Ford AI Needed Human Expertise

Welcome to another edition of AI PlanetX.

Ford says human expertise still matters; Cursor brings AI coding agents to mobile; Meta faces scrutiny over chatbot safety testing.

• Hottest AI News

• Top AI & SaaS Tools

• AI Tutorial: Automate Meeting Prep with Gemini

• Top AI & Tech News

• AI Art Spotlight

• Prompt of the Day: Prompt Tech That Actually Work

• Featured AI Video

• Course of the Day: OpenAI Codex Masterclass

Hottest AI News

Ford

Ford Learned Human Expertise Cannot Be Automated

Ford’s AI lesson is bigger than cars. After leaning on AI cameras and automated quality checks, it brought back 350 veteran engineers because machines missed what experience, judgment, and product-cycle memory could see.

Details:

• Ford had 5,000 fewer workers than in 2020 and leaned on 900+ AI cameras for design/manufacturing checks. The problem: weak training data and lost know-how created blind spots

• The returning “greybeards” came from Ford and suppliers. They review designs early, mentor younger teams, rebuild AI workflows, and help stop issues before vehicles reach the line

• The payoff was not anti-AI. Ford kept AI for software tests and defect detection, improved quality rankings, and shifted from fixing recalls and warranty costs to preventing failures

The future won’t belong to companies replacing expertise quickest. It belongs to teams that redesign work and use AI to multiply people who know best.

Leading AI expert shares one email per day on what’s new & what’s next

AI moves faster than any single newsletter can cover. To actually stay current you'd need to read every major AI newsletter, listen to the AI podcasts that move thinking, watch what every AI lab ships, and scan public-company earnings calls, investor letters, and GitHub. Almost no one has time for that. 

MavSource fixes this in 5 minutes a day. We aggregate all of those sources, summarize what matters, analyze the trends shaping AI — across both public and private markets, apps and infrastructure — and send it as one daily email with founder commentary on what the day's signal actually means. 

No checking dozens of sources. No hype. One brief, every morning. Built for the people who can't afford to fall behind. Free.

Get The Free Brief →

Cursor

Cursor Launches Mobile App For Managing AI Coding Agents

Cursor just made AI coding mobile. The iOS app lets developers prompt agents from a phone, connect to the Cursor 2.0 agent shift, and move from writing every line to supervising software work anywhere, even off-desk.

Details:

• Current in public beta for paid plans, choose a repo, pick a frontier model, use voice or slash commands, and launch agents for features, bugs, incidents, UI fixes, or codebase questions

• Agents can run in cloud VMs or on your computer through Remote Control. Cursor keeps you updated with Live Activities and push alerts when work finishes, needs input, or is ready for review

• From the phone, you can review diffs, logs, demos, screenshots, and videos, annotate images for UI feedback, add follow-up instructions, move local sessions to cloud, and merge PRs on the go

The message is simple: phones may not replace laptops, but they can become the command center for supervising AI workers that build and test code.

Top AI & SaaS Tools

• AdPeekr (Life-time Deal): Competitor ad monitoring tool that tracks ads on Facebook, Instagram, LinkedIn, and Google 24/7 and sends email alerts when campaigns launch

• LongCat-2.0: 1.6T-parameter MoE model with about 48B active parameters and 1M-token context, designed for agentic coding and other long-context tasks [F-R-E-E to Try]

• Devin Fusion: Multi-model AI coding system that combines powerful and cheaper AI models, automatically routing work between them to maintain coding performance

• Brain2Qwerty v2: Meta’s non-invasive AI system that decodes brain recordings into text in real time with much higher accuracy than previous non-surgical methods

• Pluno: Browser automation tool that skips the UI and uses APIs directly to complete web app tasks quicker and more reliably than Claude’s browser extension [F-R-E-E to Try]

Meet America’s Newest $1B Unicorn

It just surpassed a $1B valuation, joining private US companies like SpaceX and OpenAI. Unlike them, you can invest in EnergyX today. General Motors already has. Why? EnergyX’s tech can recover up to 3X more lithium than traditional methods. Now, they hold rights to ~13M tons of lithium across North and South America. Invest in EnergyX at $13/share by 7/16.

Invest in EnergyX

^{Energy Exploration Technologies, Inc. (“EnergyX”) has engaged Beehiiv to publish this communication in connection with EnergyX’s ongoing Regulation A offering. Beehiiv has been paid in cash and may receive additional compensation. Beehiiv and/or its affiliates do not currently hold securities of EnergyX.}

^{This compensation and any current or future ownership interest could create a conflict of interest. Please consider this disclosure alongside EnergyX’s offering materials. EnergyX’s Regulation A offering has been qualified by the SEC. Offers and sales may be made only by means of the qualified offering circular. Before investing, carefully review the offering circular, including the risk factors. The offering circular is available at invest.energyx.com/.}

^{Comparisons to other companies are for informational purposes only and should not imply similar results. Past performance is not indicative of future results. Market shortfall are forward‑looking estimates and are subject to substantial uncertainty.}

AI Tutorial

How to Automate Meeting Prep with Google Gemini

Never enter a meeting unprepared. This guide shows a Google Workspace Studio automation that uses Gemini to create a meeting brief, organize context, suggest an agenda, and block time before the call.

1. Create meeting-based flow

   Go to Google Workspace Studio. Create a fresh flow. Choose Based on a meeting so it uses your Google Calendar meeting data.

2. Set trigger time

   Set the trigger to run 10–15 minutes before the meeting. This makes the prep block appear before the call starts.

3. Add Ask Gemini

   Add an Ask Gemini step. Ask Gemini to create a short prep brief from the meeting details.

   Prompt example:

   “Create a concise meeting prep brief using the meeting details. Include the meeting goal, key context, unresolved items, a suggested agenda, and smart questions to ask.”

4. Define brief sections

   Keep the brief focused on useful prep details:

   • Meeting context

   • Open loops or unresolved items

   • Suggested agenda

   • Questions to ask

5. Create Google Doc

   Add Create a doc next. Use the meeting title variable plus “Prep Brief” as the doc name. Use the Gemini output as the document body.

   Example:

   “[Meeting Title] Prep Brief”

6. Block prep time

   Add Block time as the final action. Use the meeting title and meeting start time variables. Add the Google Doc link variable in the prep block description. This lets you open the brief directly from Calendar.

7. Test workflow

   Create a test meeting in Google Calendar. Go back to Google Workspace Studio. Tap Test workflow. Select that meeting from the dropdown.

   Before turning it on, confirm that:

   • prep block appears before the meeting

   • Google Doc is created correctly

   • brief link opens from the calendar block

   Once everything works, turn the flow on.

Tip: Add meeting notes, agenda links, or related docs to the calendar event for better context.

Top AI & Tech News

• Meta used contractors posing as minors to test rival chatbots with thousands of crisis prompts about self-harm, sexual content, and drugs, raising privacy and safety concerns

• Anthropic’s latest Economic Index combines 24/7 Claude usage data with a survey of 9,700 users to show how people use AI daily and how they feel about it at work

• San Francisco’s AI boom is driving housing costs so high that even well-paid tech workers are struggling to afford rent

• DeepSeek open-sourced DSpark, a framework that speeds up LLM inference by up to 85% using speculative prediction and fast verification

AI Art Spotlight

Create Your Own Photo Like This Using the Prompt Below:

Modern editorial collage poster design. The background features four stacked rounded panels filled with black and white cinematic portraits of a stylish young man in different fashion poses. Overlaid in the foreground is a high-quality full-color cutout of the same man wearing a [COLOR] oversized shirt with black pants and sunglasses, striking a confident fashion pose. Clean minimal design, no text, no typography, no letters, soft shadows, depth layering, high contrast lighting, premium magazine style, ultra realistic, 8K, professional poster composition

Model: ChatGPT Images 2.0

Prompt of the Day

Top 30 Prompt Techniques That Actually Work in 2026

This X article (log in to X to view it) shares 30 practical prompt techniques for Claude or other AI tools in 2026, based on real daily use—not outdated advice. It includes core rules, advanced workflows, and copy-paste templates for coding, research, writing, debugging, and more.

Featured AI Video

F-R-E-E Wispr Flow, ElevenLabs, and CapCut Alternatives + More GitHub Hits

AI Course of the Day

OpenAI Codex Masterclass

This course provides an overview of OpenAI Codex as a software engineering agent and shows how it can support developers across the full workflow, from writing and reviewing code to running tests, exploring codebases, and automating recurring tasks.