RAG and Knowledge Systems
Retrieval-augmented generation, enterprise search, vector databases, embeddings, document intelligence, and knowledge-grounded AI systems.
Graph-Shaped Skills Turn Agent Decision Traces Into Governed Procedures
Zachary Blumenfeld of Neo4j argues that agents become more predictable and governable when their procedures are represented as graphs, not left as instructions for a model to interpret. In his account, these graphs can encode decision steps, tool calls and escalation rules, while linking them to the data and past traces behind a decision. A loan-approval demo shows how Neo4j compiles policy and successful runs into a reusable procedure that constrains routing and makes each step inspectable.
A ChatGPT Plugin Tripled Registrations for Stack Overflow for Agents
Stack Overflow says registrations for its Stack Overflow for Agents product tripled overnight after it launched a ChatGPT plugin, which VP of Product Alexandra Lato attributes to easier setup for people already using ChatGPT. The company also reports that users created up to ten times more agents, a separate increase it does not tie to the registration jump. Lato says the product is intended to turn scattered workplace information into verified knowledge that people and AI agents can use.
Europe’s AI Strategy Depends on Building Local Compute and AI Factories
In his GTC Berlin keynote, NVIDIA CEO Jensen Huang argued that Europe’s AI economy will depend on producing intelligence, not just adopting AI services. He called for investment across the stack—from energy and computing to AI factories, models and applications—and presented NVIDIA’s hardware, software and partner ecosystem as infrastructure for that production. His case extended from industrial agents and robotics to secure runtimes and local workstations: AI, he said, requires systems built to run models, connect them to knowledge and tools, and put them to work.
AI Made Vanguard’s Legacy Ledger Research Queryable in 15 Minutes
Vanguard’s cash-ledger modernization required teams to move data, producers and consumers from a mainframe to the cloud while the system handled up to 30 million service calls a day. Gareth Yoder, who leads the cash program, says the migration’s research bottleneck eased when Vanguard made its COBOL code and database metadata queryable through AI tools: a question that once took a mainframe engineer seven days to answer could be resolved in 15 minutes. His broader case is that modernization also depends on usable migration documentation, incremental adoption and observability.
AI Evaluations Need Human Calibration Before They Can Gate Deployments
Tejas Kumar of IBM argues that AI evaluations should be treated as calibrated reliability checks, not as proof that a system works. In a customer-support example, a test passes an answer that wrongly approves a return because it contains the word “cannot”; an LLM judge can also mislead unless its verdicts are checked against human-labeled cases and the relevant policy. Kumar’s approach is to examine disagreements, refine the judge and dataset, and use measured agreement as a deployment gate.
AI Agents Need Business Context to Run Enterprise Software Reliably
SAP chief executive Christian Klein argues that AI will change how enterprise software is used, not make systems such as SAP’s obsolete: agents still need reliable business data, process knowledge and controls to handle consequential work. In an interview with Big Technology, he says those requirements make accuracy and fragmented company systems key limits on adoption, even as he expects agents to take on more tasks. Klein also expects jobs to shift, with companies needing to reskill workers and change how they organize work.
The Best Agent Workflows Start With Context, Guardrails, and Human Judgment
Charlie Holtz, co-founder and CEO of Conductor, argues that teams using coding agents should build around human judgment rather than treat software development as a factory line. His principles include staying close to new tools without chasing workflows that will soon become standard, protecting code and agent instructions with strict review, and giving agents access to organizational knowledge and persistent workspaces. The aim, he says, is for people to conduct teams of colleagues and agents, not simply manage automated production.
Data Agents Need Reviewed Semantic Context, Not Just Table Access
OpenAI argues that a useful data agent needs the same context a new analyst would receive, not just access to a warehouse. In its ChatGPT Work demonstration, the company shows how to combine Databricks tables, Slack discussions and metric documentation into a reusable semantic layer, then have a data expert review its definitions and rules before sharing it as a company plugin. The aim is to make the organization’s interpretation of metrics available alongside the underlying records.
Data Agents Need Governed Metric Definitions, Not Just Table Access
OpenAI’s data team argues that data agents need a governed semantic layer—not merely access to warehouse tables or SQL—to interpret metrics according to a company’s agreed definitions, populations, filters and source hierarchy. The team says organizations should reuse existing semantic work where possible, but have domain experts resolve contradictions and review the layer before distributing it as a shared skill. Maintaining that foundation is an ongoing governance responsibility, not a one-time plugin setup.
Agent Autonomy Makes Organizational Context an Engineering Requirement
Brandon Waselnuk of Unblocked argues that the main constraint on AI coding agents is not model intelligence but missing organizational context—the accumulated knowledge of conventions, decisions and incidents that human teammates acquire over time. In Unblocked’s same-prompt test, adding a context engine cut token use from 20.9 million to 10.8 million and reduced runtime from two hours and 33 minutes to 25 minutes. He contends that curated documentation and MCP access alone do not solve the problem, because agents need to weigh conflicting, current and permissioned information rather than merely retrieve it.
Insulin Testing Could Reveal Metabolic Risk Before Blood Sugar Rises
Dr Mark Hyman argues that US healthcare is built to treat diagnosed disease rather than identify the metabolic and nutritional problems that precede it. Through Function Health, Hyman is making the case for patient-held, longitudinal records that combine laboratory tests, imaging, wearables and medical history, with AI used to organize the data under clinician supervision. He says routinely overlooked measures such as insulin and ApoB can reveal risk hidden by normal blood-sugar readings, while warning that wider testing and GLP-1 use require careful interpretation, follow-up and muscle-preserving care.
Agentic Search Requires a New Payment Model for Publishers
Parallel Web Systems founder and CEO Parag Agrawal argues that AI agents will make the web’s human-centered search and advertising model untenable: they will query far more often than people, but cannot generate the clicks and conversions publishers rely on. His proposed alternative combines agent-oriented retrieval—ranked by task outcomes rather than human clicks—with a Shapley-value-inspired payment system that would compensate content owners for the value their material adds to an agent’s work.
Agent Memory Requires Extraction, Separate Stores, and Hybrid Retrieval
Alejandro Ao argues that persistent memory for AI agents is not a longer chat history or a single vector database, but a write-and-retrieve pipeline that extracts durable claims, stores them alongside entity links and recent context, then ranks them for later use. In his walkthrough of Mem0, semantic search supplies the candidate set while BM25 and entity-based signals rerank it; that design makes the vector index the system’s gatekeeper. Ao’s practical case is that the architecture can run locally with small extraction models and open embedding models.
ChatGPT Uses Desktop Activity History to Recover Work Context
OpenAI’s Dominik Kundel presents Computer History as an opt-in Mac desktop feature that turns interaction events into an agent-readable record of recent work for ChatGPT and Codex. Rather than recording screens or audio, it tracks actions such as typing, clicking and app switching so users can refer to “that doc” or an earlier conversation without rebuilding context. Kundel says users can inspect, delete, pause or narrow the history, while ChatGPT can use it to suggest reusable skills and automations from recurring workflows.
AI Product Differentiation Is Shifting From Interfaces to Intelligence
Sequoia Capital partner Sonya Huang argues that companies should decide which AI capabilities to own down to the model weights and which to rent from frontier providers, rather than treating sovereignty as an all-or-nothing choice. Her test is whether cost, latency, domain-specific performance and proprietary data make intelligence central enough to control. As open-weight models approach frontier performance, Huang says application companies can use their data, evaluations and production feedback to build specialized systems that outperform general APIs in their domains.
Enterprise Agents Route Tasks Across Specialized And Frontier Models
NVIDIA argues that enterprise AI agents should route work across multiple models rather than rely on a single general-purpose system. In its example of Glean, a specialized model gathers context from enterprise sources and handles straightforward requests, while frontier models are used for complex analysis involving tools, multiple sources, or deeper reasoning. NVIDIA says this division can reduce latency and token use while preserving answer quality, though the performance figures are presented as Glean claims.
Longer Agent Task Horizons Still Fall Short of Dependable Autonomy
Stanford’s Aakanksha Chowdhery argues that longer agent task horizons should not be mistaken for dependable autonomy. Her CS329A lecture distinguishes among benchmarks that measure how long agents can complete tasks at given reliability levels, whether their outputs match professional work, and whether they can synthesize research with verifiable evidence. Across those measures, the central limitation is persistent: agents improve on well-specified tasks but remain unreliable when success requires recovery, organizational context, or judgment about what work needs doing.
Phasing Out Fossil Fuels Delivers Immediate Public-Health Benefits
Edward Maibach argues that phasing out fossil fuels should be treated as an immediate public-health intervention, not only a response to future climate risks. Alongside pediatrician Lisa Patel, sanitation advocate Catherine Coleman Flowers and air-quality entrepreneur Darren Riley, he points to local benefits—from fewer asthma exposures near schools and in homes to safer water during floods—that can make decarbonization a more concrete policy choice.
The 1% Rule for Finding Durable AI Opportunities
Google chief scientist Jeff Dean argues that AI founders should test frontier models on the workflows they hope to build around: if a general model already succeeds meaningfully, rapid model improvement may erase the opportunity. More durable openings, he says, are tasks where the model succeeds only 0% or 1% of the time and where a small team can add private context, distinct data, specialized models or better evaluation loops. The larger question is whether that advantage will persist long enough—and whether solving the problem matters.
New Transcription Models Separate Batch Processing From Live Speech
OpenAI introduces gpt-transcribe for completed audio files and gpt-live-transcribe for streaming speech, arguing that the choice depends on when an application needs the text rather than on a general performance hierarchy. The company says both models support 57 languages and can be guided with custom vocabulary and language hints, while handling accents, multilingual speech, names, numbers and background noise. It positions the batch model for recordings that feed search, summaries and follow-on workflows, and the live model for captions, dictation and voice interfaces.
Revenue Intelligence Turns Sales Signals Into Weekly Operating Decisions
OpenAI presents ChatGPT Work as a revenue intelligence system that turns customer conversations, seller activity and market signals into a recurring learning loop for sales leaders. In its Blossom Systems example, weekly reports surface risks in large deals, competitive threats, capacity gaps and high-performing rep behaviours; leaders can then interrogate the supporting evidence and send proposed, owned actions through Slack. The company’s argument is that the value lies not in a dashboard, but in feeding decisions and their results back into the next reporting cycle.
Telemetry Files Turn Coding Agents Into First-Response Investigators
Jason Lopatecki of Arize argues that the constraint on agent-driven software repair is no longer generating code but assembling enough production evidence to trust a fix. His proposed loop has agents retrieve traces, logs and evaluations into the repository as files, investigate the execution path that actually failed, and produce a pull request for human review. The model shifts engineers from initial incident response toward review, though Lopatecki says larger changes still require human direction.
AI Agents Need Bounded Loops, Observable Goals, and Approval Boundaries
OpenAI developer-experience lead Jason Liu argues that Codex is most useful when treated as a set of durable, bounded workstreams rather than a succession of disposable chats. His model starts with a pinned thread that retains context and reports on a defined condition, then adds persistent goals only where completion can be verified, and durable memory, skills and broader computer control only when repeated work warrants them. The governing constraint is explicit: give the system enough context to prepare useful work, but keep action and approval boundaries clear.
Vector Search Finds Similar Facts, Graphs Establish Their Relationships
Stephen Chin of Neo4j argues that agent memory should represent relationships, not just retrieve similar text. In a homelab test built from the same Markdown source material, a graph-backed agent identified an internet-exposed Minecraft server running Debian 8 and found WAN-exposed management services, while a vector-backed agent could not connect the relevant facts. Chin’s proposed GraphRAG approach uses vectors to find starting points, then traverses stored entities and relationships to produce answers that can be inspected and audited.