Build logs, guides, and field notes
What shipped, what broke, and what it really cost — from running production AI systems.
Prefer this site in Google
Mark omidsaffari.com as preferred and Google lifts it in Top Stories, AI Overviews and AI Mode for you.
- 142
- AI
- Models, agents, coding assistants, image, video, voice 124
- Build
- Ship with AI when you're not an engineer: vibe-coding, app/SaaS builders, automation, MCP, just-enough infra 90
- Design
- For designers, brand owners, creative directors 117
- Growth
- AI for marketing, SEO/GEO, content engines, and the operator-business work of turning audience into revenue 4
- Playbooks
- AI for your niche: the workflows that actually move, tool by tool, priced 22
- Explained
- What shipped, explained: every real release, decoded for the people who use it 0
- Lab
- The agent journey, entry by entry: what shipped, what broke, what was decided, in the ventures I run
Latest articlesWhat shipped, what broke, and what it really cost — from running production AI systems.
Vercel Flat Rate CDN Makes Traffic Bills Predictable
Vercel Pro can use fixed monthly CDN tiers. Learn what spike protection covers, when the next bill rises, and which workloads are excluded.Sep 9, 2026Explained
OmniSEO Review for Small Agencies
Evaluate OmniSEO for a small agency: prompt coverage, citation checks, client reporting, exports, and the plan limits that shape the purchase.Sep 9, 2026Growth
How to Use ChatGPT Sketch on Mobile
Turn a rough phone sketch into a usable image in ChatGPT, then revise, save, and share it with the current mobile controls.
Sep 9, 2026Design
Cut Vercel Build Costs With Basic Machines
Vercel Pro teams can choose Basic builds. Compare rates, build duration, and queue time before switching smaller apps.Sep 9, 2026Explained
How to Create a Punch List From Photos With AI
Turn photo evidence in an inspection report into a checked punch list, with room labels, trade assignments, and a review before handoff.Sep 9, 2026Growth
Best AI Tools for Submittal Spec Checking
Compare AI tools that check submittals against project specs, with source citations, revision handling, file support, and trial checks.Sep 9, 2026AI
VetGeni vs ScribbleVet
Compare VetGeni and ScribbleVet for clinic note workflows, PIMS transfer, team seats, costs, and the checks to make before switching.Sep 8, 2026AI
InspectMind AI Review
Evaluate InspectMind AI for drawing checks, cited findings, revision review, pricing visibility, and the limits a project team should test.Sep 8, 2026AI
Claude Managed Agents Bring Config Changes Into Review
Claude ant apply puts agent setup in versioned files. See what teams can review, how the lockfile works, and the CI status-code catch.Sep 8, 2026Explained
BuildSync vs SpecLens
Compare BuildSync and SpecLens by submittal checks, source citations, supported files, integrations, and the procurement work each fits.Sep 8, 2026AI468–491 / 499
Notion Custom Agents: $340/month shock — cap or rebuild?
The real burn math after Notion metered Custom Agents at $10 per 1,000 credits: a client OS's three-way decision and the accounting recaps skip.May 16, 2026Growth
Figma Make Custom Skills: 3-Skill Pack for Design Systems
Packaging a design system as a reusable Figma Make skill: the skill files, the Notion-connector wiring for live tokens, and the two real limits.May 16, 2026Design
AI Bandit vs A/B Testing: 30-Day CVR Data & the Trade
Replacing A/B testing with AI bandits over 30 days: tool costs, the rollout, and the statistical-significance problem the CRO listicles skip.May 16, 2026Growth
Production AI-agent guardrails: blast-radius architecture
The production blast-radius architecture for AI agents: one cost chokepoint, a no-shell tool allowlist, idempotent steps, and pre-execution denial.May 16, 2026Build
Opus 4.7 +27%, GPT-5.5 2x: The Harness That Held
Three vendors quietly raised AI cost in one week. Which mechanism hits your stack, and the cache, router and spend-cap architecture that absorbs it.May 16, 2026AI
Grok Build: cheapest model, $300/mo door — the operator math
Grok Build's cheap model is gated behind a $300/mo tier: the subscription-vs-API math for an operator already on Claude Max, and why it waits.May 16, 2026AI
Dubai Legal AI Stack: 68% Less Review, AED 9,500/Month
A workflow-mode playbook for the managing partner of a 10-25 lawyer UAE boutique who has watched Harvey AI, Vincent AI, and Lexis+ Protégé pricing drift past USD 1,000 per seat per month and concluded — correctly — that the enterprise…May 15, 2026Growth
Mercury OCC Approval: My 5-Venture Banking Decision
Mercury received OCC conditional approval for Mercury Bank, N.A. on April 28, 2026, two weeks after acquiring Central, an AI-native payroll platform. Senior founders running multiple entities now have to decide whether to consolidate…May 15, 2026Growth
Runway Agent vs 4-Tool Pipeline: 9 min vs 4.5 hrs
Runway Agent (launched May 13, 2026) compresses what used to be a four-tool brand-video pipeline — Midjourney + Runway Gen-4.5 + ElevenLabs + DaVinci — into a single conversation, with voiceover, dialogue, and music assembled in minutes.…May 15, 2026Design
AdCreative.ai vs Pencil Pro vs Control: $4,800 CPA Data
A 6-week, $4,800 Meta ads test pitting AdCreative.ai Professional ($249/mo) against Pencil Pro ($249/mo) against hand-designed control creative on a single DTC product, with matched audiences, identical offers, and clean 7-day click…May 15, 2026Growth
Meta Andromeda + Advantage+ ad-creative stack for DTC, 2026
Meta defaulted Advantage+ Creative on and dropped the Sales conversion threshold to 25/week. Creative variety is the new lever. Stack I'd run now.May 15, 2026Growth
Anthropic SDK 0.100–0.102: What to Delete on Cloudflare
A migration playbook for senior devs running production AI on a Durable-Object-plus-Workflows stack. Maps every piece of the Managed Agents API that landed in SDK 0.100–0.102 to the Cloudflare primitive it replaces, surfaces the three…May 15, 2026Build
Claude Agent SDK on a Separate Meter June 15: The Token Math
On May 13 Anthropic announced that starting June 15, 2026, programmatic Claude usage (Agent SDK, `claude -p`, Claude Code GitHub Actions, third-party apps) draws from a separate credit pool instead of subscription limits. Pro gets $20,…May 15, 2026AI
PwC Certifies 30,000 on Claude: 18-Month Arbitrage Window
PwC and Anthropic announced a multi-year alliance expansion on May 14, 2026 that puts Claude Code and Cowork into hundreds of thousands of PwC professionals' hands, with 30,000 US staff certified inside the year. The release publishes…May 15, 2026AI
Codex Mobile Preview: Async Coding as the Solo-Op Default
On May 14, 2026, OpenAI shipped a preview of Codex inside the ChatGPT mobile app on iOS, iPad, and Android, available on all plans including Free and Go. The phone becomes a thin controller over a Codex desktop session running on a paired…May 15, 2026AI
Codex in ChatGPT mobile: async coding for solo operators
OpenAI shipped Codex inside ChatGPT mobile on May 14, free tier included. The phone is now the agent control plane for solo Mac operators.May 15, 2026AI
Notion Developer Platform: the August 11 credit cliff
On May 13, 2026, Notion launched its Developer Platform — Workers (hosted code runtime), External Agents with partner integrations for Claude Code, Cursor, Codex and Decagon, an External Agent API for custom agents, a CLI called `ntn`,…May 15, 2026AI
Abu Dhabi Dental Recall Stack: 38% Fewer No-Shows
A real anonymized playbook for a 14-chair Abu Dhabi multi-specialty dental group rebuilt around the DOH Responsible AI Standard V1 (2025) and ADHICS V2.0. Every architectural choice, Arabic + English templates, human-in-the-loop…May 14, 2026Growth
OpenAI's Free Codex Offer: The 60-Day P&L That Said No
A first-person operator P&L for solo founders weighing OpenAI's May 13 promotion against staying on Anthropic Max with the new +50% weekly Claude Code limit through July 13. Walks the actual switching cost in engineering hours, the…May 14, 2026Growth
Webflow May 2026 Pricing: 8-Site Studio Ledger
A studio-operator breakdown of Webflow's May 13, 2026 pricing migration. Maps the old Basic / CMS / Business / Ecommerce ladder to the new Basic / Premium / Ecommerce / Team layout, walks Webflow's three official scenarios (A: save $10,…May 14, 2026Design
Anthropic Buying Stainless: What to Do in Your Codebase Now
On May 12, The Information reported Anthropic is in advanced talks to acquire Stainless for at least $300 million, a deal that would hand the Claude maker control of the SDK-generation pipeline that produces the official client libraries…May 14, 2026AI
Dubai Brokerage WhatsApp Stack: AED 22K, 4-Min Reply
A working playbook for Dubai real-estate brokerage principals running 10–60 agents on Bayut, Property Finder, and dubizzle traffic. Walks through the actual four-component AI stack we shipped to cut WhatsApp first-reply latency from a…May 14, 2026Growth
Claude Code +50% Weekly Cap: Migration Math for July 13
On May 13, 2026, Anthropic raised Claude Code weekly limits 50 percent through July 13 for Pro, Max, Team, and seat-based Enterprise accounts. The same day, OpenAI offered two free months of Codex to teams who migrate inside 30 days. The…May 14, 2026AI
Bun.Image 1.3.14: Sharp migration in 4 steps
A working migration playbook for senior devs running production image workloads on Bun. Maps every Sharp method I had in production to its Bun.Image equivalent, surfaces the four API differences that broke first, and benchmarks the result…May 14, 2026BuildNewsletter
One letter, every Sunday.Working systems, not hot takes.
Weekly. No spam. Unsubscribe anytime.