Ship software with AI, whether or not you write code.

Setups, guides and tool verdicts for shipping with AI: Claude Code, Codex and Cursor, vibe-coding and app builders, automation, MCP servers and just enough infra on Vercel, Cloudflare and Supabase. Priced and tested on the stack behind my own live products.

Latest articlesWhat shipped, what broke, and what it really cost — from running production AI systems.

NVIDIA OpenShell

NVIDIA OpenShell

Run agents inside NVIDIA OpenShell: current OS support, first-agent setup, file and network policies, and the limits to check before production.

Nov 8, 2026Build

The other lanes.Pick the one you came for.

204–227 / 354
AgentRun Review

AgentRun Review

Test AgentRun's workflow beta on support tasks, inspect branching and escalation, and see when it earns its place beside your existing agent.Sep 24, 2026Build
Perplexity Fast Search vs Default

Perplexity Fast Search vs Default

Compare Perplexity Fast Search with default web search on price, latency, source coverage, and the API setting your agent should use.Sep 24, 2026Build
AI Agent Fallback Costs

AI Agent Fallback Costs

A sandboxed writer triggered paid image fallbacks until a shared balance ran out. The incident, missing outputs, and fix at the upload boundary.Sep 24, 2026Build
Is Cursor Rollouts Free

Is Cursor Rollouts Free

Cursor Rollouts needs Teams or Enterprise. Understand the 10-day launch credits, roughly 50 or 500 changes, and the costs to check.Sep 24, 2026Build
How to Use Unreal Agent

How to Use Unreal Agent

Run Unreal Agent from Unreal Labs on a bounded repo task. Check Go setup, provider keys, JSONL output, sessions and actual usage.Sep 24, 2026Build
How to Use JetBrains Air

How to Use JetBrains Air

Install Air Alpha in your JetBrains IDE, connect an agent, add project context, and review your first code change.Sep 23, 2026Build
Is JetBrains Air Free

Is JetBrains Air Free

Air's IDE plugin is free. Compare Junie Lite, existing agent subscriptions, provider API billing, and JetBrains AI credits.Sep 23, 2026Build
Firecrawl Self Host

Firecrawl Self Host

Self-host Firecrawl from a pinned release, verify a scrape, and compare features and 30-day costs with Cloud before choosing a deployment.Sep 22, 2026Build
Human Approval for AI Agent Retries

Human Approval for AI Agent Retries

An agent spent $5.48 before anyone looked. See why paid redos need approval that the model cannot grant itself.Sep 22, 2026Build
MindStudio AI Agent Builder

MindStudio AI Agent Builder

Evaluate MindStudio AI Agent Builder by workflow fit, plan limits, model charges, and the cost of 1,000 or 10,000 completed jobs.Sep 22, 2026Build
Superwhisper vs Wispr Flow

Superwhisper vs Wispr Flow

Compare Superwhisper and Wispr Flow for business dictation: local and cloud settings, supported devices, correction work, and the full subscription cost.Sep 22, 2026Build
AI Automation Agency

AI Automation Agency

Choose an AI automation agency by workflow fit, 90-day total cost, support, and ownership. Compare providers and check the pilot before signing.Sep 22, 2026Build
How to Use Claude Code Projects

How to Use Claude Code Projects

Set up Claude Code Projects, check beta access, share context across cloud threads, and see which usage and local-tool limits matter.Sep 21, 2026Build
How to Use Jev

How to Use Jev

Use Jev to route a support ticket, read its confidence scores, and test when your workflow should hand the decision to a person.Sep 21, 2026Build
How to Make Claude Code Read AGENTS.md

How to Make Claude Code Read AGENTS.md

Set up Claude Code's native AGENTS.md support, check which instruction file loads, and handle provider limits and existing CLAUDE.md files.Sep 19, 2026Build
How to Set Claude Code MCP Startup Timeout

How to Set Claude Code MCP Startup Timeout

Set the MCP startup wait for Claude Code jobs, distinguish connection waits from tool timeouts, and check required tools before work starts.Sep 17, 2026Build
How to Block AI Training Without Blocking Search

How to Block AI Training Without Blocking Search

Use Cloudflare’s new training controls while keeping search access. Check migrated settings and separate crawler preferences from request blocking.Sep 16, 2026Build
Murmure Dictation Review

Murmure Dictation Review

Review Murmure for offline dictation, custom vocabulary, hardware needs, and what changes when you connect a local or remote LLM.Sep 14, 2026Build
RenderIO FFmpeg API Pricing

RenderIO FFmpeg API Pricing

Decode RenderIO command charges, chained jobs, download credits, runtime limits, and when an upgrade costs less than overage.Sep 14, 2026Build
Dictare AI Dictation Pricing

Dictare AI Dictation Pricing

Dictare is free, local voice input for coding agents. Separate its software cost from speech-model setup, hardware, and your coding-agent plan.Sep 13, 2026Build
How to Test Claude Code Plugins With Evals

How to Test Claude Code Plugins With Evals

Run Claude Code plugin evals, compare results with a no-plugin baseline, and budget the repeated agent and judge calls before adding CI.Sep 12, 2026Build
Debug Cloudflare Voice Agent Latency

Debug Cloudflare Voice Agent Latency

Trace slow and silent Cloudflare voice turns with stage timings and outcomes, then separate transcription, model, speech, and interruption problems.Sep 12, 2026Build
Burn SRT Subtitles Into a Video With Rendi

Burn SRT Subtitles Into a Video With Rendi

Turn a video and SRT file into a captioned MP4 with Rendi, covering API submission, completion checks, subtitle styling, and output review.Sep 11, 2026Build
OpenAI Agents API vs Agents SDK

OpenAI Agents API vs Agents SDK

Compare the managed OpenAI Agents API with Agents SDK on session ownership, runtime control, sandbox costs, and migration work.Sep 11, 2026Build

Prefer this site in Google

Add as a preferred sourceon Google

Mark 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.