News
AI has a sprawling data problem. Airbyte has just launched a tool to fix it.
1+ hour, 43+ min ago (27+ words) Airbyte has launched Airbyte Agents, a new service with a Context Store that pre-indexes business data so AI agents can query it without live API calls....
Lovelace emerges from stealth with context engine that claims 1000x AI investigative power
1+ week, 6+ hour ago (665+ words) Lovelace founder Andrew Moore says enterprise AI keeps failing investigative tasks. His answer is a context engine that claims 1000x the investigative power at 1/1000th the token cost " built for environments where being wrong is not an option....
Jaeger adopts Open Telemetry at its core to solve the AI agent observability gap
1+ week, 3+ day ago (572+ words) By adopting the Model Context Protocol (MCP), Agent Client Protocol (ACP), and Agent'User Interaction Protocol (AG-UI), the project is building an environment where engineers and AI agents can collaborate." Managing AI workloads requires an efficient data collection pipeline. This need…...
Vectors gave us AI search, tensors are going to make it smarter
1+ week, 4+ day ago (383+ words) If you've paid AI any mind in the last few years, you've heard of vectors. They are easy to understand: A vector is a single, ordered list of numbers that represent something. You can turn a paragraph into a vector,…...
Cursor and Chainguard partner to lock down the AI agent supply chain
1+ week, 4+ day ago (398+ words) Cursor and Chainguard are setting their sights on securing the open source dependency chain in AI-generated code " a problem that has grown sharper as agentic development moves from experiment to production. The partnership, announced this week, gives Cursor access to…...
Postgres to Iceberg in 13 minutes: How Supermetal compares to Flink, Kafka Connect, and Spark
2+ week, 6+ day ago (1701+ words) Supermetal recently added Iceberg sink support, and I wanted to take it for a spin. A couple of months ago, I tested the newly announced Kafka sink, so you can think about this post as a continuation of this blog…...
Kumo's new foundation model replaces months of data science engineering with plain-English queries
3+ week, 3+ hour ago (830+ words) Large language models are very good at predicting the next word in a sequence. That's because they've been trained on massive amounts of unstructured text " books, web pages, code. But enterprise data looks different. It lives in relational databases: rows…...
How to build an AI-powered private document search app with RAG, Chroma DB, and memory
3+ week, 4+ day ago (817+ words) As AI advances, more tools are being introduced into the ecosystem, enabling engineers and developers to experiment and build custom AI apps. But it's not that simple." In fact, each advantage of AI is accompanied by a disadvantage. For example,…...
Niantic Spatial wants to map the 80% of the economy AI can't see
3+ week, 5+ day ago (778+ words) By now, we're all generally familiar with large language models (LLMs) and the core use of text in predictive, generative, and agentic AI services. As automated intelligence services now diversify, our attention turns to large image/vision models, large audio…...
Moving beyond the "magic scaling sauce" myth
1+ mon, 3+ day ago (407+ words) Even if a system is working reliably today, that doesn't mean it will necessarily work reliably in the future. One common reason for degradation is increased load. Perhaps the system has grown from 10, 000 concurrent users to 100, 000 concurrent users, or from…...