Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Tips for 🥽 VR/MR developers, or anyone getting into VR by building a new app or game: leverage the Meta VR CLI + Muse Code in your agentic workflow. - An MCP server that gives your AI coding agent full context from the Meta VR docs - Device management:... list, inspect, and control connected headsets - App installs and build deployment straight from the terminal - Log streaming and shell access for fast debugging - Performance capture and trace analysis - Screenshots and UI automation 𝙄𝙣𝙨𝙩𝙖𝙡𝙡 𝙤𝙣 𝙢𝙖𝙘𝙊𝙎/𝙇𝙞𝙣𝙪𝙭: 𝙘𝙪𝙧𝙡 -𝙛𝙨𝙎𝙇 𝙝𝙩𝙩𝙥𝙨://𝙙𝙚𝙫𝙚𝙡𝙤𝙥𝙚𝙧𝙨.𝙢𝙚𝙩𝙖.𝙘𝙤𝙢/𝙝𝙤𝙧𝙞𝙯𝙤𝙣/𝙞𝙣𝙨𝙩𝙖𝙡𝙡-𝙘𝙡𝙞/ | 𝙨𝙝 𝙄𝙣𝙨𝙩𝙖𝙡𝙡 𝙤𝙣 𝙒𝙞𝙣𝙙𝙤𝙬𝙨 (𝙋𝙤𝙬𝙚𝙧𝙎𝙝𝙚𝙡𝙡): 𝙞𝙬𝙧 -𝙪𝙨𝙚𝙗 𝙝𝙩𝙩𝙥𝙨://𝙙𝙚𝙫𝙚𝙡𝙤𝙥𝙚𝙧𝙨.𝙢𝙚𝙩𝙖.𝙘𝙤𝙢/𝙝𝙤𝙧𝙞𝙯𝙤𝙣/𝙞𝙣𝙨𝙩𝙖𝙡𝙡-𝙘𝙡𝙞/𝙬𝙞𝙣𝙙𝙤𝙬𝙨/ | 𝙞𝙚𝙭 🎥 The video in this post shows you exactly how the Meta VR CLI is used to gain performance analysis from perfetto traces, which is normally time consuming & complex to do it manually.show more

Dilmer

49,945 subscribers

10,278 views • 19 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Meta just shipped the official Ads CLI 🤯 The first time you can plug Claude Code directly into your Meta ad account without a third-party connector or (allegedly) getting your account banned. Plug it into Claude Code and Claude can pull live performance data, build dashboards, and analyze creative fatigue, all from one prompt. Here's what's possible inside Claude Code: → Pull last 30 days of campaign performance into a styled HTML dashboard → Find every ad with frequency over 3.0 or CTR drops over 20% week-over-week → Generate weekly client reports written in your brand voice → Run anomaly detection on spend, CPM, and conversions → Build creative fatigue alerts that flag dying ads before CPAs blow up The biggest difference from every third-party Meta MCP that's been floating around: This one is built and maintained by Meta themselves. Most folks running Meta ads won't touch third-party connectors because the ban risk is real. The official CLI (mostly) eliminates that. It's your token, your app, your direct connection to Meta's API. I put together the complete playbook: → The exact 15-minute setup: Meta Developer App, system user, asset assignment, token generation → 20+ prompt templates for reporting, fatigue detection, opportunity scoring, and anomaly analysis → A weekly operating cadence: Monday performance pull, Wednesday creative review, Friday exec brief → Rate limit guardrails so you don't trip Meta's automated enforcement → The 5 prompts to run first Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

35,834 views • 5 months ago

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Akshay 🚀

258,823 views • 3 months ago

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

Avi Chawla

30,932 views • 10 months ago

I just vibe coded a Meta Ads creative analytics tool in Claude Code 🤯 It syncs your ad accounts, AI-analyzes every creative, and tells you exactly what's working, what's not, and WHY. Built 100% in Claude Code. Perfect for DTC brands and agencies who are tired of staring at Meta Ads Manager trying to figure out WHY an ad is working or not. Here's the problem: Meta gives you the data. Spend, ROAS, CTR, hook rate. But it never tells you WHY an ad is performing or what to do about it. You're left manually watching videos, guessing at angles, and making gut-call decisions on what to iterate. This tool solves it: → Connect your Meta ad accounts → AI watches every video and analyzes every static → Auto-labels each ad by asset type, messaging angle, hook tactic, and funnel stage → Win rate analysis broken down by every category → Kill/scale recommendations segmented by TOF, MOF, and BOF → AI-generated iteration recommendations for every underperforming ad No manual video watching. No guessing at what's working. No spreadsheets to track creative performance. What you get: - Full creative analytics dashboard - AI classification on every ad - Iteration priorities for ads with real spend behind them - Weekly reports with top/bottom performers and AI insights I recorded a full walkthrough showing exactly how this works and what every feature does, including ALL the prompts I used so you can build it yourself. Want access to all the prompts for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just vibe coded a Meta Ads creative analytics tool in Claude Code 🤯 It syncs your ad accounts, AI-analyzes every creative, and tells you exactly what's working, what's not, and WHY. Built 100% in Claude Code. Perfect for DTC brands and agencies who are tired of staring at Meta Ads Manager trying to figure out WHY an ad is working or not. Here's the problem: Meta gives you the data. Spend, ROAS, CTR, hook rate. But it never tells you WHY an ad is performing or what to do about it. You're left manually watching videos, guessing at angles, and making gut-call decisions on what to iterate. This tool solves it: → Connect your Meta ad accounts → AI watches every video and analyzes every static → Auto-labels each ad by asset type, messaging angle, hook tactic, and funnel stage → Win rate analysis broken down by every category → Kill/scale recommendations segmented by TOF, MOF, and BOF → AI-generated iteration recommendations for every underperforming ad No manual video watching. No guessing at what's working. No spreadsheets to track creative performance. What you get: - Full creative analytics dashboard - AI classification on every ad - Iteration priorities for ads with real spend behind them - Weekly reports with top/bottom performers and AI insights I recorded a full walkthrough showing exactly how this works and what every feature does, including ALL the prompts I used so you can build it yourself. Want access to all the prompts for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

83,074 views • 7 months ago

You’ve probably seen some of the games I’ve been building with AI. I can't code. But with AI's help, I've built 15+ game prototypes in the past 6 months. That process has been eye-opening. It made me realize how fast game creation is evolving and how much easier it’s becoming to turn ideas into playable worlds. So I started Vibeforge, a Patreon where I share everything I’ve learned about using AI to make games: - Step-by-step vibe-coding guides (like this top-down auto-shooter) - Behind-the-scenes devlogs as I experiment with new prototypes - Game boilerplates you can modify for your own projects I’m joined by Aldric Chang, founder of the game studio behind 13Z: The Zodiac Trials ➡️ Wishlist on Steam!, Hellsweeper VR, Sairento VR and Gordian Quest. While I focus on AI-driven experimentation, Aldric will be sharing real-world lessons from traditional game development: design, production, and marketing, bridging both worlds. Whether you’re building your first prototype or dreaming up your next indie project, we welcome you to join us: See you on the inside.

You’ve probably seen some of the games I’ve been building with AI. I can't code. But with AI's help, I've built 15+ game prototypes in the past 6 months. That process has been eye-opening. It made me realize how fast game creation is evolving and how much easier it’s becoming to turn ideas into playable worlds. So I started Vibeforge, a Patreon where I share everything I’ve learned about using AI to make games: - Step-by-step vibe-coding guides (like this top-down auto-shooter) - Behind-the-scenes devlogs as I experiment with new prototypes - Game boilerplates you can modify for your own projects I’m joined by Aldric Chang, founder of the game studio behind 13Z: The Zodiac Trials ➡️ Wishlist on Steam!, Hellsweeper VR, Sairento VR and Gordian Quest. While I focus on AI-driven experimentation, Aldric will be sharing real-world lessons from traditional game development: design, production, and marketing, bridging both worlds. Whether you’re building your first prototype or dreaming up your next indie project, we welcome you to join us: See you on the inside.

Danny Limanseta

76,932 views • 11 months ago

Claude Cowork is f*cking cracked for Meta Ads 🤯 Point it at a folder with your ad export, your brand context, and your brief template —> ... and it analyzes your account like a senior creative strategist + saves a finished brief directly to your computer. All inside Claude Cowork. Perfect for DTC brands and agencies who are still manually digging through ad reports trying to figure out why performance shifted. If you're running Meta Ads and pulling weekly reports that tell you what happened but not why — CPAs creeping up, CTRs dropping... You're killing creatives on gut feel because mapping performance back to hook type, angle, and offer framing takes hours you don't have. Claude Cowork eliminates the entire loop: → Drop your Meta Ads CSV export into a project folder → Add a brand context file and your brief template → Claude reads all three files and audits across 4 lenses: hook performance, offer angles, fatigue signals, next test recommendations → Asks clarifying questions if it needs them → Saves a finished creative brief as a real .md file directly to your folder No copy-pasting data into chat windows. No manually tagging creatives in a spreadsheet. No "here are your metrics" summaries that tell you nothing new. What you get: → Pattern analysis across every creative — which hook structures are converting and why → Creative fatigue signals before CPAs blow up → Competitor intelligence layered in from the Meta Ad Library → A data-backed brief your creative team can execute immediately Set it up once, drop in a fresh CSV every week and run the same prompt. I put together a full playbook with the exact folder setup, the prompts, and the brief template to get this running in under 30 minutes. Want it for free? > Like this post > Comment "ADS" And I'll send it over (must be following so I can DM)

Mike Futia

85,910 views • 7 months ago

I just built a Claude skill that audits your entire Meta Ads account in under 5 minutes 🤯 Export your CSV from Ads Manager → drop it into Claude → get back an account health score, a wasted spend breakdown, and a prioritized fix list telling you exactly what to change this week. All inside Claude Cowork. Perfect for DTC brands and agencies who are running Meta Ads but have no idea which creatives are bleeding budget, which audiences stopped converting, or why CPA crept up 40% last month. If your weekly Meta workflow still looks like this — open Ads Manager, stare at the dashboard, sort by spend, squint at CTR columns, export a CSV you never actually analyze, close the tab and hope for the best... This skill runs the full audit for you: → Reads your Meta Ads CSV export (campaign, ad set, and ad-level data) → Scores your account 0-100 across 6 dimensions: creative health, audience efficiency, budget allocation, funnel performance, fatigue signals, and offer effectiveness → Calculates your exact wasted spend in dollars: every ad with spend and zero purchases → Identifies creative fatigue before it tanks your CPA (declining CTR + rising frequency + increasing cost) → Flags audience overlap and saturation across ad sets → Delivers a top-5 fix list ranked by how much money each fix saves you No API connection. No third-party tool access to your ad account. No risk of Meta flagging your account. What you get: →A full account health score (0-100) with a grade for each dimension →Your exact wasted spend in dollars (not a vague "you're overspending") →Creative fatigue signals with specific ads to kill or refresh this week →Audience efficiency analysis showing which ad sets are cannibalizing each other →A prioritized fix list ranked by budget impact (do #1 first, save the most money) One CSV export, one prompt. Five minutes. I put together the full playbook with the skill file, the scoring methodology, and the exact CSV export steps from Ads Manager. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Claude skill that audits your entire Meta Ads account in under 5 minutes 🤯 Export your CSV from Ads Manager → drop it into Claude → get back an account health score, a wasted spend breakdown, and a prioritized fix list telling you exactly what to change this week. All inside Claude Cowork. Perfect for DTC brands and agencies who are running Meta Ads but have no idea which creatives are bleeding budget, which audiences stopped converting, or why CPA crept up 40% last month. If your weekly Meta workflow still looks like this — open Ads Manager, stare at the dashboard, sort by spend, squint at CTR columns, export a CSV you never actually analyze, close the tab and hope for the best... This skill runs the full audit for you: → Reads your Meta Ads CSV export (campaign, ad set, and ad-level data) → Scores your account 0-100 across 6 dimensions: creative health, audience efficiency, budget allocation, funnel performance, fatigue signals, and offer effectiveness → Calculates your exact wasted spend in dollars: every ad with spend and zero purchases → Identifies creative fatigue before it tanks your CPA (declining CTR + rising frequency + increasing cost) → Flags audience overlap and saturation across ad sets → Delivers a top-5 fix list ranked by how much money each fix saves you No API connection. No third-party tool access to your ad account. No risk of Meta flagging your account. What you get: →A full account health score (0-100) with a grade for each dimension →Your exact wasted spend in dollars (not a vague "you're overspending") →Creative fatigue signals with specific ads to kill or refresh this week →Audience efficiency analysis showing which ad sets are cannibalizing each other →A prioritized fix list ranked by budget impact (do #1 first, save the most money) One CSV export, one prompt. Five minutes. I put together the full playbook with the skill file, the scoring methodology, and the exact CSV export steps from Ads Manager. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

36,164 views • 5 months ago

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑

Vercel Developers

963,432 views • 1 month ago

Running cold email campaigns just became a whole lot easier Smartlead now runs an MCP server, which in plain terms means Claude can read and act on your live campaign data directly instead of working off a spreadsheet that went stale the moment you exported it. The workflow is worth walking through properly, because it is shorter than people expect. You generate an API key inside your account, point Claude at the server once, and from then on you ask for what you want in a sentence. Here is a prompt worth stealing in full: "Fetch all Smartlead clients, then get today's performance for each: emails sent, replied, positive replies, unique lead count. Compute reply rate per client, run a top and bottom performer analysis, format it as a daily client performance report, and post it to Slack." One paste, and it pulls live figures for every account, does the arithmetic, ranks the strongest and the weakest, and delivers the finished thing into the channel your team already sits in, before anyone has logged on for the day. Be clear about the division of labour, because it is what makes this useful rather than a novelty. Smartlead is the engine holding the campaigns, the mailboxes, the warmup and the reply data, and Claude is simply the interface you operate all of it through, so nothing about your sending changes and everything about how you interrogate it does. The effect people underestimate is on the questions you start asking. Once a report costs you a sentence rather than an afternoon, you stop rationing the ones that used to feel like too much trouble, and problems that used to surface on a Friday start surfacing on a Tuesday. Connect it with Claude through MCP and run one prompt against your own account today.

Running cold email campaigns just became a whole lot easier Smartlead now runs an MCP server, which in plain terms means Claude can read and act on your live campaign data directly instead of working off a spreadsheet that went stale the moment you exported it. The workflow is worth walking through properly, because it is shorter than people expect. You generate an API key inside your account, point Claude at the server once, and from then on you ask for what you want in a sentence. Here is a prompt worth stealing in full: "Fetch all Smartlead clients, then get today's performance for each: emails sent, replied, positive replies, unique lead count. Compute reply rate per client, run a top and bottom performer analysis, format it as a daily client performance report, and post it to Slack." One paste, and it pulls live figures for every account, does the arithmetic, ranks the strongest and the weakest, and delivers the finished thing into the channel your team already sits in, before anyone has logged on for the day. Be clear about the division of labour, because it is what makes this useful rather than a novelty. Smartlead is the engine holding the campaigns, the mailboxes, the warmup and the reply data, and Claude is simply the interface you operate all of it through, so nothing about your sending changes and everything about how you interrogate it does. The effect people underestimate is on the questions you start asking. Once a report costs you a sentence rather than an afternoon, you stop rationing the ones that used to feel like too much trouble, and problems that used to surface on a Friday start surfacing on a Tuesday. Connect it with Claude through MCP and run one prompt against your own account today.

Tim

21,666 views • 16 days ago

BREAKING: Claude Code + Meta Ads MCP replaced my $5K/month creative strategist. It connected to my Ad Manager. Looked at my best ads. Then cranked out 12 new ads ready to launch. Took minutes. Here's the full system. No coding required. Most marketers I know still download CSVs from Meta Ads. Paste them into ChatGPT. Ask "what should I change." That worked in 2024. In 2026 you can plug Claude right into your live Meta ad data. Uses something called MCP. Model Context Protocol. Then run it straight into your AI ad making process. Here's what it does. Pulls live campaign data on command. "Show me my top 3 ads by ROAS this week." Answer in seconds. Finds what makes your winning ads work. Looks at the hooks, visuals, and buttons that get clicks from your best stuff. Writes creative briefs automatically. Gives you the angle. The visual style. The pacing. Not spreadsheets. Real creative direction. Makes ready-to-use prompts for HeyOz. Copy and paste into your AI ad tool. Get launch-ready ads from one idea. Spots tired ads before costs spike. Watches click rate, frequency, and spend. Tells you when an ad is dying. Here's the part most people miss. It doesn't just look at your ads. It makes the next batch for you. All in one chat. Setup takes about 15 minutes. No coding required. I don't know why more agencies aren't using this yet. Comment LOOP and I'll send the one-click setup guide.

BREAKING: Claude Code + Meta Ads MCP replaced my $5K/month creative strategist. It connected to my Ad Manager. Looked at my best ads. Then cranked out 12 new ads ready to launch. Took minutes. Here's the full system. No coding required. Most marketers I know still download CSVs from Meta Ads. Paste them into ChatGPT. Ask "what should I change." That worked in 2024. In 2026 you can plug Claude right into your live Meta ad data. Uses something called MCP. Model Context Protocol. Then run it straight into your AI ad making process. Here's what it does. Pulls live campaign data on command. "Show me my top 3 ads by ROAS this week." Answer in seconds. Finds what makes your winning ads work. Looks at the hooks, visuals, and buttons that get clicks from your best stuff. Writes creative briefs automatically. Gives you the angle. The visual style. The pacing. Not spreadsheets. Real creative direction. Makes ready-to-use prompts for HeyOz. Copy and paste into your AI ad tool. Get launch-ready ads from one idea. Spots tired ads before costs spike. Watches click rate, frequency, and spend. Tells you when an ad is dying. Here's the part most people miss. It doesn't just look at your ads. It makes the next batch for you. All in one chat. Setup takes about 15 minutes. No coding required. I don't know why more agencies aren't using this yet. Comment LOOP and I'll send the one-click setup guide.

Ahad Shams | AI Ads Guy

31,563 views • 4 months ago

I just vibe coded a Meta Ads creative analytics tool in Claude Code 🤯 It plugs into your ad accounts, AI-analyzes every creative you've ever run, and tells you exactly what's working, what isn't, and WHY. Built 100% in Claude Code. Perfect for DTC brands and creative agencies who are sick of staring at Ads Manager trying to reverse-engineer why one ad scaled and another tanked. If you're pulling weekly reports that show you spend, ROAS, CTR, and hook rate but never tell you WHY any of it is happening — and you're stuck watching videos one by one, guessing at angles, and making kill/scale calls on gut feel... This tool runs the entire loop for you: → Connect your Meta ad accounts in one click → AI watches every video and analyzes every static → Auto-labels each ad by asset type, messaging angle, hook tactic, and funnel stage → Win rate analysis broken down by every category → Kill/scale recommendations segmented by TOF, MOF, and BOF → AI-generated iteration recommendations for every underperformer No manual video watching. No guessing at what's working. No spreadsheets to track creative performance. What you get: - A full creative analytics dashboard pulling live from your accounts - AI classification on every ad you've ever run - Iteration priorities ranked by ads with real spend behind them - Weekly reports surfacing top and bottom performers with AI insights Built 100% in Claude Code as a real tool, not a one-off script. I recorded a full walkthrough showing exactly how this works and what every feature does, including ALL the prompts I used so you can build it yourself. Want access to all the prompts for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just vibe coded a Meta Ads creative analytics tool in Claude Code 🤯 It plugs into your ad accounts, AI-analyzes every creative you've ever run, and tells you exactly what's working, what isn't, and WHY. Built 100% in Claude Code. Perfect for DTC brands and creative agencies who are sick of staring at Ads Manager trying to reverse-engineer why one ad scaled and another tanked. If you're pulling weekly reports that show you spend, ROAS, CTR, and hook rate but never tell you WHY any of it is happening — and you're stuck watching videos one by one, guessing at angles, and making kill/scale calls on gut feel... This tool runs the entire loop for you: → Connect your Meta ad accounts in one click → AI watches every video and analyzes every static → Auto-labels each ad by asset type, messaging angle, hook tactic, and funnel stage → Win rate analysis broken down by every category → Kill/scale recommendations segmented by TOF, MOF, and BOF → AI-generated iteration recommendations for every underperformer No manual video watching. No guessing at what's working. No spreadsheets to track creative performance. What you get: - A full creative analytics dashboard pulling live from your accounts - AI classification on every ad you've ever run - Iteration priorities ranked by ads with real spend behind them - Weekly reports surfacing top and bottom performers with AI insights Built 100% in Claude Code as a real tool, not a one-off script. I recorded a full walkthrough showing exactly how this works and what every feature does, including ALL the prompts I used so you can build it yourself. Want access to all the prompts for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

55,149 views • 5 months ago

Seems like Visual Studio Code is starting to tell you: your agent primitives need to move. There is now a new migration banner in the Chat panel, and it is part of a much bigger change happening under the hood: the move from the old Local harness to the new Agent Host architecture built around AHP. This is not just about moving where an agent runs. The old model was very VS Code-centric: prompts, custom agents, instructions and skills could live in VS Code-specific locations and the agent runtime lived inside the extension host. The new Agent Host separates the agent runtime from the editor. Sessions can keep running when the window closes, be shared across VS Code windows, run remotely, and support different harnesses such as Copilot, CLI and Copilot Desktop App through a common session layer. And that means some of our primitives need to move too. Prompt files are being deprecated for Agent Host and migrated to Skills. User-level agents and instructions that lived in VS Code profile storage need to move to harness-supported locations. Even the old location settings are being deprecated. The new migration experience can detect these things and guide you through moving or converting them, while keeping the originals unless you explicitly remove them. The new banner is basically the first visible sign that this migration is becoming a real product workflow. Basically telling us - it's time to move on!!!! If you have accumulated a lot of prompts, custom agents, instructions and skills over the last year, now is probably a good time to understand where they actually live and which harness owns them. To summarize the shift - it isn't just: VS Code Chat → Agent Host It is: VS Code-specific primitives → harness-native primitives. And I think this is going to become increasingly important as agents stop being features inside an IDE and become runtimes that multiple clients can connect to. Go run your migrations now 🏃‍♀️

Oren Melamed

29,753 views • 4 days ago

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.

Rohan Paul

178,460 views • 1 year ago

Claude Code + Google Stitch 2.0 is f*cking cracked 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)

Mike Futia

126,588 views • 6 months ago

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Rachel🥥

61,994 views • 3 months ago

If you’ve ever managed custom icons in React Native, you know the frustration of choosing between performance and developer experience. Libraries like 𝗿𝗲𝗮𝗰𝘁-𝗻𝗮𝘁𝗶𝘃𝗲-𝘀𝘃𝗴 are flexible but heavy. Every icon creates its own React subtree. The alternative? Manual icon fonts that force you into a constant back-and-forth of using web tools like IcoMoon and syncing font assets every time a design changes. 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗠𝗮𝗻𝘀𝗶𝗼𝗻 𝗟𝗮𝗯𝘀 just released 𝗿𝗲𝗮𝗰𝘁-𝗻𝗮𝘁𝗶𝘃𝗲-𝗻𝗮𝗻𝗼-𝗶𝗰𝗼𝗻𝘀 to solve exactly this. It’s a build-time icon font generator that gives you the performance of native fonts with the flexibility of simple SVG files. 𝗪𝗵𝗮𝘁’𝘀 𝗵𝗮𝗽𝗽𝗲𝗻𝗶𝗻𝗴? Instead of rendering complex vector paths at runtime, this library automatically converts your folder of SVGs into an optimized icon font during the build process. It essentially teaches your app to treat icons like standard text characters, which allows it to bypass React’s component tree and layout engine entirely. ➡️ 𝗕𝘂𝗶𝗹𝗱-𝘁𝗶𝗺𝗲 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻: It handles the entire pipeline—watching your icon folder, converting SVGs to .ttf files, and linking them to your native project automatically. ➡️ 𝗡𝗮𝘁𝗶𝘃𝗲 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲: Because icons render as native text glyphs, it is significantly faster than traditional SVG rendering, making it the ideal choice for long, scrollable lists or icon-heavy dashboards. ➡️ 𝗘𝘅𝗽𝗼 𝗖𝗼𝗻𝗳𝗶𝗴 𝗣𝗹𝘂𝗴𝗶𝗻: It features first-class support for Expo, automating the native plumbing like Info.plist updates and asset linking during the prebuild phase. ➡️ 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗧𝘆𝗽𝗲 𝗦𝗮𝗳𝗲𝘁𝘆: The library generates TypeScript definitions for your icon set, providing full IDE autocomplete and ensuring you never break the UI with a misspelled icon name. 𝗪𝗵𝘆 𝗶𝘁 𝗺𝗮𝘁𝘁𝗲𝗿𝘀? In high-performance applications, small overheads add up. By shifting the heavy lifting from the mobile device to your build machine, 𝗿𝗲𝗮𝗰𝘁-𝗻𝗮𝘁𝗶𝘃𝗲-𝗻𝗮𝗻𝗼-𝗶𝗰𝗼𝗻𝘀 ensures your UI stays buttery smooth while keeping your developer workflow modern. It’s another great example of how 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗠𝗮𝗻𝘀𝗶𝗼𝗻 continues to solve the "last mile" of performance friction in the ecosystem. Before you migrate your entire library, keep in mind: this is designed for the 𝗡𝗲𝘄 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 (Fabric) and requires React Native 0.74 or higher. #ReactNative #Expo #SoftwareMansion #Icons #MobileDev #Performance #DeveloperExperience #OpenSource #JavaScript #TypeScript #SVG #Fabric

If you’ve ever managed custom icons in React Native, you know the frustration of choosing between performance and developer experience. Libraries like 𝗿𝗲𝗮𝗰𝘁-𝗻𝗮𝘁𝗶𝘃𝗲-𝘀𝘃𝗴 are flexible but heavy. Every icon creates its own React subtree. The alternative? Manual icon fonts that force you into a constant back-and-forth of using web tools like IcoMoon and syncing font assets every time a design changes. 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗠𝗮𝗻𝘀𝗶𝗼𝗻 𝗟𝗮𝗯𝘀 just released 𝗿𝗲𝗮𝗰𝘁-𝗻𝗮𝘁𝗶𝘃𝗲-𝗻𝗮𝗻𝗼-𝗶𝗰𝗼𝗻𝘀 to solve exactly this. It’s a build-time icon font generator that gives you the performance of native fonts with the flexibility of simple SVG files. 𝗪𝗵𝗮𝘁’𝘀 𝗵𝗮𝗽𝗽𝗲𝗻𝗶𝗻𝗴? Instead of rendering complex vector paths at runtime, this library automatically converts your folder of SVGs into an optimized icon font during the build process. It essentially teaches your app to treat icons like standard text characters, which allows it to bypass React’s component tree and layout engine entirely. ➡️ 𝗕𝘂𝗶𝗹𝗱-𝘁𝗶𝗺𝗲 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻: It handles the entire pipeline—watching your icon folder, converting SVGs to .ttf files, and linking them to your native project automatically. ➡️ 𝗡𝗮𝘁𝗶𝘃𝗲 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲: Because icons render as native text glyphs, it is significantly faster than traditional SVG rendering, making it the ideal choice for long, scrollable lists or icon-heavy dashboards. ➡️ 𝗘𝘅𝗽𝗼 𝗖𝗼𝗻𝗳𝗶𝗴 𝗣𝗹𝘂𝗴𝗶𝗻: It features first-class support for Expo, automating the native plumbing like Info.plist updates and asset linking during the prebuild phase. ➡️ 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗧𝘆𝗽𝗲 𝗦𝗮𝗳𝗲𝘁𝘆: The library generates TypeScript definitions for your icon set, providing full IDE autocomplete and ensuring you never break the UI with a misspelled icon name. 𝗪𝗵𝘆 𝗶𝘁 𝗺𝗮𝘁𝘁𝗲𝗿𝘀? In high-performance applications, small overheads add up. By shifting the heavy lifting from the mobile device to your build machine, 𝗿𝗲𝗮𝗰𝘁-𝗻𝗮𝘁𝗶𝘃𝗲-𝗻𝗮𝗻𝗼-𝗶𝗰𝗼𝗻𝘀 ensures your UI stays buttery smooth while keeping your developer workflow modern. It’s another great example of how 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗠𝗮𝗻𝘀𝗶𝗼𝗻 continues to solve the "last mile" of performance friction in the ecosystem. Before you migrate your entire library, keep in mind: this is designed for the 𝗡𝗲𝘄 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 (Fabric) and requires React Native 0.74 or higher. #ReactNative #Expo #SoftwareMansion #Icons #MobileDev #Performance #DeveloperExperience #OpenSource #JavaScript #TypeScript #SVG #Fabric

The React Native Rewind

24,992 views • 4 months ago

90% of "AI developers" just download pre packaged GGUF files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.

Alok

62,631 views • 2 months ago

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

12,875 views • 4 months ago