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.
AI Acceptable Use Policy: A One-Page Template for Small Business
Copy a one-page AI acceptable use policy covering approved accounts, customer data, human review and disclosure, then roll it out in one team meeting.Oct 19, 2026AI
Best AI for Data Analysis in 2026: ChatGPT, Claude, Julius AI, Gemini and Copilot (Compared)
Compare ChatGPT, Claude, Julius AI, Gemini and Copilot for CSVs, spreadsheets and reports, with maker-sourced file limits and data policies.Oct 19, 2026AI
Langflow: What It Is and When to Use It
What Langflow is, who owns it, how agents and RAG flows work, and when to choose it over Flowise or n8n. Includes current hosting options.
Oct 19, 2026Build
Brand24 Review
Brand24’s sources, AI features, alerts and reports, with practical workflows, specific limitations and a clear rule for choosing it.Oct 19, 2026Business
Microsoft 365 Copilot Pricing: Plans, Bundles and Agent Costs
Compare Microsoft 365 Copilot prices, Business bundles, annual commitments and agent charges, with seat-cost comparisons against ChatGPT and Claude.Oct 19, 2026AI
Multimodal AI: What It Means for Your Business
What multimodal AI accepts and returns, how current models differ, and what invoices, meetings, product videos and voice agents need.Oct 19, 2026AI
Adobe Firefly Review
Adobe Firefly reviewed for commercial work: Adobe and partner models, credits, usage rights, and workflows in Photoshop, Express and Premiere.Oct 19, 2026Design
Amazon Bedrock Pricing: Model Rates and a $1,270 App Budget
Amazon Bedrock model rates, direct API comparisons, caching and add-ons, with a $1,270 monthly budget for 100,000 support answers.Oct 19, 2026Build
ChatGPT for Business: What Your Team Gets Beyond Plus
What ChatGPT Business adds beyond Plus: shared work, Work, Codex, data privacy and admin controls, plus when your company needs Enterprise.Oct 19, 2026AI
Claude Fast Mode
Claude fast mode for Opus 5.5: exact setup, subscription billing, standard-versus-fast costs, and when paying for speed makes sense.Oct 19, 2026BuildThe lanes.Pick the one you came for.
232 pieces
AI
Models, agents and coding assistants, image, video and voice tools: reviewed, priced and compared.279 piecesBuild
Ship software with AI, whether or not you write code: coding agents, app builders, automation, MCP and the infra under it.122 piecesDesign
AI as a craft tool for designers, brand owners and creative directors: image, video, type, and the prompts behind the work.201 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 run60–83 / 894
ChatGPT Projects
Set up ChatGPT Projects for recurring client work: files, instructions, project-only memory, team sharing and the limits that matter.Oct 16, 2026AI
Context Window: Token Limits, Recall and What Fits
What a context window holds, current Claude, GPT-6 and Gemini limits, and how retrieval, summaries and caching help you manage long prompts.Oct 16, 2026Build
RAG vs Fine Tuning: Company Knowledge and Behavior
Choose retrieval for company facts and fine-tuning for behavior, with three business cases, maker prices, and the effect of long context and caching.Oct 16, 2026Build
ChatGPT Connectors
Connect company tools to ChatGPT with clear access controls. Current app plans, sync limits, retention, and HubSpot, Drive and GitHub setup steps.Oct 16, 2026AI
Answer Engine Optimization: What to Change on Your Pages
Make your pages useful in AI answers: official source guidance, a before-and-after rewrite, and a practical plan to measure AEO.Oct 16, 2026Business
Monday vs Asana: Which AI Work Manager Fits Your Team?
Monday vs Asana for 10-50 people: compare AI automation, usage limits, integrations and the best fit for operations, projects or client work.Oct 16, 2026Business
Aider AI Review
Aider reviewed for developers: Git edits, repository maps, model setup, API task arithmetic, and when Claude Code, Codex or Cursor is the better fit.Oct 16, 2026Build
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, 2026Build
Agent Skills: How One Folder Works Across AI Tools
Agent Skills explained: the SKILL.md standard, verified tool support, a portable weekly-report example, context overhead and security boundaries.Oct 15, 2026Build
Julius AI: Review
Julius AI reviewed for spreadsheets, databases and business reporting, with current features, notebook changes, security limits and alternatives.Oct 15, 2026AI
Best Embedding Models in 2026: Gemini, OpenAI, Voyage, Cohere, Qwen and BGE Compared
Compare Gemini, OpenAI, Voyage, Cohere and open embedding models by retrieval fit, languages, deployment and migration work.Oct 15, 2026Build
Napkin AI: Text to Visuals
Napkin AI reviewed for proposals, posts and reports: diagrams, Slides, editing, export limits, commercial use and client data.Oct 15, 2026Design
Small Language Models: What They Are and When to Use Them
Understand small language models, their limits and five practical jobs. Compare current model sizes and licences, then run one locally or via an API.Oct 14, 2026AI
LLMs TXT Explained: Who Reads llms.txt and Is It Worth It?
What llms.txt does, what OpenAI, Anthropic, Google and Perplexity document, plus a small-business template and server-log checks.Oct 14, 2026Business
LangSmith vs Langfuse
Compare LangSmith and Langfuse for tracing, evaluations, datasets, prompts and self-hosting. Choose by framework fit and operational ownership.Oct 14, 2026BuildPrefer 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.