Blog

AI engineering insights, practical advice, and things I'm learning.

Latest AI news, updated daily. Go to News →

Ai Agents

How to Automate Desktop Workflows With Claude Cowork

Learn how to configure Claude Cowork to execute multi-step desktop tasks using local file access, markdown skills, and built-in workspace connectors.

Desktop Automation · Workflow Optimization · Claude Cowork

Ai Agents

How to Extend Reachy Mini Capabilities With Remote MCP Tools

Learn how to extend the Reachy Mini robot using remote Model Context Protocol tools hosted on Hugging Face Spaces without modifying local application code.

Robotics · Mcp Protocol · Hugging Face Spaces

Ai Engineering

How to Stop OCR Degeneration With DharmaOCR Lite 3B

Dharma-AI's new DharmaOCR models apply DPO to eliminate autoregressive looping. Learn how to configure the 3B parameter model for structured JSON extraction.

Optical Character Recognition · Direct Preference Optimization · Structured Data Extraction

Ai Engineering

How to Find GPU Gaps in PyTorch 2.12 With torch.profiler

Learn how to identify performance bottlenecks and idle GPU lanes using the native torch.profiler in PyTorch 2.12 across Blackwell and AMD hardware.

Pytorch · Gpu Optimization · Performance Profiling

Ai Engineering

How to Automate Google Pay Integrations With MCP

Connect your AI development environment to real-time merchant data and documentation using the new Google Pay and Wallet Developer MCP server.

Mcp Server · Google Pay · Workflow Automation

Ai Agents

How to Orchestrate Parallel Subagents in Claude Code

Learn how to use dynamic workflows in Claude Code to manage up to 1,000 parallel subagents, handle resumable state, and optimize your Opus 4.8 API costs.

Claude Code · Parallel Orchestration · Dynamic Workflows

Ai Engineering

How to Cut Checkpoint Time by 85% With TRL Delta Weight Sync

Learn how to configure TRL Delta Weight Sync to reduce trillion-parameter model checkpointing times by 85 percent using Hugging Face Hub Buckets.

Hugging Face · Checkpointing · Trl Library

Ai Engineering

How to Run Gemma 4 On-Device with LiteRT-LM

Learn how to configure LiteRT-LM to deploy the Gemma 4 model family locally across mobile, desktop, and edge environments with constrained JSON decoding.

Gemma 4 · Litert Lm · On Device Ai

Ai Agents

How to run Claude Managed Agents in self-hosted sandboxes

Learn how to deploy Claude Managed Agents using self-hosted sandboxes and MCP tunnels to securely execute tools and access private data.

Claude Managed Agents · Self Hosted Sandboxes · Mcp Tunnels

Ai Engineering

How to Fine-Tune Cosmos Predict 2.5 for Robotics With LoRA

Learn how to adapt NVIDIA's 2B and 14B Cosmos Predict 2.5 world foundation models using parameter-efficient fine-tuning methods like LoRA and DoRA.

Fine Tuning · Lora Dora · World Models

Ai Coding

How to Scale Claude Code Across Enterprise Monorepos

Learn how to deploy Claude Code in multi-million line monorepos using hierarchical context, language server protocol integration, and on-demand skills.

Claude Code · Monorepo Scaling · Enterprise Software

Ai Agents

How to Control Agent Tool Execution via Genkit Middleware

Learn how to use Google's new Genkit Middleware to intercept model calls, implement human-in-the-loop tool approvals, and handle transient API failures.

Genkit Middleware · Agentic Workflows · Human In The Loop

Ai Agents

How to Build Long-Running AI Agents With Google ADK 1.0

Google's Agent Development Kit 1.0 enables multi-day workflows that survive restarts. Learn to configure durable state machines and persistent session storage.

Google Adk · Durable Computing · State Machines

Ai Engineering

How to Scale PyTorch Training With AWS Building Blocks

Learn how to configure AWS infrastructure and Hugging Face tools to optimize large-scale foundation model pre-training and inference workflows.

Pytorch · Aws Cloud · Foundation Models

Ai Agents

How to Build Multi-Agent CNC Workflows on AMD MI300X

Learn how to coordinate LangChain agents and Qwen 2.5 7B on the AMD MI300X to reduce CNC manufacturability analysis time from hours to seconds.

Amd Mi300x · Langchain · Qwen Model

Ai Engineering

How to Fine-Tune Qwen3 on AMD MI300X Using ROCm

Learn how to configure ROCm 6.1 environment variables and use the Hugging Face stack to fine-tune Qwen3-1.7B on AMD hardware without CUDA.

Fine Tuning · Amd Rocm · Qwen 3

Ai Coding

Cursor's Autoinstall Bootstraps RL Training Environments

Learn how Cursor uses previous model generations to automate reinforcement learning environment setups, mock dependencies, and verify target commands.

Cursor Editor · Reinforcement Learning · Automated Testing

Ai Engineering

How to Implement Event-Driven Webhooks in the Gemini API

Learn how to configure static and dynamic webhooks in the Gemini API to eliminate polling overhead for long-running AI operations and agent workflows.

Gemini Api · Webhooks · Event Driven Architecture

Ai Coding

How to build an iOS app with Claude Code subagents

Learn how to orchestrate parallel subagents in Claude Code to build and ship a production Swift application using natural language and specialized roles.

Claude Code · Ios Development · Ai Agents

Ai Agents

How to Run Multi-Tenant Agents With Dynamic Workflows

Learn how to use Cloudflare Dynamic Workflows to execute durable, stateful operations for multi-tenant applications and long-running AI agents.

Cloudflare Workers · Multi Tenancy · Durable Execution