Blog
AI engineering insights, practical advice, and things I'm learning.
Ai Engineering
How to Export Custom Geospatial Embeddings via OlmoEarth Studio
Learn how to extract custom Earth observation embedding vectors as Cloud-Optimized GeoTIFFs using the new export workflow in OlmoEarth Studio.
Geospatial Ai · Embedding Extraction · Earth Observation · Cloud Optimized Geotiff
Ai Engineering
How to Run Gemma 4 E2B on Raspberry Pi 5 with LiteRT
Deploy the Gemma 4 E2B model locally on a Raspberry Pi 5 using the LiteRT-LM runtime for real-time edge workflows and robotics.
Edge Ai · Raspberry Pi · Litert
Ai Engineering
How to Distill Large Models With CompactifAI Top-K Logits
Learn how to use Multiverse Computing's CompactifAI to distill large language models locally using offline Top-K logits and Fused Chunked KL loss.
Knowledge Distillation · Large Language Models · Model Compression
Ai Agents
How to Deploy Claude Code Auto Mode in Production
Learn how to configure Claude Code's auto mode to run unattended agent workflows, set up defense-in-depth tool guards, and manage the safety classifier.
Claude Code · Autonomous Agents · Production Deployment
Ai Engineering
Why Local AI Belongs in Your Personal Tech Stack
Cloud AI access is conditional. A local model gives you a private, offline capability that remains available when networks and providers fail.
Local Ai · On Device Ai · Offline Ai
Ai Engineering
How to Audit a Local AI App's Privacy
A practical audit for local AI inference, storage, network requests, optional tools, encryption, deletion, and offline behavior.
Local Ai · Privacy · On Device Ai
Ai Coding
How to run Claude Code locally with self-hosted containers
Deploy Claude Code v1.4.0 execution environments to your own infrastructure to secure agent workflows and reduce file operation latency.
Claude Code · Self Hosting · Containerization
Ai Coding
How to Cut Token Costs with the Cursor Compass Router
You will learn how to configure Cursor's request-level routing modes to reduce inference costs while maintaining frontier model performance.
Cursor Editor · Token Optimization · Model Routing
Ai Agents
How to Build Portable Tools With Agent Plugins 1.0.0
Learn how to structure skills and MCP servers into a single Agent Plugin package that works natively across Cursor, Copilot, and Google Agents CLI.
Mcp Servers · Agent Plugins · Cursor Editor
Ai Agents
How to Expose Site Tools to Agents With Cloudflare WebMCP
Cloudflare WebMCP lets you expose structured tools to browser-based AI agents without changing your origin code. Learn how to configure and register tools.
Cloudflare Webmcp · Ai Tool Calling · Agentic Workflows
Ai Agents
How to Secure MCP Servers With Cloudflare WriteGuard
Configure Cloudflare WriteGuard to enforce granular access policies, audit agent actions, and implement human-in-the-loop approvals for your MCP servers.
Mcp Protocol · Cloud Security · Cloudflare Writeguard
Ai Agents
How to Deploy AI Agents With Cloudflare OS
Cloudflare OS lets you build secure AI applications and deploy automated agents within your own infrastructure.
Cloudflare Os · Agentic Workflows · Deployment Infrastructure
Ai Agents
How to Build Self-Debugging AI Agents With Cloudflare ADLC
Learn how to deploy, debug, and manage autonomous coding workflows using Cloudflare's new Agent Development Lifecycle and Local Explorer API tools.
Cloudflare Adlc · Autonomous Workflows · Agentic Systems
Ai Agents
How to Scale Real-Time Agents With Session-Aware Load Balancing
Manage long-lived multimodal AI streams and prevent dropped connections by implementing application-level session tracking in your routing architecture.
Real Time Ai · Load Balancing · Multimodal Streams
Ai Agents
How to Orchestrate AI Agent Runtimes With @cloudflare/computer
Learn to deploy and scale autonomous AI agents using @cloudflare/computer to dynamically switch between fast isolates and full Linux containers.
Cloudflare Computer · Agentic Infrastructure · Serverless Runtimes
Ai Agents
How to Build Modular Agent Skills in Genkit Go
Learn how to package agent capabilities into modular bundles using Genkit Go to reduce token consumption and prevent context window bloat.
Genkit Go · Modular Agents · Token Optimization
Ai Engineering
How to Profile Cloud TPUs With Google's Microbenchmark Suite
Learn how to measure interconnect latency, compute throughput, and memory bandwidth on Cloud TPUs to establish a Roofline model for your workloads.
Cloud Tpu · Performance Profiling · Benchmarking
Prompt Engineering
How to Build Context Stacks for Claude Opus 5
Learn how to configure three-layer context stacks, minimize reasoning noise, and manage dynamic tools for Claude Opus 5.
Context Engineering · Claude Opus 5 · Prompt Optimization
Ai Coding
How to Build Claude Code Verification Loops With Skills
Learn how to use Claude Code skills to design iterative verification loops that autonomously run tests and fix errors before returning a response.
Claude Code · Autonomous Agents · Iterative Testing
Ai Engineering
How to Run TPU Workloads on Google Cloud with Ray 2.55
Learn how to provision Google Cloud TPUs, handle slice topologies, and deploy machine learning models using Ray 2.55 and the KubeRay Operator.
Google Cloud Tpu · Ray Framework · Machine Learning Infrastructure