature. This implementation would work with any vector database or vector index of your choosing. The key requirement is to store and efficiently retrieve both text and vector embeddings at any level of the pyramid. This approach essentially creates the essence of a knowledge graph, but stores information in natural language, the way an LLM natively wants to interact with it, and is more efficient on token retrieval. We also let the LLM pick the terms used to categorize each level of the pyramid, this seemed to let the model decide for itself the best way to describe and differentiate between the information stored at each level. For example, the LLM preferred “insights” to “facts” as the label for the first level of distilled knowledge. Our goal in doing this was to better understand how an LLM thinks about the process by letting it decide how to store and group related information. Using the pyramid: How it works with RAG & Agents At inference time, both traditional RAG and agentic approaches benefit from the pre-processed, distilled information ingested in our knowledge pyramid. The pyramid structure allows for efficient retrieval in both the traditional RAG case, where only the top X related pieces of information are retrieved or in the Agentic case, where the Agent iteratively plans, retrieves, and evaluates information before returning a final response. The benefit of the pyramid approach is that information at any and all levels of the pyramid can be used during inference. For our implementation, we used PydanticAI to create a search agent that takes in the user request, generates search terms, explores ideas related to the request, and keeps track of information relevant to the request. Once the search agent determines there’s sufficient information to address the user request, the results are re-ranked and sent back to the LLM to generate a final reply. Our implementation allows a search agent to traverse the information in the pyramid as it gathers details about a concept/search term. This is similar to walking a knowledge graph, but in a way that’s more natural for the LLM since all the information in the pyramid is stored in natural language. Depending on the use case, the Agent could access information at all levels of the pyramid or only at specific levels (e.g. only retrieve information from the concepts). For our experiments, we did not retrieve raw page-level data since we wanted to focus on token efficiency and found the LLM-generated information for the insights, concepts, abstracts, and recollections was sufficient for completing our tasks. In theory, the Agent could also have access to the page data; this would provide additional opportunities for the agent to re-examine the original document text; however, it would also significantly increase the total tokens used. Here is a high-level visualization of our Agentic approach to responding to user requests: Image created by author and team providing an overview of the agentic research & response process Results from the pyramid: Real-world examples To evaluate the effectiveness of our approach, we tested it against a variety of question categories, including typical fact-finding questions and complex cross-document research and analysis tasks. Fact-finding (spear fishing): These tasks require identifying specific information or facts that are buried in a document. These are the types of questions typical RAG solutions target but often require many searches and consume lots of tokens to answer correctly. Example task: “What was IBM’s total revenue in the latest financial reporting?” Example response using pyramid approach: “IBM’s total revenue for the third quarter of 2024 was $14.968 billion [ibm-10q-q3-2024.pdf, pg. 4] Total tokens used to research and generate response This result is correct (human-validated) and was generated using only 9,994 total tokens, with 1,240 tokens in the generated final response. Complex research and analysis: These tasks involve researching and understanding multiple concepts to gain a broader understanding of the documents and make inferences and informed assumptions based on the gathered facts. Example task: “Analyze the investments Microsoft and NVIDIA are making in AI and how they are positioning themselves in the market. The report should be clearly formatted.” Example response: Response generated by the agent analyzing AI investments and positioning for Microsoft and NVIDIA. The result is a comprehensive report that executed quickly and contains detailed information about each of the companies. 26,802 total tokens were used to research and respond to the request with a significant percentage of them used for the final response (2,893 tokens or ~11%). These results were also reviewed by a human to verify their validity. Snippet indicating total token usage for the task Example task: “Create a report on analyzing the risks disclosed by the various financial companies in the DOW. Indicate which risks are shared and unique.” Example response: Part 1 of response generated by the agent on disclosed risks. Part 2 of response generated by the agent on disclosed risks. Similarly, this task was completed in 42.7 seconds and used 31,685 total tokens, with 3,116 tokens used to generate the final report. Snippet indicating total token usage for the task These results for both fact-finding and complex analysis tasks demonstrate that the pyramid approach efficiently creates detailed reports with low latency using a minimal amount of tokens. The tokens used for the tasks carry dense meaning with little noise allowing for high-quality, thorough responses across tasks. Benefits of the pyramid: Why use it? Overall, we found that our pyramid approach provided a significant boost in response quality and overall performance for high-value questions. Some of the key benefits we observed include: Reduced model’s cognitive load: When the agent receives the user task, it retrieves pre-processed, distilled information rather than the raw, inconsistently formatted, disparate document chunks. This fundamentally improves the retrieval process since the model doesn’t waste its cognitive capacity on trying to break down the page/chunk text for the first time. Superior table processing: By breaking down table information and storing it in concise but descriptive sentences, the pyramid approach makes it easier to retrieve relevant information at inference time through natural language queries. This was particularly important for our dataset since financial reports contain lots of critical information in tables. Improved response quality to many types of requests: The pyramid enables more comprehensive context-aware responses to both precise, fact-finding questions and broad analysis based tasks that involve many themes across numerous documents. Preservation of critical context: Since the distillation process identifies and keeps track of key facts, important information that might appear only once in the document is easier to maintain. For example, noting that all tables are represented in millions of dollars or in a particular currency. Traditional chunking methods often cause this type of information to slip through the cracks. Optimized token usage, memory, and speed: By distilling information at ingestion time, we significantly reduce the number of tokens required during inference, are able to maximize the value of information put in the context window, and improve memory use. Scalability: Many solutions struggle to perform as the size of the document dataset grows. This approach provides a much more efficient way to manage a large volume of text by only preserving critical information. This also allows for a more efficient use of the LLMs context window by only sending it useful, clear information. Efficient concept exploration: The pyramid enables the agent to explore related information similar to navigating a knowledge graph, but does not require ever generating or maintaining relationships in the graph. The agent can use natural language exclusively and keep track of important facts related to the concepts it’s exploring in a highly token-efficient and fluid way. Emergent dataset understanding: An unexpected benefit of this approach emerged during our testing. When asking questions like “what can you tell me about this dataset?” or “what types of questions can I ask?”, the system is able to respond and suggest productive search topics because it has a more robust understanding of the dataset context by accessing higher levels in the pyramid like the abstracts and recollections. Beyond the pyramid: Evaluation challenges & future directions Challenges While the results we’ve observed when using the pyramid search approach have been nothing short of amazing, finding ways to establish meaningful metrics to evaluate the entire system both at ingestion time and during information retrieval is challenging. Traditional RAG and Agent evaluation frameworks often fail to address nuanced questions and analytical responses where many different responses are valid. Our team plans to write a research paper on this approach in the future, and we are open to any thoughts and feedback from the community, especially when it comes to evaluation metrics. Many of the existing datasets we found were focused on evaluating RAG use cases within one document or precise information retrieval across multiple documents rather than robust concept and theme analysis across documents and domains. The main use cases we are interested in relate to broader questions that are representative of how businesses actually want to interact with GenAI systems. For example, “tell me everything I need to know about customer X” or “how do the behaviors of Customer A and B differ? Which am I more likely to have a successful meeting with?”. These types of questions require a deep understanding of information across many sources. The answers to these questions typically require a person to synthesize data from multiple areas of the business and think critically about it. As a result, the answers to these questions are rarely written or saved anywhere which makes it impossible to simply store and retrieve them through a vector index in a typical RAG process. Another consideration is that many real-world use cases involve dynamic datasets where documents are consistently being added, edited, and deleted. This makes it difficult to evaluate and track what a “correct” response is since the answer will evolve as the available information changes. Future directions In the future, we believe that the pyramid approach can address some of these challenges by enabling more effective processing of dense documents and storing learned information as recollections. However, tracking and evaluating the validity of the recollections over time will be critical to the system’s overall success and remains a key focus area for our ongoing work. When applying this approach to organizational data, the pyramid process could also be used to identify and assess discrepancies across areas of the business. For example, uploading all of a company’s sales pitch decks could surface where certain products or services are being positioned inconsistently. It could also be used to compare insights extracted from various line of business data to help understand if and where teams have developed conflicting understandings of topics or different priorities. This application goes beyond pure information retrieval use cases and would allow the pyramid to serve as an organizational alignment tool that helps identify divergences in messaging, terminology, and overall communication. Conclusion: Key takeaways and why the pyramid approach matters The knowledge distillation pyramid approach is significant because it leverages the full power of the LLM at both ingestion and retrieval time. Our approach allows you to store dense information in fewer tokens which has the added benefit of reducing noise in the dataset at inference. Our approach also runs very quickly and is incredibly token efficient, we are able to generate responses within seconds, explore potentially hundreds of searches, and on average use

Introduction

Many generative AI use cases still revolve around Retrieval Augmented Generation (RAG), yet consistently fall short of user expectations. Despite the growing body of research on RAG improvements and even adding Agents into the process, many solutions still fail to return exhaustive results, miss information that is critical but infrequently mentioned in the documents, require multiple search iterations, and generally struggle to reconcile key themes across multiple documents. To top it all off, many implementations still rely on cramming as much “relevant” information as possible into the model’s context window alongside detailed system and user prompts. Reconciling all this information often exceeds the model’s cognitive capacity and compromises response quality and consistency.

This is where our Agentic Knowledge Distillation + Pyramid Search Approach comes into play. Instead of chasing the best chunking strategy, retrieval algorithm, or inference-time reasoning method, my team, Jim Brown, Mason Sawtell, Sandi Besen, and I, take an agentic approach to document ingestion.

We leverage the full capability of the model at ingestion time to focus exclusively on distilling and preserving the most meaningful information from the document dataset. This fundamentally simplifies the RAG process by allowing the model to direct its reasoning abilities toward addressing the user/system instructions rather than struggling to understand formatting and disparate information across document chunks.

We specifically target high-value questions that are often difficult to evaluate because they have multiple correct answers or solution paths. These cases are where traditional RAG solutions struggle most and existing RAG evaluation datasets are largely insufficient for testing this problem space. For our research implementation, we downloaded annual and quarterly reports from the last year for the 30 companies in the DOW Jones Industrial Average. These documents can be found through the SEC EDGAR website. The information on EDGAR is accessible and able to be downloaded for free or can be queried through EDGAR public searches. See the SEC privacy policy for additional details, information on the SEC website is “considered public information and may be copied or further distributed by users of the web site without the SEC’s permission”. We selected this dataset for two key reasons: first, it falls outside the knowledge cutoff for the models evaluated, ensuring that the models cannot respond to questions based on their knowledge from pre-training; second, it’s a close approximation for real-world business problems while allowing us to discuss and share our findings using publicly available data.

While typical RAG solutions excel at factual retrieval where the answer is easily identified in the document dataset (e.g., “When did Apple’s annual shareholder’s meeting occur?”), they struggle with nuanced questions that require a deeper understanding of concepts across documents (e.g., “Which of the DOW companies has the most promising AI strategy?”). Our Agentic Knowledge Distillation + Pyramid Search Approach addresses these types of questions with much greater success compared to other standard approaches we tested and overcomes limitations associated with using knowledge graphs in RAG systems.

In this article, we’ll cover how our knowledge distillation process works, key benefits of this approach, examples, and an open discussion on the best way to evaluate these types of systems where, in many cases, there is no singular “right” answer.

Building the pyramid: How Agentic Knowledge Distillation works

AI-generated image showing a pyramid structure for document ingestion with labelled sections. — Image by author and team depicting pyramid structure for document ingestion. Robots meant to represent agents building the pyramid.

Overview

Our knowledge distillation process creates a multi-tiered pyramid of information from the raw source documents. Our approach is inspired by the pyramids used in deep learning computer vision-based tasks, which allow a model to analyze an image at multiple scales. We take the contents of the raw document, convert it to markdown, and distill the content into a list of atomic insights, related concepts, document abstracts, and general recollections/memories. During retrieval it’s possible to access any or all levels of the pyramid to respond to the user request.

How to distill documents and build the pyramid:

Convert documents to Markdown: Convert all raw source documents to Markdown. We’ve found models process markdown best for this task compared to other formats like JSON and it is more token efficient. We used Azure Document Intelligence to generate the markdown for each page of the document, but there are many other open-source libraries like MarkItDown which do the same thing. Our dataset included 331 documents and 16,601 pages.
Extract atomic insights from each page: We process documents using a two-page sliding window, which allows each page to be analyzed twice. This gives the agent the opportunity to correct any potential mistakes when processing the page initially. We instruct the model to create a numbered list of insights that grows as it processes the pages in the document. The agent can overwrite insights from the previous page if they were incorrect since it sees each page twice. We instruct the model to extract insights in simple sentences following the subject-verb-object (SVO) format and to write sentences as if English is the second language of the user. This significantly improves performance by encouraging clarity and precision. Rolling over each page multiple times and using the SVO format also solves the disambiguation problem, which is a huge challenge for knowledge graphs. The insight generation step is also particularly helpful for extracting information from tables since the model captures the facts from the table in clear, succinct sentences. Our dataset produced 216,931 total insights, about 13 insights per page and 655 insights per document.
Distilling concepts from insights: From the detailed list of insights, we identify higher-level concepts that connect related information about the document. This step significantly reduces noise and redundant information in the document while preserving essential information and themes. Our dataset produced 14,824 total concepts, about 1 concept per page and 45 concepts per document.
Creating abstracts from concepts: Given the insights and concepts in the document, the LLM writes an abstract that appears both better than any abstract a human would write and more information-dense than any abstract present in the original document. The LLM generated abstract provides incredibly comprehensive knowledge about the document with a small token density that carries a significant amount of information. We produce one abstract per document, 331 total.
Storing recollections/memories across documents: At the top of the pyramid we store critical information that is useful across all tasks. This can be information that the user shares about the task or information the agent learns about the dataset over time by researching and responding to tasks. For example, we can store the current 30 companies in the DOW as a recollection since this list is different from the 30 companies in the DOW at the time of the model’s knowledge cutoff. As we conduct more and more research tasks, we can continuously improve our recollections and maintain an audit trail of which documents these recollections originated from. For example, we can keep track of AI strategies across companies, where companies are making major investments, etc. These high-level connections are super important since they reveal relationships and information that are not apparent in a single page or document.

Sample subset of insights extracted from IBM 10Q, Q3 2024 (page 4)

We store the text and embeddings for each layer of the pyramid (pages and up) in Azure PostgreSQL. We originally used Azure AI Search, but switched to PostgreSQL for cost reasons. This required us to write our own hybrid search function since PostgreSQL doesn’t yet natively support this feature. This implementation would work with any vector database or vector index of your choosing. The key requirement is to store and efficiently retrieve both text and vector embeddings at any level of the pyramid.

This approach essentially creates the essence of a knowledge graph, but stores information in natural language, the way an LLM natively wants to interact with it, and is more efficient on token retrieval. We also let the LLM pick the terms used to categorize each level of the pyramid, this seemed to let the model decide for itself the best way to describe and differentiate between the information stored at each level. For example, the LLM preferred “insights” to “facts” as the label for the first level of distilled knowledge. Our goal in doing this was to better understand how an LLM thinks about the process by letting it decide how to store and group related information.

Using the pyramid: How it works with RAG & Agents

At inference time, both traditional RAG and agentic approaches benefit from the pre-processed, distilled information ingested in our knowledge pyramid. The pyramid structure allows for efficient retrieval in both the traditional RAG case, where only the top X related pieces of information are retrieved or in the Agentic case, where the Agent iteratively plans, retrieves, and evaluates information before returning a final response.

The benefit of the pyramid approach is that information at any and all levels of the pyramid can be used during inference. For our implementation, we used PydanticAI to create a search agent that takes in the user request, generates search terms, explores ideas related to the request, and keeps track of information relevant to the request. Once the search agent determines there’s sufficient information to address the user request, the results are re-ranked and sent back to the LLM to generate a final reply. Our implementation allows a search agent to traverse the information in the pyramid as it gathers details about a concept/search term. This is similar to walking a knowledge graph, but in a way that’s more natural for the LLM since all the information in the pyramid is stored in natural language.

Depending on the use case, the Agent could access information at all levels of the pyramid or only at specific levels (e.g. only retrieve information from the concepts). For our experiments, we did not retrieve raw page-level data since we wanted to focus on token efficiency and found the LLM-generated information for the insights, concepts, abstracts, and recollections was sufficient for completing our tasks. In theory, the Agent could also have access to the page data; this would provide additional opportunities for the agent to re-examine the original document text; however, it would also significantly increase the total tokens used.

Here is a high-level visualization of our Agentic approach to responding to user requests:

Overview of the agentic research & response process — Image created by author and team providing an overview of the agentic research & response process

Results from the pyramid: Real-world examples

To evaluate the effectiveness of our approach, we tested it against a variety of question categories, including typical fact-finding questions and complex cross-document research and analysis tasks.

Fact-finding (spear fishing):

These tasks require identifying specific information or facts that are buried in a document. These are the types of questions typical RAG solutions target but often require many searches and consume lots of tokens to answer correctly.

Example task: “What was IBM’s total revenue in the latest financial reporting?”

Example response using pyramid approach: “IBM’s total revenue for the third quarter of 2024 was $14.968 billion [ibm-10q-q3-2024.pdf, pg. 4]

Screenshot of total tokens used to research and generate response — Total tokens used to research and generate response

This result is correct (human-validated) and was generated using only 9,994 total tokens, with 1,240 tokens in the generated final response.

Complex research and analysis:

These tasks involve researching and understanding multiple concepts to gain a broader understanding of the documents and make inferences and informed assumptions based on the gathered facts.

Example task: “Analyze the investments Microsoft and NVIDIA are making in AI and how they are positioning themselves in the market. The report should be clearly formatted.”

Example response:

Screenshot of the response generated by the agent analyzing AI investments and positioning for Microsoft and NVIDIA. — Response generated by the agent analyzing AI investments and positioning for Microsoft and NVIDIA.

The result is a comprehensive report that executed quickly and contains detailed information about each of the companies. 26,802 total tokens were used to research and respond to the request with a significant percentage of them used for the final response (2,893 tokens or ~11%). These results were also reviewed by a human to verify their validity.

Screenshot of snippet indicating total token usage for the task — Snippet indicating total token usage for the task

Example task: “Create a report on analyzing the risks disclosed by the various financial companies in the DOW. Indicate which risks are shared and unique.”

Example response:

Screenshot of part 1 of a response generated by the agent on disclosed risks. — Part 1 of response generated by the agent on disclosed risks.

Screenshot of part 2 of a response generated by the agent on disclosed risks. — Part 2 of response generated by the agent on disclosed risks.

Similarly, this task was completed in 42.7 seconds and used 31,685 total tokens, with 3,116 tokens used to generate the final report.

Screenshot of a snippet indicating total token usage for the task — Snippet indicating total token usage for the task

These results for both fact-finding and complex analysis tasks demonstrate that the pyramid approach efficiently creates detailed reports with low latency using a minimal amount of tokens. The tokens used for the tasks carry dense meaning with little noise allowing for high-quality, thorough responses across tasks.

Benefits of the pyramid: Why use it?

Overall, we found that our pyramid approach provided a significant boost in response quality and overall performance for high-value questions.

Some of the key benefits we observed include:

Reduced model’s cognitive load: When the agent receives the user task, it retrieves pre-processed, distilled information rather than the raw, inconsistently formatted, disparate document chunks. This fundamentally improves the retrieval process since the model doesn’t waste its cognitive capacity on trying to break down the page/chunk text for the first time.
Superior table processing: By breaking down table information and storing it in concise but descriptive sentences, the pyramid approach makes it easier to retrieve relevant information at inference time through natural language queries. This was particularly important for our dataset since financial reports contain lots of critical information in tables.
Improved response quality to many types of requests: The pyramid enables more comprehensive context-aware responses to both precise, fact-finding questions and broad analysis based tasks that involve many themes across numerous documents.
Preservation of critical context: Since the distillation process identifies and keeps track of key facts, important information that might appear only once in the document is easier to maintain. For example, noting that all tables are represented in millions of dollars or in a particular currency. Traditional chunking methods often cause this type of information to slip through the cracks.
Optimized token usage, memory, and speed: By distilling information at ingestion time, we significantly reduce the number of tokens required during inference, are able to maximize the value of information put in the context window, and improve memory use.
Scalability: Many solutions struggle to perform as the size of the document dataset grows. This approach provides a much more efficient way to manage a large volume of text by only preserving critical information. This also allows for a more efficient use of the LLMs context window by only sending it useful, clear information.
Efficient concept exploration: The pyramid enables the agent to explore related information similar to navigating a knowledge graph, but does not require ever generating or maintaining relationships in the graph. The agent can use natural language exclusively and keep track of important facts related to the concepts it’s exploring in a highly token-efficient and fluid way.
Emergent dataset understanding: An unexpected benefit of this approach emerged during our testing. When asking questions like “what can you tell me about this dataset?” or “what types of questions can I ask?”, the system is able to respond and suggest productive search topics because it has a more robust understanding of the dataset context by accessing higher levels in the pyramid like the abstracts and recollections.

Beyond the pyramid: Evaluation challenges & future directions

Challenges

While the results we’ve observed when using the pyramid search approach have been nothing short of amazing, finding ways to establish meaningful metrics to evaluate the entire system both at ingestion time and during information retrieval is challenging. Traditional RAG and Agent evaluation frameworks often fail to address nuanced questions and analytical responses where many different responses are valid.

Our team plans to write a research paper on this approach in the future, and we are open to any thoughts and feedback from the community, especially when it comes to evaluation metrics. Many of the existing datasets we found were focused on evaluating RAG use cases within one document or precise information retrieval across multiple documents rather than robust concept and theme analysis across documents and domains.

The main use cases we are interested in relate to broader questions that are representative of how businesses actually want to interact with GenAI systems. For example, “tell me everything I need to know about customer X” or “how do the behaviors of Customer A and B differ? Which am I more likely to have a successful meeting with?”. These types of questions require a deep understanding of information across many sources. The answers to these questions typically require a person to synthesize data from multiple areas of the business and think critically about it. As a result, the answers to these questions are rarely written or saved anywhere which makes it impossible to simply store and retrieve them through a vector index in a typical RAG process.

Another consideration is that many real-world use cases involve dynamic datasets where documents are consistently being added, edited, and deleted. This makes it difficult to evaluate and track what a “correct” response is since the answer will evolve as the available information changes.

Future directions

In the future, we believe that the pyramid approach can address some of these challenges by enabling more effective processing of dense documents and storing learned information as recollections. However, tracking and evaluating the validity of the recollections over time will be critical to the system’s overall success and remains a key focus area for our ongoing work.

When applying this approach to organizational data, the pyramid process could also be used to identify and assess discrepancies across areas of the business. For example, uploading all of a company’s sales pitch decks could surface where certain products or services are being positioned inconsistently. It could also be used to compare insights extracted from various line of business data to help understand if and where teams have developed conflicting understandings of topics or different priorities. This application goes beyond pure information retrieval use cases and would allow the pyramid to serve as an organizational alignment tool that helps identify divergences in messaging, terminology, and overall communication.

Conclusion: Key takeaways and why the pyramid approach matters

The knowledge distillation pyramid approach is significant because it leverages the full power of the LLM at both ingestion and retrieval time. Our approach allows you to store dense information in fewer tokens which has the added benefit of reducing noise in the dataset at inference. Our approach also runs very quickly and is incredibly token efficient, we are able to generate responses within seconds, explore potentially hundreds of searches, and on average use (this includes all the search iterations!).

We find that the LLM is much better at writing atomic insights as sentences and that these insights effectively distill information from both text-based and tabular data. This distilled information written in natural language is very easy for the LLM to understand and navigate at inference since it does not have to expend unnecessary energy reasoning about and breaking down document formatting or filtering through noise.

The ability to retrieve and aggregate information at any level of the pyramid also provides significant flexibility to address a variety of query types. This approach offers promising performance for large datasets and enables high-value use cases that require nuanced information retrieval and analysis.

Note: The opinions expressed in this article are solely my own and do not necessarily reflect the views or policies of my employer.

Interested in discussing further or collaborating? Reach out on LinkedIn!

Stay Ahead

Explore More Insights

Stay ahead with more perspectives on cutting-edge power, infrastructure, energy, bitcoin and AI solutions. Explore these articles to uncover strategies and insights shaping the future of industries.

Nissan, SK On announce $661M EV battery supply deal

Dive Brief: Nissan Motor Corp. and SK On inked a battery agreement to bolster the automaker’s electric vehicle production in North America, according to a Wednesday press release. Under the $661 million deal, the battery manufacturer will supply Nissan with roughly 100 GWh of high-nickel batteries from 2028 to 2033.

Nvidia launches research center to accelerate quantum computing breakthrough

The new research center aims to tackle quantum computing’s most significant challenges, including qubit noise reduction and the transformation of experimental quantum processors into practical devices. “By combining quantum processing units (QPUs) with state-of-the-art GPU technology, Nvidia hopes to accelerate the timeline to practical quantum computing applications,” the statement added.

Keysight network packet brokers gain AI-powered features

The technology has matured considerably since then. Over the last five years, Singh said that most of Keysight’s NPB customers are global Fortune 500 organizations that have large network visibility practices. Meaning they deploy a lot of packet brokers with capabilities ranging anywhere from one gigabit networking at the edge,

Adding, managing and deleting groups on Linux

$ sudo groupadd -g 1111 techs In this case, a specific group ID (1111) is being assigned. Omit the -g option to use the next available group ID (e.g., sudo groupadd techs). Once a group is added, you will find it in the /etc/group file. $ grep techs /etc/grouptechs:x:1111: Adding

Power Moves: New renewables managing director for PX Group and more

Tracy Wilson-Long has been appointed to Teesside-based PX Group as its new managing director for power and renewables. Originally from Teesside, Wilson-Long brings a wealth of experience to the role, having previously held strategic leadership positions at BP, working on global large-scale projects across North America, Europe, Asia, and Africa. Most recently she has worked in the Canadian clean technology space, helping start-ups advance to commercialisation, with a key focus and expertise in the developing hydrogen market. Tracy succeeds Neil Grimley, who has been with PX Group for over three decades and has shown outstanding, dedication and contribution, most recently in his leadership role building the power and renewables portfolio. He will now transition to the role of group business development director, where he will leverage his extensive experience to drive growth in fuels, terminals, and major net zero projects. Wilson-Long said: “PX Group’s vision, strategy and culture are a fantastic fit for me, I’m really looking forward to getting out to all our sites, meeting our people and customers, whilst learning all about the diverse operations in our business. I’m looking forward to working with PX Group’s talented team to unlock new possibilities.” PX Group recently scored a major contract win as it landed an operations and maintenance deal for the Tees Renewable Energy Plant (Tees REP). © Supplied by EnerMechEnerMech head of regional management in the Asia Pacific region Jason Jeow. Jason Jeow has been promoted to head Aberdeen-based EnerMech’s regional management in the Asia Pacific region. Jeow joined EnerMech in February as vice-president for Asia Pacific and will take on responsibility for managing relationships with regulatory bodies and environmental agencies as well as collaborate with business lines and local leaders to ensure adherence to high HSE standards and the safety of EnerMech personnel. EnerMech CEO Charles ‘Chuck’

USA Crude Oil Inventories Rise Week on Week

U.S. commercial crude oil inventories, excluding those in the Strategic Petroleum Reserve (SPR), increased by 1.7 million barrels from the week ending March 7 to the week ending March 14, the U.S. Energy Information Administration (EIA) highlighted in its latest weekly petroleum status report. That report was released on March 19 and included data for the week ending March 14. This EIA report showed that crude oil stocks, not including the SPR, stood at 437.0 million barrels on March 14, 435.2 million barrels on March 7, and 445.0 million barrels on March 15, 2024. Crude oil in the SPR stood at 395.9 million barrels on March 14, 395.6 million barrels on March 7, and 362.3 million barrels on March 15, 2024, the report outlined. The EIA report highlighted that data may not add up to totals due to independent rounding. Total petroleum stocks – including crude oil, total motor gasoline, fuel ethanol, kerosene type jet fuel, distillate fuel oil, residual fuel oil, propane/propylene, and other oils – stood at 1.596 billion barrels on March 14, the report showed. Total petroleum stocks were up 1.9 million barrels week on week and up 22.5 million barrels year on year, the report revealed. “At 437.0 million barrels, U.S. crude oil inventories are about five percent below the five year average for this time of year,” the EIA said in its latest weekly petroleum status report. “Total motor gasoline inventories decreased by 0.5 million barrels from last week and are two percent above the five year average for this time of year. Finished gasoline inventories and blending components inventories both decreased last week,” it added. “Distillate fuel inventories decreased by 2.8 million barrels last week and are about six percent below the five year average for this time of year. Propane/propylene inventories decreased by

Ceres Power strikes ‘record’ 2024

Fuel cell and electrolyser company Ceres Power generated record revenues and orders which narrowed losses in 2024, according to its final results for the year to 31 December. “This past year has been a record,” the company’s chief executive Phil Caldwell said on a call on Friday. “Looking ahead to next year… if we can get similar performance in 2025, that would also be a very good year.” The Horsham-based company’s revenues more than doubled over the year to £51.9 million, up from £22.3m a year earlier. Its gross margin rose to 77%, with gross profit nearly quadrupling to £40.2m, up from £13.6m in 2023. Healthy sales of services and licences and increased profitability meant pre-tax losses for the year halved to £25.9m, from a £53.6m loss in the prior year. Caldwell attributed the results, including a record order book of £112.8m for the period, to “progress” that the company has made with its partners. The firm signed three “significant” partner licence agreements in the year, although it was also disappointed” that its shareholder Bosch announced in February it would cease production of the firm’s fuel cells and divest its minority stake. During the period, Ceres signed two new manufacturing licensees, Taiwan-based Delta Electronics and Denso in Japan, together with India’s electrolyser company Thermax. “What that does is that builds out our market share and really where this business becomes profitable is, as those partners get to market and we’ve started to get products in the market, that’s where we get royalties and that’s what really drives the business forwards,” he said. “So, making progress with existing partners and also adding new partners to that is really how we grow the business.” First hydrogen production This fiscal year, the fuel cell and electrolyser company said it expects to reach initial

UK net zero innovators to showcase pioneering tech in Aberdeen

Leading energy technology companies from across the UK will head to Aberdeen in April for the Net Zero Innovators conference at the P&J Live. Organised by the Net Zero Technology Centre (NZTC), the event comes amid a multibillion-pound boom in the UK’s energy transition sector. Taking place on 3 April, the conference will feature 50 exhibiting startups including previous participants from the NZTC TechX Accelerator programme. Firms including Frontier Robotics, Wastewater Fuels and JET Connectivity will showcase their innovations, alongside a series of panel discussions. Technologies on display range from renewables to energy storage, carbon capture, hydrogen, alternative fuels and industrial decarbonisation. Since its launch, the Aberdeen-headquartered NZTC has co-invested £420 million in technology development and demonstration projects. Jointly funded by the UK and Scottish governments as part of the Aberdeen City Region Deal, the NZTC said its investment programme has created 1,550 direct jobs in Scotland. Net Zero Innovators NZTC chief acceleration officer Mark Anderson said events like the Net Zero Innovators conference “are about more than just ideas”. “They’re about bringing people together and driving real change,” he said. “As our first-ever Net Zero Innovators conference, this event is a major step forward in our journey to connect the brightest minds and most impactful innovations with their potential customers and backers in the energy industry. © Supplied by NZTCNZTC TechX director Mark Anderson. “It’s happening at an exciting time for Scotland’s net zero economy, which is growing at the fastest rate in the UK.” Anderson said the conference will demonstration how collaboration can “accelerate the transition to net zero” and boost “not also sustainability but also the economy”. “We’re thrilled to bring together experts and innovators who, through our TechX Accelerator, are turning cutting-edge ideas into scalable, commercial solutions,” he said. “These startups are making a real impact

US deploys record energy storage in 2024, but Trump policies cloud outlook: WoodMac/ACP

Dive Brief: U.S. energy storage installations reached 12.3 GW/37.1 GWh in 2024 despite a 20% year-over-year drop in the fourth quarter, Wood Mackenzie and the American Clean Power Association said Wednesday. The full-year 2024 and Q1 2025 Energy Storage Monitor projected 15 GW/48 GWh of energy storage deployments in 2025, a 25% increase over 2024, due to strong growth in the utility-scale segment and an expected 47% jump in the residential segment. But state and federal policy uncertainty cloud the medium-term outlook for energy storage, resulting in a 27-GW gap between Wood Mackenzie’s five-year “high” and “low” cases, the report said. Dive Insight: U.S. energy storage deployments rose 34% from 2023 to 2024, and all three energy storage segments Wood Mackenzie tracks saw double-digit growth. The utility-scale segment grew 32% to 33.7 GWh, while the residential segment jumped 64% to just over 3 GWh and the community-scale, commercial and industrial segment rose 11% to 370 MWh, Wood Mackenzie said. The residential and CCI segments saw strong growth in Q4 2024, but utility-scale deployments fell 28%, resulting in a decline in total deployments during the quarter. Development delays in late 2024 pushed about 2 GW of projects originally expected for last year into 2025, boosting Wood Mackenzie’s 2025 forecast for utility-scale deployments by 11% from the previous quarter. Q4 2024 saw a noticeable increase in installations outside California and Texas, the United States’ largest energy storage markets. The two states accounted for 61% of deployments in the fourth quarter, a 30% drop from Q3 2024, as New Mexico (400 MW), Oregon (292 MW), Arizona (185 MW) and North Carolina (115 MW) made meaningful contributions. In the residential market, the storage attachment rate reached 34% despite slower-than-expected progress to retire California’s backlog of projects under the legacy NEM 2.0 tariff, Wood Mackenzie

FERC approves SPP’s RTO West, plus 4 other open meeting takeaways

The Southwest Power Pool will expand its regional transmission organization operations into the Western Interconnection as soon as early next year under its RTO West plan, which the Federal Energy Regulatory Commission approved on Thursday. “This proposal will likely enhance grid reliability and operational efficiency by consolidating transmission management under a single RTO,” FERC Commissioner Willie Phillips said during the agency’s monthly meeting. The approval of SPP’s RTO West plan “is another major milestone for the market evolution in the Western part of the U.S.,” FERC Commissioner Judy Chang said. Chang and Phillips said more work needs to occur on RTO West, however, especially on how the seams between markets and nonmarket areas will be managed. “In the near future, I hope we can address seams issues — like data sharing, congestion management, market power mitigation, transmission availability, export-import management and intertie optimization — to maximize reliability and consumer benefits,” Phillips said. In its decision, FERC said it was too soon to address the seams issues, which were raised by the Colorado Public Service Commission, Xcel Energy’s Public Service Co. of Colorado and Black Hills utilities. Entities pursuing RTO membership or expanded participation in SPP’s markets include Basin Electric Power Cooperative, Colorado Springs Utilities, Deseret Generation and Transmission Cooperative, Municipal Energy Agency of Nebraska, Platte River Power Authority, Tri-State Generation and Transmission Association, Western Area Power Administration – Colorado River Storage Project Management Center, WAPA – Rocky Mountain Region and WAPA – Upper Great Plains Region. “We greatly value the full benefits of the SPP RTO, including day-ahead and ancillary services markets, efficient regional transmission planning, a common transmission tariff and participatory governance model that help us to further reduce costs for our members across the West,” Tri-State CEO Duane Highley said in an SPP press release. SPP is working with additional Western utilities that are considering joining

PEAK:AIO adds power, density to AI storage server

There is also the fact that many people working with AI are not IT professionals, such as professors, biochemists, scientists, doctors, clinicians, and they don’t have a traditional enterprise department or a data center. “It’s run by people that wouldn’t really know, nor want to know, what storage is,” he said. While the new AI Data Server is a Dell design, PEAK:AIO has worked with Lenovo, Supermicro, and HPE as well as Dell over the past four years, offering to convert their off the shelf storage servers into hyper fast, very AI-specific, cheap, specific storage servers that work with all the protocols at Nvidia, like NVLink, along with NFS and NVMe over Fabric. It also greatly increased storage capacity by going with 61TB drives from Solidigm. SSDs from the major server vendors typically maxed out at 15TB, according to the vendor. PEAK:AIO competes with VAST, WekaIO, NetApp, Pure Storage and many others in the growing AI workload storage arena. PEAK:AIO’s AI Data Server is available now.

SoftBank to buy Ampere for $6.5B, fueling Arm-based server market competition

SoftBank’s announcement suggests Ampere will collaborate with other SBG companies, potentially creating a powerful ecosystem of Arm-based computing solutions. This collaboration could extend to SoftBank’s numerous portfolio companies, including Korean/Japanese web giant LY Corp, ByteDance (TikTok’s parent company), and various AI startups. If SoftBank successfully steers its portfolio companies toward Ampere processors, it could accelerate the shift away from x86 architecture in data centers worldwide. Questions remain about Arm’s server strategy The acquisition, however, raises questions about how SoftBank will balance its investments in both Arm and Ampere, given their potentially competing server CPU strategies. Arm’s recent move to design and sell its own server processors to Meta signaled a major strategic shift that already put it in direct competition with its own customers, including Qualcomm and Nvidia. “In technology licensing where an entity is both provider and competitor, boundaries are typically well-defined without special preferences beyond potential first-mover advantages,” Kawoosa explained. “Arm will likely continue making independent licensing decisions that serve its broader interests rather than favoring Ampere, as the company can’t risk alienating its established high-volume customers.” Industry analysts speculate that SoftBank might position Arm to focus on custom designs for hyperscale customers while allowing Ampere to dominate the market for more standardized server processors. Alternatively, the two companies could be merged or realigned to present a unified strategy against incumbents Intel and AMD. “While Arm currently dominates processor architecture, particularly for energy-efficient designs, the landscape isn’t static,” Kawoosa added. “The semiconductor industry is approaching a potential inflection point, and we may witness fundamental disruptions in the next 3-5 years — similar to how OpenAI transformed the AI landscape. SoftBank appears to be maximizing its Arm investments while preparing for this coming paradigm shift in processor architecture.”

Nvidia, xAI and two energy giants join genAI infrastructure initiative

The new AIP members will “further strengthen the partnership’s technology leadership as the platform seeks to invest in new and expanded AI infrastructure. Nvidia will also continue in its role as a technical advisor to AIP, leveraging its expertise in accelerated computing and AI factories to inform the deployment of next-generation AI data center infrastructure,” the group’s statement said. “Additionally, GE Vernova and NextEra Energy have agreed to collaborate with AIP to accelerate the scaling of critical and diverse energy solutions for AI data centers. GE Vernova will also work with AIP and its partners on supply chain planning and in delivering innovative and high efficiency energy solutions.” The group claimed, without offering any specifics, that it “has attracted significant capital and partner interest since its inception in September 2024, highlighting the growing demand for AI-ready data centers and power solutions.” The statement said the group will try to raise “$30 billion in capital from investors, asset owners, and corporations, which in turn will mobilize up to $100 billion in total investment potential when including debt financing.” Forrester’s Nguyen also noted that the influence of two of the new members — xAI, owned by Elon Musk, along with Nvidia — could easily help with fundraising. Musk “with his connections, he does not make small quiet moves,” Nguyen said. “As for Nvidia, they are the face of AI. Everything they do attracts attention.” Info-Tech’s Bickley said that the astronomical dollars involved in genAI investments is mind-boggling. And yet even more investment is needed — a lot more.

IBM broadens access to Nvidia technology for enterprise AI

The IBM Storage Scale platform will support CAS and now will respond to queries using the extracted and augmented data, speeding up the communications between GPUs and storage using Nvidia BlueField-3 DPUs and Spectrum-X networking, IBM stated. The multimodal document data extraction workflow will also support Nvidia NeMo Retriever microservices. CAS will be embedded in the next update of IBM Fusion, which is planned for the second quarter of this year. Fusion simplifies the deployment and management of AI applications and works with Storage Scale, which will handle high-performance storage support for AI workloads, according to IBM. IBM Cloud instances with Nvidia GPUs In addition to the software news, IBM said its cloud customers can now use Nvidia H200 instances in the IBM Cloud environment. With increased memory bandwidth (1.4x higher than its predecessor) and capacity, the H200 Tensor Core can handle larger datasets, accelerating the training of large AI models and executing complex simulations, with high energy efficiency and low total cost of ownership, according to IBM. In addition, customers can use the power of the H200 to process large volumes of data in real time, enabling more accurate predictive analytics and data-driven decision-making, IBM stated. IBM Consulting capabilities with Nvidia Lastly, IBM Consulting is adding Nvidia Blueprint to its recently introduced AI Integration Service, which offers customers support for developing, building and running AI environments. Nvidia Blueprints offer a suite pre-validated, optimized, and documented reference architectures designed to simplify and accelerate the deployment of complex AI and data center infrastructure, according to Nvidia. The IBM AI Integration service already supports a number of third-party systems, including Oracle, Salesforce, SAP and ServiceNow environments.

Nvidia’s silicon photonics switches bring better power efficiency to AI data centers

Nvidia typically uses partnerships where appropriate, and the new switch design was done in collaboration with multiple vendors across different aspects, including creating the lasers, packaging, and other elements as part of the silicon photonics. Hundreds of patents were also included. Nvidia will licensing the innovations created to its partners and customers with the goal of scaling this model. Nvidia’s partner ecosystem includes TSMC, which provides advanced chip fabrication and 3D chip stacking to integrate silicon photonics into Nvidia’s hardware. Coherent, Eoptolink, Fabrinet, and Innolight are involved in the development, manufacturing, and supply of the transceivers. Additional partners include Browave, Coherent, Corning Incorporated, Fabrinet, Foxconn, Lumentum, SENKO, SPIL, Sumitomo Electric Industries, and TFC Communication. AI has transformed the way data centers are being designed. During his keynote at GTC, CEO Jensen Huang talked about the data center being the “new unit of compute,” which refers to the entire data center having to act like one massive server. That has driven compute to be primarily CPU based to being GPU centric. Now the network needs to evolve to ensure data is being fed to the GPUs at a speed they can process the data. The new co-packaged switches remove external parts, which have historically added a small amount of overhead to networking. Pre-AI this was negligible, but with AI, any slowness in the network leads to dollars being wasted.

Critical vulnerability in AMI MegaRAC BMC allows server takeover

“In disruptive or destructive attacks, attackers can leverage the often heterogeneous environments in data centers to potentially send malicious commands to every other BMC on the same management segment, forcing all devices to continually reboot in a way that victim operators cannot stop,” the Eclypsium researchers said. “In extreme scenarios, the net impact could be indefinite, unrecoverable downtime until and unless devices are re-provisioned.” BMC vulnerabilities and misconfigurations, including hardcoded credentials, have been of interest for attackers for over a decade. In 2022, security researchers found a malicious implant dubbed iLOBleed that was likely developed by an APT group and was being deployed through vulnerabilities in HPE iLO (HPE’s Integrated Lights-Out) BMC. In 2018, a ransomware group called JungleSec used default credentials for IPMI interfaces to compromise Linux servers. And back in 2016, Intel’s Active Management Technology (AMT) Serial-over-LAN (SOL) feature which is part of Intel’s Management Engine (Intel ME), was exploited by an APT group as a covert communication channel to transfer files. OEM, server manufacturers in control of patching AMI released an advisory and patches to its OEM partners, but affected users must wait for their server manufacturers to integrate them and release firmware updates. In addition to this vulnerability, AMI also patched a flaw tracked as CVE-2024-54084 that may lead to arbitrary code execution in its AptioV UEFI implementation. HPE and Lenovo have already released updates for their products that integrate AMI’s patch for CVE-2024-54085.

Microsoft will invest $80B in AI data centers in fiscal 2025

And Microsoft isn’t the only one that is ramping up its investments into AI-enabled data centers. Rival cloud service providers are all investing in either upgrading or opening new data centers to capture a larger chunk of business from developers and users of large language models (LLMs). In a report published in October 2024, Bloomberg Intelligence estimated that demand for generative AI would push Microsoft, AWS, Google, Oracle, Meta, and Apple would between them devote $200 billion to capex in 2025, up from $110 billion in 2023. Microsoft is one of the biggest spenders, followed closely by Google and AWS, Bloomberg Intelligence said. Its estimate of Microsoft’s capital spending on AI, at $62.4 billion for calendar 2025, is lower than Smith’s claim that the company will invest $80 billion in the fiscal year to June 30, 2025. Both figures, though, are way higher than Microsoft’s 2020 capital expenditure of “just” $17.6 billion. The majority of the increased spending is tied to cloud services and the expansion of AI infrastructure needed to provide compute capacity for OpenAI workloads. Separately, last October Amazon CEO Andy Jassy said his company planned total capex spend of $75 billion in 2024 and even more in 2025, with much of it going to AWS, its cloud computing division.

John Deere unveils more autonomous farm machines to address skill labor shortage

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Self-driving tractors might be the path to self-driving cars. John Deere has revealed a new line of autonomous machines and tech across agriculture, construction and commercial landscaping. The Moline, Illinois-based John Deere has been in business for 187 years, yet it’s been a regular as a non-tech company showing off technology at the big tech trade show in Las Vegas and is back at CES 2025 with more autonomous tractors and other vehicles. This is not something we usually cover, but John Deere has a lot of data that is interesting in the big picture of tech. The message from the company is that there aren’t enough skilled farm laborers to do the work that its customers need. It’s been a challenge for most of the last two decades, said Jahmy Hindman, CTO at John Deere, in a briefing. Much of the tech will come this fall and after that. He noted that the average farmer in the U.S. is over 58 and works 12 to 18 hours a day to grow food for us. And he said the American Farm Bureau Federation estimates there are roughly 2.4 million farm jobs that need to be filled annually; and the agricultural work force continues to shrink. (This is my hint to the anti-immigration crowd). John Deere’s autonomous 9RX Tractor. Farmers can oversee it using an app. While each of these industries experiences their own set of challenges, a commonality across all is skilled labor availability. In construction, about 80% percent of contractors struggle to find skilled labor. And in commercial landscaping, 86% of landscaping business owners can’t find labor to fill open positions, he said. “They have to figure out how to do

2025 playbook for enterprise AI success, from agents to evals

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More 2025 is poised to be a pivotal year for enterprise AI. The past year has seen rapid innovation, and this year will see the same. This has made it more critical than ever to revisit your AI strategy to stay competitive and create value for your customers. From scaling AI agents to optimizing costs, here are the five critical areas enterprises should prioritize for their AI strategy this year. 1. Agents: the next generation of automation AI agents are no longer theoretical. In 2025, they’re indispensable tools for enterprises looking to streamline operations and enhance customer interactions. Unlike traditional software, agents powered by large language models (LLMs) can make nuanced decisions, navigate complex multi-step tasks, and integrate seamlessly with tools and APIs. At the start of 2024, agents were not ready for prime time, making frustrating mistakes like hallucinating URLs. They started getting better as frontier large language models themselves improved. “Let me put it this way,” said Sam Witteveen, cofounder of Red Dragon, a company that develops agents for companies, and that recently reviewed the 48 agents it built last year. “Interestingly, the ones that we built at the start of the year, a lot of those worked way better at the end of the year just because the models got better.” Witteveen shared this in the video podcast we filmed to discuss these five big trends in detail. Models are getting better and hallucinating less, and they’re also being trained to do agentic tasks. Another feature that the model providers are researching is a way to use the LLM as a judge, and as models get cheaper (something we’ll cover below), companies can use three or more models to

OpenAI’s red teaming innovations define new essentials for security leaders in the AI era

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More OpenAI has taken a more aggressive approach to red teaming than its AI competitors, demonstrating its security teams’ advanced capabilities in two areas: multi-step reinforcement and external red teaming. OpenAI recently released two papers that set a new competitive standard for improving the quality, reliability and safety of AI models in these two techniques and more. The first paper, “OpenAI’s Approach to External Red Teaming for AI Models and Systems,” reports that specialized teams outside the company have proven effective in uncovering vulnerabilities that might otherwise have made it into a released model because in-house testing techniques may have missed them. In the second paper, “Diverse and Effective Red Teaming with Auto-Generated Rewards and Multi-Step Reinforcement Learning,” OpenAI introduces an automated framework that relies on iterative reinforcement learning to generate a broad spectrum of novel, wide-ranging attacks. Going all-in on red teaming pays practical, competitive dividends It’s encouraging to see competitive intensity in red teaming growing among AI companies. When Anthropic released its AI red team guidelines in June of last year, it joined AI providers including Google, Microsoft, Nvidia, OpenAI, and even the U.S.’s National Institute of Standards and Technology (NIST), which all had released red teaming frameworks. Investing heavily in red teaming yields tangible benefits for security leaders in any organization. OpenAI’s paper on external red teaming provides a detailed analysis of how the company strives to create specialized external teams that include cybersecurity and subject matter experts. The goal is to see if knowledgeable external teams can defeat models’ security perimeters and find gaps in their security, biases and controls that prompt-based testing couldn’t find. What makes OpenAI’s recent papers noteworthy is how well they define using human-in-the-middle