All posts tagged: context

AI agents keep giving confident wrong answers. The context layer is enterprise AI’s next production problem.

AI agents keep giving confident wrong answers. The context layer is enterprise AI’s next production problem.

Published by skeptic

Enterprise AI agents have a new production failure mode, and it is not the model. As enterprises move from single-layer RAG to hybrid retrieval architectures, the same underlying data produces different answers depending on which agent, tool or system asks the question. Revenue means one thing in a business intelligence (BI) dashboard, something slightly different in a SQL table and something else again in an agent instruction. The retrieval infrastructure build-out of the past two years produced faster and cheaper vector search. It did not produce a shared definition of what the data means. At Snowflake Summit 26 in San Francisco, the data cloud vendor is taking a broad swing at that problem, with announcements spanning a Kafka-compatible managed streaming service called Data Stream, adaptive compute improvements, expanded Apache Iceberg interoperability and updates to its Cowork and CoCo agent and coding products. Running underneath all of it is a context layer: Horizon Context and Cortex Sense, a two-layer system designed to give agents a governed, shared definition of business logic across retrieval stacks. The context …

SQL query logs hold the context AI agents need to stop hallucinating joins

SQL query logs hold the context AI agents need to stop hallucinating joins

Published by skeptic

When Miro’s data team pointed AI agents directly at its Snowflake environment, the agents got the wrong answer more than 65% of the time. The problem wasn’t the model — it was context. With more than 10,000 tables and no semantic layer to guide routing, the agents had no way to know which data assets matched which business questions. DataHub is releasing a context intelligence layer Thursday that mines existing SQL query history to build a semantic index — and exposes it to agents via MCP, LangChain, Google’s Agent Development Kit and CrewAI. The company calls it Context Intelligence, and it’s built on the same query-log infrastructure DataHub has used for lineage tracking in production deployments worldwide. The company was founded by the team that built DataHub as an open source project at LinkedIn, where co-founder and CTO Shirshanka Das led data infrastructure for nearly 11 years. The open source project now has more than 15,000 contributors and 3,000 production deployments worldwide. “For the first time, enterprises can turn years of analyst query history into …

how to use RAG and an embedding model to stop wasting context

how to use RAG and an embedding model to stop wasting context

Published by skeptic

Local LLMs are fantastic, and they keep getting better at a staggering pace. I have non-negotiable reasons for preferring a local setup over relying on cloud giants like Claude or ChatGPT. Because of that, I’ve been relentlessly trying to integrate local models into my actual, day-to-day workflow. But as anyone who has tried will tell you, the DIY route comes with distinct caveats and drawbacks. The absolutely biggest hurdle is the context window. To get better responses from an LLM, we need to give it more context. But context is expensive. And as soon as the context window starts to fill up, the model starts to deteriorate in both speed and quality. So what are we supposed to do? The problem, I realized, was not the LLM itself. The problem was that I was using the LLM for a job it was never meant to do. And the fix was a tiny model I had completely ignored. LLMs and the problem of context It really is expensive Raghav Sethi/MakeUseOf Half of our experience with a …

No reinspections despite new context measure

No reinspections despite new context measure

Published by skeptic

Ofsted has defied calls to reinspect hundreds of schools already visited under its new framework once measures to better understand local context are introduced. The watchdog announced this week that, from September, as well as comparing a school’s performance to national averages, inspectors will also consider the performance of “similar schools”. It follows growing concern among school leaders that Ofsted’s new framework penalises schools with poorer cohorts because of its focus on attainment and use of national averages. Those concerns deepened when Ofsted acknowledged this week the “relationship” between disadvantage and performance against its ‘achievement’ judgment. Its analysis of more than 900 inspections conducted since November revealed schools with above-average free school meals rates are almost three times as likely as those with below-average levels to be graded ‘needs attention’ or ‘urgent improvement’ for achievement. Schools Week analysis of further data published by Ofsted on Wednesday suggested a similar pattern for attendance and behaviour – which also uses national averages to assess school performance. Almost one-quarter (24 per cent) of schools in the top quintile …

responses should focus on social context, not just mental health

responses should focus on social context, not just mental health

Published by skeptic

Around one in six adolescents worldwide report having self-harmed at some point in their lives. In England, an NHS mental health survey of 2,370 children and young people found that more than one in three young adults aged 17 to 24 had self-harmed. Typically, responses to self-harm focus on the individual – diagnosis, treatment and risk management. Mental health support is clearly essential, but a large and growing body of global research points to wider, social factors contributing to self-harm. Young people across different cultures describe self-harm less as a symptom of a specific “mental illness” and more as a response to unbearable pressures often linked to intense social challenges, relationship difficulties and changes as they develop into adulthood. These issues are raised in India, Pakistan and China. Even if these social drivers are well acknowledged, there is a lack of alignment between how distress is understood and how it is addressed. This mismatch has real consequences. Responses to youth self-harm that prioritise the individual may reduce immediate danger. However, approaches that prevent distress from …

Context architecture is replacing RAG as agentic AI pushes enterprise retrieval to its limits

Context architecture is replacing RAG as agentic AI pushes enterprise retrieval to its limits

Published by skeptic

Redis built its name as the caching layer that kept web applications from collapsing under load. The problem it is targeting now has the same structure but is harder to solve: production AI agents failing not because the models are wrong, but because the data underneath them is scattered, stale and structured for humans rather than machines. Retrieval pipelines built for single queries cannot absorb the volume agents generate. The gap Redis is targeting is structural: agents make orders of magnitude more data requests than human users, but most retrieval layers were built for the human-scale problem. Redis Iris, launched Monday, is the company’s answer: a context and memory platform that sits between an agent and the data it needs to act. The platform combines real-time data ingestion, a semantic interface that auto-generates MCP tools from business data models, and an agent memory server built on Redis Flex, a rewritten storage engine that runs 99% of data on flash at a tenth of the cost of in-memory storage alone. The announcement lands as enterprise RAG …

Why AI breaks without context — and how to fix it

Why AI breaks without context — and how to fix it

Published by skeptic

Presented by Zeta Global The gap between what AI promises and what it delivers is not subtle. The same model can produce precise, useful output in one system and generic, irrelevant results in another. The issue is not the model. It’s the context. Most enterprise systems were not built for how AI operates. Data is scattered across tools. Identity is inconsistent. Signals arrive late or not at all. Systems record events but fail to connect them into a continuous view. AI depends on that continuity. Without it, the model fills in the gaps so the result looks polished but lacks relevance. This is where most teams get stuck. A better model does not fix fragmented, stale, or commoditized data. Gartner estimates organizations lose an average of $12.9 million annually due to poor data quality. AI does not solve that problem, it surfaces it faster and at a greater scale. The mirror test There is a fast diagnostic test for this. Give your AI a perfect, high-intent customer signal and see what comes back. If the …

AI agents are missing all the discussions your team is having. SageOX has an answer: agentic context infrastructure

AI agents are missing all the discussions your team is having. SageOX has an answer: agentic context infrastructure

Published by skeptic

As AI model providers increasingly move downstream, launching products and agents for specific enterprise applications and sectors like finance, one big question still remains: how will said AI agents be equipped with the proper context surrounding a task — who assigned it, which other stakeholders are involved, what data or discussions have taken place about it and how it should be done? This practice of “context engineering” remains one of the great unsolved problems of the AI era. But SageOx, a Seattle-based startup founded by the veterans who built the original AWS EC2 and EBS infrastructure, believes it has the answer: a new systems layer it calls “agentic context infrastructure.” Using a combination of small hardware recording devices and the existing applications enterprises already rely on — Slack, email, documents, files — and applying new, open-source frameworks and instructions atop it all, SageOX has developed a system by which enterprises can keep agents as “in-the-loop” and updated on the enterprise’s tasks as their human employees are, and prevent them from “drifting” off their assigned tasks …

Salesforce’s Agentforce Vibes 2.0 targets a hidden failure: context overload in AI agents

Salesforce’s Agentforce Vibes 2.0 targets a hidden failure: context overload in AI agents

Published by skeptic

When startup fundraising platform VentureCrowd began deploying AI coding agents, they saw the same gains as other enterprises: they cut the front-end development cycle by 90% in some projects. However, it didn’t come easy or without a lot of trial and error.  VentureCrowd’s first challenge revolved around data and context quality, since Diego Mogollon, chief product officer at VentureCrowd, told VentureBeat that “agents reason against whatever data they can access at runtime” and would then be confidently “wrong” because they’re only basing their knowledge on the context given to them. Their other roadblock, like many others, was messy data and unclear processes. Similar to context, Mogollon said coding agents would amplify bad data, so the company had to build a well-structured codebase first.   “The challenges are rarely about the coding agents themselves; they are about everything around them,” said Mogollon. “It’s a context problem disguised as an AI problem, and it is the number one failure mode I see across agentic implementations.” Mogollon said VentureCrowd encountered several roadblocks in overhauling its software development.  VentureCrowd’s experience …

Social context influences dating preferences just as much as biological sex

Social context influences dating preferences just as much as biological sex

Published by José Betancourt

A recent study published in Evolution and Human Behavior suggests that a person’s socioeconomic background plays a massive role in shaping what they look for in a romantic partner. The findings provide evidence that the surrounding environment and access to resources often influence dating preferences just as much as biological sex. Ultimately, this research challenges rigid stereotypes about male and female behavior, showing that human mating strategies adapt fluidly to social conditions. Historically, evolutionary psychology has focused heavily on the biological differences between men and women when it comes to choosing a partner. The standard framework suggests that men tend to prioritize physical attractiveness to maximize reproductive success, while women tend to prioritize resources to ensure stability for offspring. However, human dating behavior is highly complex and responsive to environmental pressures. The authors of the new study wanted to better understand how resource availability and social standing interact with these biological predispositions. They wanted to see if people from different socioeconomic backgrounds adjusted their romantic preferences and their self-esteem to fit their specific life circumstances. …