Blog
AI engineering insights, practical advice, and things I'm learning.
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 · Llm Architecture
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
Ai Engineering
How to Scale Diffusers Training With NeMo Automodel
Learn how to fine-tune large diffusion models like FLUX.1-dev and Wan 2.1 across multiple GPUs using the NVIDIA NeMo Automodel library.
Diffusion Models · Gpu Acceleration · Model Fine Tuning
Ai Agents
How to build ordering agents with DoorDash dd-cli
Learn how to configure the new DoorDash dd-cli to enable autonomous food ordering and real transaction processing for your AI workflows.
Autonomous Agents · Doordash Api · Command Line Interface
Ai Agents
How to Scale AI Agents with Modular Prompt Transpilation
Learn how to replace fragile monolithic system prompts with Google's modular prompt transpiler to build, validate, and deploy scalable AI agents.
Prompt Engineering · Modular Architecture · Agentic Systems
Ai Agents
How to Build Reliable Agents With Ai2's Shippy Architecture
Learn how to implement the Shippy agent architecture using distinct personas, versioned skills, and deterministic CLI tooling for reliable AI deployments.
Agentic Workflows · Shippy Architecture · Deterministic Ai
Ai Engineering
How to Profile PyTorch Attention Kernels on A100 GPUs
Learn how to use the PyTorch profiler to identify memory and compute bottlenecks in attention mechanisms using Hugging Face's tracing methodology.
Pytorch Profiler · Attention Mechanism · Gpu Optimization
Ai Coding
How to Control Token Budgets in Claude Code via Effort Levels
Learn how to configure model selection and the new effort parameter in Claude Code to optimize token spend and agentic task thoroughness.
Claude Code · Token Optimization · Agentic Workflows
Ai Engineering
How to Cut CPU Costs with Cloudflare Workers Cache
You will learn how to configure Cloudflare Workers Cache to serve responses directly from entrypoints, handle invalidations, and partition cache keys.
Cloudflare Workers · Edge Computing · Serverless Optimization
Ai Engineering
How to launch Hugging Face models in SageMaker Studio
You will learn how to use the new Hugging Face integration to automatically provision and deploy open-source models directly into Amazon SageMaker Studio.
Hugging Face · Amazon Sagemaker · Model Deployment
Ai Engineering
SkyPilot Drops Cross-Cloud Egress Fees With Hugging Face Storage
Configure SkyPilot to mount Hugging Face Storage natively and eliminate cross-cloud egress fees for multi-cloud AI workloads.
Multi Cloud · Skypilot · Hugging Face
Ai Engineering
How to Configure Elastic Training in MaxText on TPUs
Learn how to enable elastic training in MaxText to survive hardware failures and resume distributed AI workloads in seconds.
Tpu Acceleration · Distributed Training · Fault Tolerance
Ai Agents
How to Build Stateful AI Agents With the Genkit Agents API
Learn how to manage multi-turn conversation state and automate tool execution loops in your full-stack applications using the new Genkit Agents API.
Genkit · Stateful Agents · Tool Execution
Ai Agents
How to Automate Agent Evaluation With Google Quality Flywheel
Learn how to configure Google's new Agent Quality Flywheel skill to automate evaluation, grading, and prompt optimization for your AI coding agents.
Automated Evaluation · Google Cloud · Prompt Optimization
Ai Agents
How to Build Graph-Based Workflows With Google ADK Go 2.0
Learn how to migrate from rigid DAGs to dynamic, stateful AI agent graphs using Google's new ADK Go 2.0 workflow engine and Human-in-the-Loop primitives.
Google Adk · Graph Based Workflows · Multi Agent Systems
Ai Agents
How to Build Autonomous GRC Agents With Anecdotes
Learn how to build and orchestrate continuous compliance monitoring agents using the Anecdotes Agent Studio and its Model Context Protocol integration.
Autonomous Agents · Compliance Automation · Grc Engineering
Ai Engineering
How to Expose Ephemeral vLLM Endpoints on Hugging Face Jobs
Learn how to spin up temporary, OpenAI-compatible vLLM inference endpoints on Hugging Face serverless infrastructure using a single CLI command.
Vllm · Hugging Face · Serverless Inference
Ai Engineering
How to Implement Saga Rollbacks in Cloudflare Workflows
Learn how to manage distributed transactions and write compensating actions using the saga rollback feature in Cloudflare Workflows.
Distributed Transactions · Cloudflare Workflows · State Management
Ai Coding
How to Build Programmatic Agents with the Cursor SDK
Learn how to deploy programmatic coding agents in your own applications using the Cursor SDK, Composer 2.5, and the remote Model Context Protocol.
Cursor Sdk · Programmatic Agents · Model Context Protocol