Entropy Exchange

Conversations as Code

Deterministic agentic problem solving with tool calls

We often end up devoting too much time perfecting LLM prompts or over-relying on LLMs to autonomously run the workflow for us end-to-end. In this article, we propose a…

How I Built NEON CIRCUIT: An Arcade Racer in a Few Working Days with an AI Agent

ai

claude-code

game-development

Play it now at nt-race.vercel.app.

Trust But Verify

A dashboard KPI can be wrong even when every source table is right. Nightly recompute of the dataset and widget layers, plus a detection layer that flags and routes what it finds, closes an observability gap table-level checks can’t reach.

databricks

data-engineering

data-quality

dashboards

monitoring

A business user notices a KPI is wrong before the data team does. The actual failure could be any of the following:

Redaction Is Not Enough: What Unity AI Gateway Solves for Healthcare AI, and What It Doesn’t

Unity AI Gateway closes most of the runtime governance gap for healthcare agents; a tokenizing DLP proxy at the MCP layer closes the rest.

AI

security

Databricks

agents

At Data + AI Summit 2026, Databricks closed the largest remaining open question in enterprise agent deployment: who governs what an agent does at runtime. The answer is…

Controlling Qwen’s thinking mode with serving controls for reliable local inference

Qwen’s thinking mode needed serving controls, not just a bigger token cap.

We recently set out to create a coding agent that could run on our local hardware without resorting to using any third-party APIs. This would be a great way to keep it all…

The Genie Trap: Three Patterns Hidden Inside Databricks’ AI Brand

A Synaptiq customer recently asked me whether they should use a Genie Agent or Genie Code to build an executive sales dashboard. The right answer was “neither, on its own.”…

Why fast models can still feel slow

Decode speed is only one part of agent performance; prefill, cache reuse, tool latency, and serving behavior shape the loop before the model writes a token.

My desk has been losing the hardware battle for years: a 3090, then Apple Silicon, then borrowed time on bigger boxes whenever I could arrange it. I told myself it was…

ML Pipelines With and Without Feature Stores

databricks

pipeline

featurestore

Feature engineering pipelines help you automate and modularize the process of turning your raw data into features that can be used to train your ML models. Specifically…

Why You Should Just Use A Feature Store

databricks

pipeline

featurestore

You can think of a Feature Store like a table specifically managed for ML pipelines. If you’re familiar with the Medallion Architecture, Feature Stores can be thought of as s…

OpenAI vs Gemini on Documents

ai

agents

documents

In the following section, we present a fictional dialogue between two advanced AI agents — Goodle Gen AI and OpenAI. These agents engage in an analytical discussion about…

Gemini API Starting Guide

ai

agents

gemini

The Google Gen AI SDK offers a standardized interface for interacting with Gemini models via both the Gemini Developer API and the Gemini API available on Vertex AI. With…

Reflexion Pattern for AI Agents

ai

agents

This Jupyter Notebook is designed to demonstrate a simple setup for querying and comparing responses from two large language models (LLMs): OpenAI’s GPT-4 and Google’s…

Why You Need a Data Catalog, and Why We Host Ours Within Databricks

databricks

data

Part 1: What is a data catalog?

How to Create Blog Posts for Entropy Exchange

guide

documentation

New blog contributors face an unclear publishing process → This guide provides step-by-step instructions for creating, previewing, and publishing posts on the Entropy…

Rick Montgomery

How to make a Chatbot in Databricks Apps as quickly as possible

But also continue working on it