Where randomness meets reason

← Home 13 editions

The Stack

Series

August 2026

  1. The Stack — Replit Agent

    A technical teardown of Replit Agent: the models, infrastructure, and engineering decisions behind the product.
  2. The Stack — Otter.ai

    A technical teardown of Otter.ai: the models, infrastructure, and engineering decisions behind the product.
  3. The Stack — Claude Code

    A technical teardown of Claude Code: the models, infrastructure, and engineering decisions behind the product.

July 2026

  1. The Stack — Intercom Fin

    A technical teardown of Intercom Fin: the models, infrastructure, and engineering decisions behind the product.
  2. The Stack — GitHub Copilot

    A technical teardown of GitHub Copilot: the models, infrastructure, and engineering decisions behind the product.

June 2026

  1. The Stack — Harvey AI

    A technical teardown of Harvey AI: the models, infrastructure, and engineering decisions behind the product.
  2. The Stack — Gamma

    A technical teardown of Gamma: the models, infrastructure, and engineering decisions behind the product.

May 2026

  1. The Stack — Granola

    A technical teardown of Granola: the models, infrastructure, and engineering decisions behind the product.
  2. The Stack — Klarna's AI Assistant

    A technical teardown of Klarna's AI Assistant: the models, infrastructure, and engineering decisions behind the product.

April 2026

  1. The Stack — Notion AI

    A technical teardown of Notion AI: the models, infrastructure, and engineering decisions behind the product.
  2. The Stack — Perplexity AI

    A technical teardown of Perplexity AI: the models, infrastructure, and engineering decisions behind the product.

March 2026

  1. The Stack — Cursor

    A technical teardown of Cursor: the models, infrastructure, and engineering decisions behind the product.
  2. The Stack: Apple Silicon Local LLM Servers for Running Agents

    Ollama, LM Studio, omlx, llama.cpp, MLX-LM, vMLX — compared on the specific requirements of local agent workloads on Apple Silicon.