Posts
All the articles I've posted.
- 10 MIN READ•Mar 7, 2026
Context Management Strategies for Google Antigravity: A Complete Guide to the Agent-First IDE
Google Antigravity is an agent-first IDE built by Google DeepMind's Advanced Agentic Coding team. It approaches context management differently from other AI ...
AI toolscontext managementprompt engineering - 11 MIN READ•Mar 7, 2026
Context Management Strategies for Gemini CLI: A Complete Guide to Terminal-Native AI Development
Gemini CLI is an open-source terminal agent powered by Gemini models that operates directly in your command line. It brings Google's AI capabilities into the...
AI toolscontext managementprompt engineering - 11 MIN READ•Mar 7, 2026
Context Management Strategies for Gemini Web and NotebookLM: A Complete Guide to Google's AI Knowledge Ecosystem
Google's AI ecosystem for knowledge work consists of two deeply integrated tools: Gemini (the conversational AI at gemini.google.com) and NotebookLM (the res...
AI toolscontext managementprompt engineering - 11 MIN READ•Mar 7, 2026
Context Management Strategies for Claude Code: A Complete Guide for Developers
Claude Code is a terminal-native agentic coding assistant that lives in your command line and operates directly on your codebase. Unlike chat-based interface...
AI toolscontext managementprompt engineering - 11 MIN READ•Mar 7, 2026
Context Management Strategies for Claude CoWork: A Complete Guide for Knowledge Workers
Claude CoWork represents a fundamentally different approach to AI context management. Unlike chat interfaces where you send messages and receive responses, C...
AI toolscontext managementprompt engineering - 4 MIN READ•Mar 7, 2026
Agentic Analytics on the Apache Lakehouse
If you grant a Large Language Model direct access to a raw Amazon S3 bucket filled with Parquet files, it will fail to answer your business questions....
data lakehouseapache icebergapache parquet - 4 MIN READ•Mar 7, 2026
What is Apache Arrow? Erasing the Serialization Tax
If you pull a million records from a database into a Python notebook, the query runs instantly, but the transfer feels endlessly slow. Your compute en...
data lakehouseapache icebergapache parquet - 5 MIN READ•Mar 7, 2026
What is Apache Iceberg? The Table Format Revolution
If you drop ten thousand Parquet files into an S3 bucket, you have a data swamp. You do not have a database. To run SQL queries against those files sa...
data lakehouseapache icebergapache parquet - 4 MIN READ•Mar 7, 2026
What is Apache Parquet? Columns, Encoding, and Performance
If you ask a data analyst to calculate the average transaction amount for the month of July using a massive CSV file, the compute engine must read eve...
data lakehouseapache icebergapache parquet - 21 MIN READ•Mar 7, 2026
What is Apache Polaris? Unifying the Iceberg Ecosystem
Treating thousands of Parquet files as a unified database table requires a brain. Apache Iceberg provides the metadata structure to do this, but the Iceberg specification alone does not manage security roles, handle network requests, or broker credentials. You need an open catalog service to orchestrate those root metadata pointers. Apache Polaris serves as that open-source, vendor-neutral brain. This comprehensive guide explains the catalog fragmentation war, open governance under the Apache Software Foundation, role-based access control hierarchies, credential vending vs IAM sprawl, and how Polaris powers Dremio's agentic query acceleration.
data lakehouseapache icebergapache parquet - 6 MIN READ•Mar 7, 2026
Apache Software Foundation: History, Purpose, and Process
If you build a modern data lakehouse, you inevitably stack Apache Iceberg, Apache Parquet, and Apache Arrow. These projects dictate how you store, que...
data lakehouseapache icebergapache parquet - 4 MIN READ•Mar 7, 2026
Assembling the Apache Lakehouse: The Modular Architecture
For decades, the standard data architecture was monolithic. When you bought a data warehouse, you bought a single box where the vendor tightly coupled...
data lakehouseapache icebergapache parquet