Skip to main content
← All Tags

AI Engineering

65 articles in this category (Page 3 of 3)

AI NewsObservabilityAI Engineering

OpenTelemetry Standardizes LLM Tracing: Implementation Guide for GenAI Semantic Conventions

OpenTelemetry's new GenAI Semantic Conventions eliminate vendor lock-in by standardizing span naming and attributes for LLM calls across backends like Jaeger and Arize Phoenix.

Read more
AI NewsSoftware DevelopmentAI Engineering

Build Your First MCP Server in 10 Minutes with TypeScript

Learn to build a Model Context Protocol server with TypeScript and Zod to expose custom tools to AI assistants in just 30 lines of code.

Read more
AI NewsAI EngineeringDevOps

I Built a 35-Agent AI Coding Swarm That Runs Overnight

Engineer Mathew Dostal deployed a 35-agent AI swarm that completed 6,500+ coding runs and generated 124 PRs in a single session.

Read more
AI NewsmacOS DevelopmentAI Engineering

Engineering a macOS AI Agent: Lessons from Building Fazm with ScreenCaptureKit and Swift

Engineers developed Fazm, a macOS AI agent using ScreenCaptureKit and Accessibility APIs, achieving low-latency local execution by bypassing fragile vision-based OCR.

Read more
AI NewsDevOpsAI Engineering

Deploying OpenClaw AI Agents on Bare Metal: A Hetzner VPS Guide

Deploy OpenClaw on Hetzner Ubuntu arm64 by resolving systemd user service errors and configuring ACPX runtimes for autonomous operations.

Read more
AI NewsAI EngineeringDevOps

Harness Engineering: Why Scaffolding Outperforms AI Models in 2026

The same AI model scored 78% on a coding benchmark with a proper harness versus 42% without, proving scaffolding matters more than the model.

Read more
AI NewsAI EngineeringSoftware Testing

Testing AI Agents: A Framework for Preventing Production Failures

OpenAI's Operator made an unauthorized $31.43 purchase in 2025, highlighting why AI agents require behavioral testing beyond simple output evaluations.

Read more
AI NewsAI EngineeringDevOps

Automating LLM Drift Detection to Prevent Production Silent Failures

DriftWatch monitors LLM endpoints hourly to detect behavioral shifts, preventing silent failures like the GPT-4o drift reported in February 2025.

Read more
AI NewsAI EngineeringDevOps

Bridge the Prototype-to-Production Gap for Reliable AI Agents

AI agents often fail in production due to stale context and missing escalation rules despite passing initial manual testing phases.

Read more
AI NewsAI EngineeringSoftware Development

Tiered Context Loading: Reduce AI Agent Token Costs by 76%

Implement tiered context loading to cut AI agent token overhead by 60-80% and reduce monthly Sonnet costs from $198 to $48.

Read more
AI NewsAI EngineeringDevOps

Implementing Agentic Governance: Why Observability Is Not Control in AI Production

Agentic governance provides real-time enforcement of policies to prevent autonomous AI agents from exceeding budgets or leaking PII in production environments.

Read more
AI NewsAI EngineeringCloud Computing

Tracking AI Agent Costs with MCP: Introducing Agent Budget Guard

Water Woods launched Agent Budget Guard to monitor AI spending after a 260-call test resulted in $9.42 in daily API costs.

Read more
AI NewsAI EngineeringSoftware Architecture

Multi-Model AI Agent Architecture: Optimizing Cost and Performance

Reduce AI agent operation costs by up to 50% using a multi-model architecture that routes tasks to optimal models like GPT-4.1-mini and Claude Sonnet 4.6.

Read more
AI NewsAI EngineeringSoftware Development

Hydra Framework: Slashing Claude Code Costs by 50% with Agentic Specialization

Hydra optimizes Claude Code with 7 specialized agents, reducing API costs by 50% and boosting speed 3x through task-level speculative decoding.

Read more
AI NewsAI EngineeringSoftware Development

Optimizing OpenClaw: Strategies to Reduce Token Usage by 40%

Learn how the orchestrator pattern and modular file separation can reduce OpenClaw token consumption by 40% while improving agent reliability.

Read more
AI NewsSecurityAI Engineering

Security Analysis: 174 AI Agent Requests to a Public MCP Server

Analysis of 174 MCP requests reveals that 37.4% of servers lack auth and agents are already attempting credential extraction through social engineering.

Read more
AI NewsAI EngineeringWeb Development

Goose Desktop and Developer Extension Build Interactive Web App

AI-assisted development with Goose Desktop built an interactive choose-your-own-adventure winter wonderland web app with a single HTML file.

Read more