MC+A

You are going to need a bigger boat. How big of a boat...well...that's the real question. Michael Cizmar discusses sizing formulas for your retrieval workloads in Elastic

How to Create a Sizing Formula for Your Elasticsearch Queries This article dives into Elasticsearch Cluster Query Performance and explains the Math behind the Latency.

For over two decades, we’ve been the engineering backbone behind enterprise innovation.

As AI reshapes how organizations operate, you need more than strategy, you need deep technical expertise to build scalable, secure AI foundations that actually work at enterprise scale.

Had enough of proof-of-concepts that never go live?

We reopened the Kennedy files, this time with AI.

Using document intelligence, we uncovered hidden connections.

We presented this Enterprise Search and Discovery 2025. Curious to know more?You can still see how our approach to AI-driven discovery can be applied to your own data.
https://lnkd.in/gCn4THD2

Tip for the day: Friends don't let friends use their DB as the primary search engine for an ecommerce platform.

Why PostgreSQL Search Isn’t Enough: A Case for Purpose-Built Retrieval Systems Postgres is a great database — but it’s not a search engine.Instacart’s recent move to consolidate search on Postgres highlights the risks: poor autocomplete, weak ranking, and frustrated users.If relevancy drives revenue, you need purpose-built retrieval systems like Elasticsearch, OpenSearch...

This week's insight article:
+ Layered Ranking for Applications
+ Swama: A Locally Optimized Ex*****on Platform for macOS
+ ES|QL COMPLETION Command: Generating Creative Output with an LLM

MC+A Digest - Sept 2 2025 - Discover Layered Ranking for RAG Applications & More Vespa has announced a new layered ranking system for Retrieval-Augmented Generation (RAG) applications. This innovation aims to enhance context engineering at scale.

This week's insight article:
+ B2B E-commerce Industry Report
+ Search is Back!
+ Our initial post on the Kennedy Files using to predict near document duplicates ( )

Explore the Latest: Search is Back! (Did it ever leave?), Kennedy Files, & B2B EComm Jo Kristian Bergum metions "We have finally moved past the vector DB concept and back to the search engine concept." which we whole heartly agree.  The paper which introduces Seaerch-R1 in "Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning".  This highlight...