JSON Programming Tutorials & Engineering Articles

The article discusses how PeerDB facilitates large-scale PostgreSQL migrations, specifically achieving a 1TB migration in just 2 hours.

Cursor has expanded its long-running agents research preview to all Ultra, Teams, and Enterprise users, enabling autonomous AI agents that can work on ambitious coding tasks for hours or even days.

Google introduces extension settings for Gemini CLI, a structured configuration system that prompts users for required settings (API keys, URLs, project IDs) during extension installation.

Google has launched a hosted Data Commons MCP (Model Context Protocol) service on Google Cloud Platform, eliminating the need for local Python environments.

This article provides a comprehensive guide on building license-compliant synthetic data pipelines for AI model distillation using NVIDIA's NeMo Data Designer and OpenRouter.

The article provides a comprehensive guide on building a document processing pipeline using NVIDIA Nemotron RAG, focusing on the extraction of structured data from complex documents like PDFs.

This article explains how OpenAI built the Codex App Server, a bidirectional JSON-RPC API that serves as the critical link between the Codex harness (agent loop and logic) and various client surfac...

This article profiles three small businesses—a seed farm in South Carolina, a tamale shop in California, and a salvage yard in Nevada—that use ChatGPT to streamline daily operations, solve problems...

This article discusses the engineering of LinkedIn's job ingestion system, which processes millions of job postings daily from various sources.

This article demonstrates how to port a Matrix homeserver from traditional infrastructure (Synapse on VPS) to Cloudflare Workers, creating a serverless, zero-maintenance deployment with automatic p...

The article discusses how LinkedIn developed the Contextual Agent Playbooks & Tools (CAPT) to enhance AI coding agents with organizational context, enabling them to better assist engineers in their...

This article introduces Gemini CLI hooks, a customization mechanism that lets developers control and extend the agentic loop of Gemini CLI without modifying its source code.

The article discusses Palantir's approach to managing and securing VS Code extensions at scale, highlighting the security risks posed by IDE extensions and detailing the implementation of a compreh...

This article explains the core agent loop architecture behind OpenAI's Codex CLI, detailing how it orchestrates interactions between users, LLM models, and tools to perform software engineering tas...

This article demonstrates how to fine-tune FunctionGemma, a specialized 270M parameter Gemma 3 model designed for function calling in agentic AI systems.

This article explores how to train an AI agent to operate a new Command Line Interface (CLI) using synthetic data generation and reinforcement learning.

ClickHouse 25.

The Universal Commerce Protocol (UCP) is an open-source standard developed by Google to facilitate seamless commerce experiences across various platforms.

Shopify introduces the Universal Commerce Protocol (UCP), an open standard co-developed with Google that enables AI agents to discover, negotiate, and transact with any merchant.

This article provides a comprehensive tutorial on building an AI-powered catalog enrichment system that enhances e-commerce product listings using NVIDIA's advanced models.

The article discusses the NVIDIA Multi-Agent Intelligent Warehouse (MAIW), an AI command layer designed to enhance operational efficiency and supply chain intelligence in automated warehouses.

This article discusses best practices for coding with agents, specifically focusing on techniques for utilizing Cursor's agent effectively.

The article discusses the development of chDB, a Python library that integrates ClickHouse with Pandas DataFrames for high-performance SQL querying.

The article reviews the significant developments and features introduced in ClickStack over its first seven months since launch, highlighting advancements such as JSON support, integration with Cli...

The article discusses dynamic context discovery, a method for optimizing how coding agents gather relevant context while minimizing token usage.

The article discusses the advancements in agentic AI with Gemini 3, emphasizing its role as a core orchestrator for complex workflows.

The article discusses key benchmarks conducted over the past year that reveal insights into performance optimization in ClickHouse.

The article introduces A2UI, an open-source project designed for agent-driven interfaces that allows agents to generate contextually relevant user interfaces.

The article discusses ClickHouse's journey of integrating Rust into its predominantly C++ codebase without undertaking a complete rewrite.

The article discusses the NCCL Inspector, a profiling and analysis tool designed to enhance communication observability for AI workloads using the NVIDIA Collective Communication Library (NCCL).

The article discusses the new Session Management feature in Gemini CLI, which allows users to automatically save their sessions and resume work without losing context.

The article discusses the importance of protecting sensitive data during processing in cloud environments, introducing Google Cloud's Confidential Space as a solution.

This article demonstrates how to build production-ready Stripe subscription billing using Kiro, an AI-powered IDE with domain-specific 'powers' that bundle Stripe best practices, MCP servers, and a...

The article discusses the evolution of AI agent development, emphasizing the need for efficient context management in multi-agent systems.

The article discusses the use of AI Model Distillation to create efficient financial data workflows, focusing on the optimization of large language models (LLMs) for applications in quantitative fi...

The article discusses how to scale data generation for physical AI using the NVIDIA Cosmos Cookbook, which provides comprehensive recipes for synthetic data generation and augmentation.

Slack's Security Engineering team describes how they built an AI agent-based system to automate and streamline security investigations.

This article provides a detailed analysis of how the five major cloud data warehouses—Snowflake, Databricks, ClickHouse Cloud, Google BigQuery, and Amazon Redshift Serverless—calculate compute cost...

The article discusses the challenges and solutions for developing long-running AI agents, particularly focusing on the Claude Agent SDK.

This article discusses the transition from OpenTelemetry (OTel) to Rotel, an open-source Rust project that enhances tracing capabilities at petabyte scale.

The article discusses the launch of Black Forest Lab's FLUX. 2 [dev] model, which enhances image generation capabilities on Cloudflare's Workers AI platform.

The article discusses the latest updates to the Gemini API for Gemini 3, highlighting its advanced reasoning, coding capabilities, and multimodal understanding.

The article introduces advanced tool use features on the Claude Developer Platform, focusing on enabling AI agents to utilize tools more efficiently.

Ceilometer is Uber's adaptive benchmarking framework designed to enhance the performance and reliability of their infrastructure by automating benchmarking processes and providing actionable insigh...

The article details the journey of upgrading the chDB kernel from ClickHouse v25. 5 to v25. 8. 2.

The article discusses the development of StockHouse, a real-time market analytics application that leverages ClickHouse, Massive, and Perspective to handle high-frequency financial data.

The article discusses the challenges of identifying the root cause of configuration management failures using Salt at Cloudflare, particularly when dealing with a high volume of changes across nume...

The article discusses the release of NVIDIA Collective Communications Library (NCCL) 2.

The article announces the introduction of User Simulation in the Agent Development Kit (ADK), a feature designed to simplify the testing of conversational agents by allowing developers to define hi...

Thomas Ptacek argues that every developer should build an LLM agent to truly understand the technology, demonstrating through progressive Python code examples that a functional agent with tool use ...