Claude Programming Tutorials & Engineering Articles

An agent can finish a task and still take an inefficient path. A failed search can trigger another search. A truncated file read can lead to a command fetching…

Stripe built an agentic payment method factory from over 100 reusable prompts, hardened by agents observing implementation runs, and kept them current by feeding back each run's learnings.

Vision-language models have made it possible to build visual AI agents that understand video at production scale. The harder problem is turning that capability…

The chDB Durable Layer keeps agent memory fast to query locally while making its analytical state recoverable across laptops, CI jobs, and short-lived sandboxes.

AI agents can be given a goal, write code, use tools, and keep working as new information becomes available. This opens the door to applications that…

ClickHouse 26.9 introduces conditional LIMIT boundaries, incremental refreshes for append-only materialized views, disk spilling for DISTINCT, time-limited tokens, and faster min/max/count queries.

An AI coding agent’s patch can pass tests yet fail when the server loads a real model and handles requests. Evaluating changes to inference-serving software…

Agentic AI workflows can be used to prepare and validate digital twins for physical AI systems. Agents can inspect 3D scenes, author simulation-relevant data in…

OCA investigates incidents, recommends next steps, posts to Slack, answers follow-up questions, and prepares code fixes. Here's what OCA is like to use and how we built it.

Sprites are a place to run agents; the first thing you should think to do with a new Sprite is to type claude (or gemini or codex). We’ve put a lot of effort into making sure coding agents feel safe and happy when they’re on Sprites, because, to (pro

We took 201 real analytics questions from our production data warehouse, benchmarked 28 models on correctness, cost, and speed, and released an open harness so you can run the same test on your own.

Agentic AI is changing how research is done. AI scientists can read papers, propose hypotheses, call models, and determine which experiments to prioritize next.

After claims that ClickHouse is “winning the observability wars” sparked debate, we reflect on why it has become a leading storage and query engine, where it still falls short, and why winning the database layer isn’t the same as winning observability.

Navigation enables a robot to turn perception and motion into purposeful autonomy. Unlike locomotion, which produces stable movement, navigation must be used to…

AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents…

AI factories are interconnected systems where fleet economics depend on how efficiently the entire stack converts power and capital into completed agent tasks.

A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context…

As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important.

AI agents are only as effective as the context they receive. Even with capable models and well-documented NVIDIA libraries, agents can spend extra steps finding…

Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the…

Learn how NVIDIA NeMo Switchyard routes AI agent workloads across models using tuning-free and tunable routers that balance model capability, cost, and latency.

Agent Plugins 1.0.0 is a new, vendor-neutral directory specification—backed by Google, Amazon, Microsoft, and others—for packaging Agent Skills and MCP servers into a single portable unit. By standardizing the manifest (plugin.json) and utilizing a fixed directory layout, it eliminates the need for developers to maintain separate wrappers or configurations to support different AI coding agents and IDEs. Google has officially joined as a Core Maintainer and already rolled out support in the Agents CLI and Data Agent Kit, allowing developers to start building and distributing interoperable plugins today.

Google Cloud API Gateway now offers a model routing feature in Public Preview, allowing developers to dynamically route traffic to models like Gemini, Claude, or OpenAI OSS-GPT without hardcoding endpoints or managing open-source proxies. Developers can easily configure these routing rules directly within their OpenAPI 3.x specifications by mapping virtual model names to specific backend targets on a shared host. Once deployed, the Gateway acts as a serverless ingress layer that accepts standard OpenAI-compatible requests, automatically transcodes the payload to the native schema of the target model, and routes the traffic on the fly.

Agent Platform's evaluation service is now generally available, providing developers with a unified engine to measure agent quality consistently across local development experiments and live production traffic. You can evaluate agents using over 20 pre-built metrics, DeepMind-backed adaptive rubrics, or custom code-based and LLM-as-a-judge metrics stored in a centralized, versioned registry. The service integrates directly into existing workflows via the Agent Platform SDK, agents-cli, and ADK, offering built-in user and environment simulators to automate complex multi-turn testing and streamline CI pipelines.

Stripe's Knowledge AI Platform is our versatile AI agent platform built to handle diverse non-coding knowledge work, from quick queries to complex, multi-day projects. By connecting employees to over 1,000 internal tools and skills, it enables secure, enterprise-scale productivity across the organization.

One user turn can contain many model and tool iterations. Any cost inside the repeated region can be paid many times.

Oxide joins Anthropic's Project Glasswing, applying Claude Mythos 5 to find and patch vulnerabilities across its open-source stack, firmware to network.

We have relaunched clickhouse.com/docs on Mintlify, with a redesigned search and Ask AI experience, a docs MCP server, simpler navigation, an interactive API playground, and expanded localization — built for both human readers and the coding agents

NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they…

A behind-the-scenes look at hdx-evals, the open-source framework we built to benchmark the ClickStack MCP server against a raw SQL baseline using deterministic synthetic incidents, sandboxed Claude agents, and blind LLM grading — and why the MCP scored hi

How our LLM gateway uses Thompson sampling over lognormal latency posteriors to pick the fastest, most reliable model route per request

Search and uncover technology trends across 10 billion GitHub events in real time.

This post shows a lightweight metrics layer for ClickHouse using MooseStack, an open source developer agent harness for ClickHouse.

How to remain competitive in the AI era of software engineering

Retention limits, sampling, and metric roll-ups aren't observability best practices - they're workarounds for storage systems that can't handle full-fidelity data, and they're becoming a hard blocker for AI-driven workflows.