BLOG
العربيةPrompts, tutorials, and GCC growth notes.
Everything here comes from systems that actually run — agent prompts with production mileage, build tutorials, and growth notes priced in dirhams, not hypotheticals.
Looking for the prompts and checklists behind the reels? Free resources →
BROWSE BY TOPIC
AI Agents
How production AI agents are actually built — architecture, evals, observability.
Automation Case Studies
Real systems, real numbers — the builds behind this site's own missions.
AI for Google Ads
Google Ads with AI agents doing the repetitive work: search terms, budgets and reporting.
AI Careers GCC
Building a career in AI engineering in the GCC: roles, skills and market notes.
AI Agents
3 min read
Are open-source AI tools free? What OpenCode, VoiceStudio, OpenSEO, OpenMausBot and Replica still cost
Open source describes the code licence, not the bill. Five open-source AI projects for coding, voice, SEO, computer tasks and app recreation, what each one does, and the model, data, hosting and hardware costs that remain.
AI Agents
3 min read
Edge0 hardware requirements: what you need for the 8B and 35B models on Mac, Android and iOS
Edge0's 2.9 GiB memory headline is not a hardware requirement. What you actually need: Apple Silicon and Python 3.10 or newer on a Mac, about 4.2 GB or 23 GB of storage per model, 8 GB+ or 12–16 GB of phone RAM on Android, and Xcode for iOS.
AI Agents
2 min read
Can Claude post to Instagram? What the 13 free Instagram skills do, and what stays with you
Not with this skill pack: Jake Schincariol's 13 free Instagram skills draft hooks, scripts, captions, carousels and replies, but they do not connect your account, publish, comment or send DMs. Here is what each skill does and where you stay in charge.
AI Agents
2 min read
Agent harness components: the 15 parts of Mini Harness, and what each one does
An agent harness is the software around the model. Paweł Huryn's Mini Harness breaks its components into 15 parts, from the reasoning loop and tool calls to the permission gate, subagents and goal review. Here is what each part does and which one is easiest to misread.
AI Agents
2 min read
Dubai Chambers AI marketplace: what the plans, credits and 22 launch agents mean for your business
Dubai Chambers launched an AI agent marketplace on 26 October 2026: 22 agents across seven business functions, member-only access through UAE Pass, three plans and usage credits on top. What that means for a Dubai business deciding whether to try it.
Automation Case Studies
5 min read
Building a 12-agent SEO squad across 6 WordPress brands (English + Arabic)
How I run one coordinated agent system — keyword research, briefs, drafting, QA and publishing — across six WordPress brands in two languages, without every site sounding the same.
Automation Case Studies
5 min read
I built 71 live AI agents into my website — architecture and lessons
How dozens of named AI agents are actually structured on one site — shared scaffold versus bespoke logic, which agents genuinely run in production, and where the whole idea risks becoming agent theater.
AI Agents
4 min read
AI agent observability: tracing every step before it costs you
Agents fail silently — the API call succeeds while the agent does the wrong thing. Here is the lightweight, self-hosted tracing layer I run in production: an in-memory ring buffer that captures every step for zero added cost.
AI Agents
4 min read
AI automation services in UAE: what to expect and what it should include (2026)
A buyer's due-diligence guide from the builder's side: what a legitimate AI automation engagement in the UAE actually includes, what the stack looks like, and the questions that expose a weak vendor.
Automation Case Studies
4 min read
AI lead generation systems for GCC real estate: architecture that delivers
The actual pipeline behind an AI lead-gen system for GCC real estate — capture, enrichment, scoring, routing, nurture — grounded in a real Dubai property engagement at AED 76.38 per lead.
AI Careers GCC
4 min read
AI marketing manager roles in UAE 2026: skills, salaries, portfolio that wins
What the "AI marketing manager" title actually means in UAE job postings, the skill stack that gets you hired, why salary aggregators mislead, and the portfolio anatomy that passes a technical screen.
AI Careers GCC
4 min read
AI marketing manager vs marketing agency in Dubai: cost and outcome comparison
An honest cost and outcome comparison between a traditional Dubai agency retainer and an AI-agent-driven marketing operator — from someone who runs the second model in production.
Automation Case Studies
4 min read
AI voice receptionist for clinics in the UAE: a buyer's guide
What an AI voice receptionist can and cannot do for a UAE clinic — bilingual reality, latency, compliance considerations, and the questions to ask any vendor before you sign.
Automation Case Studies
5 min read
Automating appointment scheduling for a healthcare clinic with n8n and Google Workspace
A reproducible n8n workflow for clinic appointment booking, confirmations and reminders on Google Workspace — including conflict checks, reminder sequencing and where the visual builder hits its limits.
Automation Case Studies
5 min read
Building IBRAHIM: a B2B sales outreach agent running 150 touches a day
The architecture behind IBRAHIM, my production B2B outreach system: 11 specialised agents covering prospecting to follow-up, the guardrails that protect deliverability, and what still needs a human.
Automation Case Studies
5 min read
Cloning my voice with Fish Audio for a production voice agent — honest review
I cloned my own voice with Fish Audio and wired it into my production agent stack. Here is what the process actually involved, where the clone breaks down, and whether I would choose it again.
AI Agents
5 min read
How to connect an AI agent to Google Sheets and Calendar (service accounts done right)
The service-account setup I use in production agents: keys, scopes, the sharing step everyone misses, the auth code pattern, and what Google's 403 and 404 errors actually mean.
AI Careers GCC
5 min read
Dubai's 1 Million Prompters: was it worth it?
An honest first-hand review of Dubai's 1 Million Prompters AI upskilling initiative — what it teaches well, where the production gap shows up, and who should take it.
AI Careers GCC
5 min read
From performance marketer to AI builder: my 6-month transition playbook
The real month-by-month account of pivoting from PPC work to building production AI agents — while still serving live clients. Wrong turns included.
AI for Google Ads
4 min read
Google Ads automation with AI agents: what I run in production
What a custom AI agent layer adds on top of Smart Bidding and Performance Max — the production stack, the real numbers, and what stays human.
Automation Case Studies
4 min read
How I cut Google Ads CPA to AED 11.20 with attribution and an AI agent — the full system
The full Printo case: AED 42K spend, 3,750 conversions, a 5.83% CTR RSA, and AED 11K/mo reallocated via attribution — including what didn't work.
Automation Case Studies
4 min read
How I built an autonomous AI Google Ads optimization system (SARA) — full breakdown
The real architecture of SARA, my production Google Ads agent: four layers, hard guardrails, what it touches unsupervised, and what broke in testing.
AI Agents
4 min read
How to build a lead scoring agent that sales teams actually trust
Five steps to a lead scoring agent reps actually use: outcome-derived weights, a visible reason for every score, and CRM write-back into the views reps already work in.
AI Agents
5 min read
How to build an AI voice agent that books real appointments
Build notes from shipping a production voice agent: the state machine, the latency budget, and why the booking step is never left to the LLM.
AI Careers GCC
4 min read
How to hire an AI agent developer in Dubai — a founder's checklist
An insider checklist for founders hiring AI agent talent in the UAE — the six questions to ask, the portfolio red flags, and what a real answer looks like.
AI Agents
4 min read
How to show up in ChatGPT and Perplexity answers (GEO guide)
AI engines cite by retrieval, not PageRank. The verifiable mechanics — answer-first structure, schema markup, crawler access, topical depth — without the agency hype.
AI Agents
4 min read
LLM evaluation framework for AI agents: deterministic, semantic, behavioral
The three-tier eval harness I run on my own agent engine: cheap deterministic checks first, an LLM judge for meaning, and behavioral checks on the tool-call path.
AI Agents
4 min read
n8n vs custom code for business automation: how I decide
A decision framework from using both in production: where n8n's canvas wins, where it starts to hurt, and the hybrid pattern that gets you both.
AI Agents
4 min read
Prompt versioning for production AI: the system nobody talks about
Every prompt on my agent engine is a git-tracked, semantically versioned markdown file. Here's the full system: diffs, reviews, trace logging, and minutes-fast rollbacks.
AI Agents
5 min read
Rate limiting public AI demos: surviving free-tier quotas gracefully
How I rate limit the 73 live agent demos on this site so one bot or one viral link can't drain the API quota — KV-backed limits, token-aware caps, and honest fallback UX.
AI for Google Ads
5 min read
Server-side GTM + AI: the tracking setup for performance marketers
How I wire server-side Google Tag Manager so chatbot qualifications and voice-agent bookings land in GA4 and Google Ads as real conversions — with gclid attribution intact.
AI Careers GCC
5 min read
The UAE AI job market for marketers: what 100+ applications taught me
Pattern analysis from my own application run across the UAE's AI marketing market: what got responses, what interviewers actually tested, and where job descriptions lied.
AI Agents
5 min read
What production-grade AI actually means (the 5 pillars I build on)
The five criteria that separate an AI system that survives real usage from a demo: auditable reasoning, designed fallbacks, outcome measurement, real integration, and ownership after handover.
AI Agents
5 min read
WhatsApp AI agents for UAE businesses: what actually works
A blunt map of WhatsApp automation for UAE businesses: what an AI agent reliably handles, where Meta's rules and off-script conversations break it, and what a working architecture looks like.
Automation Case Studies
5 min read
How my WhatsApp AI receptionist handles real leads for a UAE printing company
Adam is the AI estimation copilot I built for Printo: it reads messy WhatsApp quote requests, extracts specs, looks up real pricing, and answers in seconds — escalating the hard cases to humans.
AI Agents
4 min read
AI agents for marketing vs marketing automation tools: what's actually different
"AI agent" gets slapped on every marketing tool with a chatbot now. Here's the real technical line between an agent and automation — and how to tell which one you're actually buying.
AI Agents
5 min read
The AI engineer roadmap most people share — and what I'd change after shipping 73 production systems
A 3-month AI engineer roadmap is making the rounds. The phase order is mostly right. But two things are missing that will burn you the moment you touch a real client system — and one phase is too light for what the job actually demands.
AI Agents
4 min read
How I built a Google Ads autonomous agent — full walkthrough
A full video walkthrough of the Google Ads autonomous agent I run in production: how it pulls live data from Google Ads and GA4, makes budget and bid decisions, and reports — every day, without me touching it.
AI Agents
5 min read
Proactive AI agents compared: what Claude Duet adds over OpenAI dots and Grok Bot, and what it costs
Anthropic's Claude Duet is a proactive agent that messages you first. Compared with OpenAI dots and Grok Bot on dated prices and access, its difference is that it adds no charge to Claude Pro and Max, though it is a US-only waitlist for now.
AI Agents
5 min read
Is Kimi K3 worth running locally? 8 GB of RAM, 1.7 TB of disk and 30 seconds per token
Kimi K3 does run locally on 8 GB of RAM with no GPU, because kimi-k3-in-c streams its experts from a fast SSD. Whether it is worth it is another question: about 1.7 TB of free disk, hours of download and about 30 seconds per token, against a hosted API at about $3 per million input tokens.
AI Agents
4 min read
What REA can reverse engineer, and what it can't: desktop, Electron, web and Android, but no iOS
REA (Reverse Engineer Anything) lets Claude Code trace how a feature works, with evidence. What it can inspect: native desktop binaries, JavaScript and Electron apps, websites, Android APKs and .NET assemblies. What it does not cover: iOS apps, and anything you are not authorized to examine.
AI for Google Ads
5 min read
Do AI search visitors convert better? The 4.4x Semrush stat, checked, and how to test it on your own site
One Semrush study found AI search visitors 4.4x as valuable as organic search visitors. The methodology is thin and other studies range from about 1.3x to over 20x. Here is what the stat really says, why it can happen, and how to test it on your own numbers.
AI Agents
5 min read
Are Claude Code skills safe? What the 1-in-4 study found and what a SkillSpector scan can't see
About 1 in 4 marketplace agent skills had a security flaw in a January 2026 study, while confirmed malware was rare. What that means for the skills in your Claude Code, what NVIDIA's free SkillSpector scanner catches, and what a low score does not prove.
AI Agents
5 min read
Is ScrapeGraphAI free? What a daily AI lead finder really costs to run, and the UK rules for using it
ScrapeGraphAI is free, MIT-licensed and can run on a free local model through Ollama. The agent that schedules it is not, a local run needs your computer awake, and the paid managed API is a separate product. Here is the full cost of a daily lead finder, plus the UK rules for emailing the results.
AI Agents
5 min read
Do AI YouTube skills work? I ran 6 of the YouTube Agent Skill's 11 on my own footage
Do AI YouTube skills work? I ran 6 of the 11 free YouTube Agent Skill commands on my own footage: a hook went from 46 to 82 after one rewrite, the edit skill found 18 dead-air cuts, and the viral skill ranked 80 videos from 6 channels. Here is what each produced, and what I have not tested.
AI Careers GCC
5 min read
Can Claude apply for jobs? What a Playwright MCP job search does, and why you still press Submit
Can Claude apply for jobs for you? Not in this workflow. With Microsoft's open-source Playwright MCP it can research career pages, shortlist up to ten roles with resume evidence and draft truthful answers, but you review every field and press Submit yourself.
AI Agents
4 min read
Why AI websites look generic: a before-and-after redesign from one better brief
AI websites look generic because the brief is generic: no single goal, no specific offer, no chosen type or colour system. A before-and-after redesign of a fictional studio shows what changes when you fill those gaps, and what it does not prove.
AI Careers GCC
4 min read
AI engineering portfolio: what reviewers look for, and how to pick a first project from 85 ideas
What makes an AI engineering portfolio worth a reviewer's time? Landed's open-source catalog of 85 project ideas says depth over breadth: a few projects with real evals, a live demo and a README that reads like a product spec. Here is how to pick the first one and what to show.
AI Agents
4 min read
A LinkedIn content workflow in Claude: which of 27 free installs to chain, and in what order
A LinkedIn content workflow in Claude has five jobs: sound like you, find ideas, draft, make the graphic and connect your apps. Here is how 27 free skills, plugins and MCP servers map to those jobs, how to chain them, and why you start with your weakest step.
AI Agents
4 min read
Prompt Motion gallery: what Claude-made motion videos teach you about writing a brief
The Prompt Motion gallery shows motion videos made with Claude next to the prompts behind them. Watch one twice, match each line of the prompt to what happens on screen, then write your own Remotion brief with product, palette, timing and final frame.
AI Agents
4 min read
Vague prompts in Claude Code: what 20 rounds, 1,089 lines and invented reviews taught me
What do vague prompts do in Claude Code? I sent the same open-ended prompt 20 times to an ugly coffee shop page. Sonnet 5.5 made careful upgrades, Opus 5.5 grew the page to 1,089 lines and invented customer reviews, and neither searched the web once.
AI Agents
4 min read
Claude Code video editing results: what one raw take becomes after my 10-step pipeline
What does Claude Code video editing actually produce? One raw take in, a finished reel out: pauses trimmed to about 0.22 seconds, your face kept in frame, a new graphic every two to three seconds, captions, music 12 dB under the voice, and a self-check of every frame before you see it.
AI Agents
4 min read
Why Claude Code won't edit video out of the box, and the eight prompt sections that fix it
Ask Claude Code to edit a video and you get a plan, not an MP4. It has nothing to cut or render with until seven free tools are installed, and it needs one structured prompt (goal, install, folder, references, workflow, checks, notes, export) that says what done means.
AI Agents
1 min read
Google Ads automation with n8n + MCP: how to build the agent
The architecture behind an autonomous Google Ads agent: n8n scheduling, MCP tool wiring, and a Claude media-buyer prompt with guardrails.