Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
TensorFold vs llama.cpp on a Mac Studio M5 Ultra: 1.84x the Throughput on Real JSON Work
I benchmarked TensorFold 1.2.0 against llama.cpp on a Mac Studio M5 Ultra with Qwen3.8-27B and 80 real JSON requests: 1.84x throughput at 8 concurrent.
9 min readHy-MT2-7B on Five Local Runtimes: Which One Should Serve Translation on a Mac?
Hy-MT2-7B load-tested on llama.cpp, LM Studio, mlx-lm, Ollama and MLX-Serve on two Mac Studio M5 Ultra machines: throughput, scaling, determinism, memory.
9 min readTraining Enterprise AI Agents: Choosing Between SFT, DPO, GRPO and RAG
Training enterprise AI agents: when to use SFT, DPO, GRPO, LoRA or plain RAG, and how to ship the result as a pinned, evaluated and reversible release.
50 min readA Production Harness for Claude Code: Six Layers From Slack to Merged MR
How a six-layer harness turns Slack tickets into merged code: event intake, gated agent loops, durable state, self-healing, observability and operator control.
42 min readOntology Shape vs Model Size: What a Graph's Design Costs an AI Agent
How three lossless shapes of one insurance knowledge graph changed accuracy, tool calls, tokens and cost for small and large models on Azure Cosmos DB.
30 min readCloud Browser: A Secure Remote Browser Platform for Any AI Agent
A reference design for a model-neutral remote browser service: gateway, workers, WebRTC live view, approvals, SSRF guards, replay, and every config setting.
32 min readMCP 2026-07-28: How the Stateless Spec Changes Remote Server Design
The MCP 2026-07-28 spec goes stateless: no sessions or handshake, plus MRTR, Tasks and cache hints. What changes for remote servers and how to migrate them.
23 min readFifty Years of Retrieval Research Hiding Inside Your RAG Pipeline
RAG chunking, hybrid search, HyDE, reranking and evals all have decades-old ancestors in information retrieval. A tour of the research and where it falls short.
17 min readSelf-Healing Multi-Agent Team in LangGraph: Architect, Tester, Debugger
Build a LangGraph state machine in Python where an Architect, Developer, pytest sandbox, Debugger and Reviewer collaborate and loop until the tests pass.
31 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.