Build logs, guides, and field notes
What shipped, what broke, and what it really cost — from running production AI systems.
Latest articlesWhat shipped, what broke, and what it really cost — from running production AI systems.
Claude Code GitHub Actions
Set up Claude Code in GitHub Actions for PR reviews and issue fixes, with API or plan billing, narrow tools, run limits, and fork safeguards.Oct 15, 2026Build
What Are Tokens in AI? A Plain-English Guide
Understand AI tokens with a counted example, the difference between input and output, and what token usage means for everyday AI limits.Oct 15, 2026AI
Claude Connectors
Connect Claude to business tools with directory and remote MCP setup steps, plan rules, three business examples and checks before enabling writes.
Oct 15, 2026AI
LLM Benchmarks: How to Read Model Scores in Five Minutes
Learn what LLM benchmarks measure, read a Gemini launch table in five minutes, and decide when coding, reasoning and agent scores need your own evals.Oct 15, 2026AI
Zed Editor
A Zed editor review covering native editing, multiplayer, AI agents, setup, and the limits that decide whether to leave Cursor or VS Code.Oct 15, 2026Build
OpenCode vs Claude Code 2026
Choose between OpenCode's model freedom and Claude Code's native workflow. Compare access, subagents, MCP, plugins and switching costs.Oct 15, 2026Build
Figma Make
What Figma Make builds, how to turn a frame into a working prototype, and when Lovable, v0 or Claude Design fits better.Oct 15, 2026Design
LLM as a Judge: Reliable Daily Evals for Agents
Build a reliable LLM judge with example prompts, human calibration, bias checks and daily evals using Promptfoo, DeepEval, Langfuse or LangSmith.Oct 15, 2026Build
KV Cache Explained: Prefill, Decode and Prompt Caching
Understand KV cache in LLM inference, prefill vs decode, memory growth and prompt caching across Anthropic, OpenAI, Google and vLLM.Oct 15, 2026Build
DSPy Explained: Signatures, Modules and Prompt Optimization
Understand DSPy signatures, modules and optimizers, try the current docs example, and decide when measured prompt optimization is worth the work.Oct 15, 2026BuildThe lanes.Pick the one you came for.
207 pieces
AI
Models, agents and coding assistants, image, video and voice tools: reviewed, priced and compared.253 piecesBuild
Ship software with AI, whether or not you write code: coding agents, app builders, automation, MCP and the infra under it.118 piecesDesign
AI as a craft tool for designers, brand owners and creative directors: image, video, type, and the prompts behind the work.191 piecesBusiness
Voice and phone agents, customer service, sales and marketing, operations and AI search visibility, for the people who run a business.8 piecesPlaybooks
AI for your niche: the workflows that actually move, tool by tool, priced52 piecesExplained
What shipped, explained: every real release, decoded for the people who use it0 piecesLab
The agent journey, entry by entry: what shipped, what broke, what was decided, in the ventures I run828–829 / 829
Claude for Small Business: What It Kills in a $50K Stack
On May 13 Anthropic launched Claude for Small Business, a Cowork add-on with eight native connectors and fifteen ready-to-run agentic workflows priced at zero incremental cost on top of an existing Claude license. This piece is the…May 14, 2026AI
Cloudflare's '100x engineer', a 6-agent operator's take
Matthew Prince cited 2x-100x AI productivity gains to justify 1,100 layoffs. I run 6 production agents on the exact stack he's describing. The 100x engineer framing is conceptually wrong, and founders copying it into H2 headcount plans are about to cut the wrong people.May 12, 2026BusinessPrefer this site in Google
Add as a preferred sourceon GoogleMark omidsaffari.com as preferred and Google lifts it in Top Stories, AI Overviews and AI Mode for you.
Newsletter
One letter, every Sunday.Working systems, not hot takes.
Weekly. No spam. Unsubscribe anytime.