Greg Isenberg

“Greg Isenberg shared a masterclass on using interviews, systems-of-record mining, documentation review, and four-way sorting—delete, plain code, agent, or human decision—to rebuild workflows in Salesforce, NetSuite, and Slack.”

#16 ▶️ Masterclass: How FDEs make $1M/yr deploying AI agents Greg Isenberg Greg Isenberg shared a masterclass on using interviews, systems-of-record mining, documentation review, and four-way sorting—delete, plain code, agent, or human decision—to rebuild workflows in Salesforce, NetSuite, and Slack. In one reported accounts-payable example, 2–3 weeks of mapping cut 17 steps to 7, cycle time from 24 days to 6 days, and handling cost from $31 to $6, while straight-through processing rose from 18% to 87%.

“In Greg Isenberg shared his view that building a ChatGPT plugin is a strong risk/reward bet, claiming 1.2 billion people use ChatGPT weekly and that, as of the day before his post, it recommended plugins during conversations.”

In Greg Isenberg shared his view that building a ChatGPT plugin is a strong risk/reward bet, claiming 1.2 billion people use ChatGPT weekly and that, as of the day before his post, it recommended plugins during conversations. He advised turning recurring workflows into plugins, matching descriptions to user phrasing, shipping five, and doubling down on the one gaining the most traction. He predicted that recommendation slots would become crowded within 12 months.

“Astra + 50 Models: This Is the New SaaS Greg Isenberg Studio Operator is built with Astra and the Higgsfield API as a semi-autonomous AI-native creative-service workflow that ingests briefs from Upwork or Fiverr, routes production across creative models, performs QA and repairs, and sends work to human approval.”

#9 Astra + 50 Models: This Is the New SaaS Greg Isenberg Studio Operator is built with Astra and the Higgsfield API as a semi-autonomous AI-native creative-service workflow that ingests briefs from Upwork or Fiverr, routes production across creative models, performs QA and repairs, and sends work to human approval. Studio Operator’s dashboard lists 25 active jobs, a $3,400 pipeline value, $3,200 in estimated gross profit, and 17 projects needing attention; a blood-orange aperitif PNG job priced at $10 had an estimated Higgsfield production cost of about $0.01 and expected profit of $9.99. The system was built in six prompts: create the operating-system shell; extract deliverables, formats, assets, risks, and questions from marketplace briefs; connect the Higgsfield API; build a model router; add QA and repair; and add spend limits, repair limits, approved models, client-message rules, approval gates, memory, and an audit log. Model routing assigns Soul to people, Seedream or Flux to product scenes, Ideogram or Recraft to text and layouts, Qwen to localized repairs, Seedance to longer scenes, Kling to hero shots, Wan or Minimax to speaking scenes, Kling Motion Control to copied movement, and Topaz plus finishing tools to resolution, captions, voice, and exports; a five-second aperitif video was estimated at about $0.70 before a 5–15% marketplace channel fee.

“Jev is used as a structured-output classifier that receives an input plus an output schema and returns probability-based decisions in about 200 milliseconds per query, including categorizing 1,700 emails for 18 cents.”

#5 ▶️ Jev is HERE. How to use it Greg Isenberg Jev is used as a structured-output classifier that receives an input plus an output schema and returns probability-based decisions in about 200 milliseconds per query, including categorizing 1,700 emails for 18 cents. Ryan Vogle passed 1,700 email objects into Jev with category, priority, spam-score, and reply-likelihood output fields; the run used 4.2 million input tokens and 500,000 output tokens and cost 18 cents.

“Instinct is used through iMessage to research and book a Copenhagen haircut and Bistro Central table, submit a Bali visa-on-arrival application and arrival card, and create an Emirates Skywards account.”

#20 ▶️ Instinct AI is For Real. What You Need to Know. Greg Isenberg Instinct is used through iMessage to research and book a Copenhagen haircut and Bistro Central table, submit a Bali visa-on-arrival application and arrival card, and create an Emirates Skywards account. Remy signs in with a phone number, chats with Instinct through iMessage and WhatsApp, and uses a web workspace with connectors for email, Slack, Granola, Outlook, Linear, and GitHub plus a vault for logins, cards, addresses, and phone numbers.

“Making $$$ with Grok Bot Greg Isenberg Billy Howell runs The Arlington Bagel, a Thursday local newsletter for 6,000 Arlingtonians, with a Grockbot agent team consisting of a chief of staff, research, sales, Beehive, and other specialized agents.”

#13 ▶️ Making $$$ with Grok Bot Greg Isenberg Billy Howell runs The Arlington Bagel, a Thursday local newsletter for 6,000 Arlingtonians, with a Grockbot agent team consisting of a chief of staff, research, sales, Beehive, and other specialized agents. Billy Howell keeps one business per Grockbot account to avoid context bloat and token consumption; he pays $200 for a separate Grockbot account dedicated to a Shopify experiment. His four-week Grockbot workflow is: build the initial team in week one, execute without adding agents or tinkering in week two, add or remove agents for real gaps in week three, and add automated routines in week four. The Arlington Bagel research agent checks sources twice weekly and creates Notion cards; Make.com formats newsletter blurbs, Beehive sends the issue each Thursday, and the Gmail-connected sales agent found a local bagel-shop sponsorship lead.

“▶️ Biggest Unlock for AI Agents in 2026: Skillsmaxxing Greg Isenberg Remy stores company agent skills as Markdown SOPs in a GitHub repository, converts the repository into department-specific plugins with JSON files, and installs those plugins in Claude Code and Codex with auto-update enabled.”

GenAI PM Daily August 20, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 20 insights for PM Builders, ranked by relevance from Blogs, X, YouTube, and LinkedIn. OpenAI announces Zero Data Retention for frontier models #1 📝 OpenAI News Offering Zero Data Retention for frontier models - OpenAI announces offering zero data retention for frontier models, committing to not retain user data for those models and clarifying how this impacts customers and data handling. The post outlines the company's privacy-focused approach for frontier model interactions. Also covered by: @OpenAI , @OpenAI , @Sam Altman #2 𝕏 Cursor announced that it can now monitor pull requests, watch a Slack thread, and run scheduled tasks. Cloud agents automatically subscribe to pull requests they create and drive them to completion. #3 𝕏 Mustafa Suleyman announced that MAI-Image-2.5 is ranked #1 on the Artificial Analysis leaderboard for image editing. #4 𝕏 Logan Kilpatrick announced that Google AI Studio now supports GitHub repository imports and bi-directional push/pull synchronization. A new UI also supports force pushes and merges. #5 𝕏 Qwen shared that Qwen3.8-27B ranked as the #1 open-weight model on Harvey’s Legal Agent benchmark, describing it as capable of professional tasks while remaining small enough to run locally. #6 𝕏 NVIDIA shared that NVIDIA cuOpt, its open-source solver, is the fastest open-source solver on Hans Mittelmann benchmarks across three optimization problem classes. #7 𝕏 Results from benchmarks of 300+ NVIDIA verified skills on real tasks showed that using skills improved correctness by 41 points, effectiveness by 39 points, and efficiency by 35 points. SkillEvaluator is open source for testing skills before shipping. #8 𝕏 Philipp Schmid shared that Gemini 3.7 Flash ranked first on Artificial Analysis’s new AA-AnalystAgent, which covers 80 real-world quantitative analysis tasks across 14 business and scientific domains. #9 𝕏 Claire Vo shared how she uses Codex browser/Chrome/computer for operational tasks including accounting, inbox management, Stripe Radar configuration, browser-based QA, security questionnaires, SaaS setup when an API is unavailable, and subscription cancellation. #10 𝕏 Madhu Guru shared an eval strategy for AI products: define a rubric, use the best available measurement process to establish a trustworthy quality frontier, then reduce costs through automation, smaller judge models, sampling, and deterministic checks where relevant. #11 𝕏 Santiago shared an unnamed automated AI agent security testing tool for chat, code, and phone-based voice agents that runs 10,000+ jailbreaks and adversarial attacks. #12 ▶️ Biggest Unlock for AI Agents in 2026: Skillsmaxxing Greg Isenberg Remy stores company agent skills as Markdown SOPs in a GitHub repository, converts the repository into department-specific plugins with JSON files, and installs those plugins in Claude Code and Codex with auto-update enabled.

“Cloudflare’s AI crawl control, pay per crawl, Monetization Gateway, and x402 payment rail use HTTP 402 responses to charge AI agents for access to pages, datasets, APIs, MCP tool calls, files, and search indexes.”

Cloudflare will make 1000+ AI millionaires Greg Isenberg Cloudflare’s AI crawl control, pay per crawl, Monetization Gateway, and x402 payment rail use HTTP 402 responses to charge AI agents for access to pages, datasets, APIs, MCP tool calls, files, and search indexes. Under x402, an agent requests a resource, receives an HTTP 402 “Payment Required” response containing the price, pays, retries with proof of payment, and Cloudflare verifies the payment at the edge before the request reaches the origin.

“A cron-based cold-outbound agent pulls LinkedIn post engagers through Apify and API Maestro, waterfalls their profiles into email and phone data for email and LinkedIn outreach, while a second agent converts calls, Slack, and transcripts into LinkedIn posts scheduled through Ordinal.”

#20 ▶️ These AI Marketing Agents Get You Customers Greg Isenberg A cron-based cold-outbound agent pulls LinkedIn post engagers through Apify and API Maestro, waterfalls their profiles into email and phone data for email and LinkedIn outreach, while a second agent converts calls, Slack, and transcripts into LinkedIn posts scheduled through Ordinal. API Maestro’s Apify actors for LinkedIn profile posts, post reactions, and post comments were used with Claude Code; one post extraction returned 63 raw engager profiles before deduplication.

“How I AI Podcast Nick Baumann uses ChatGPT Work voice to delegate browser-based travel and expense tasks, ChatGPT Sites to build and privately share a searchable website, and a custom UGC Video plugin to turn raw clips into edited vertical videos.”

#9 ▶️ How this OpenAI engineer uses Codex + ChatGPT Work to automate everything How I AI Podcast Nick Baumann uses ChatGPT Work voice to delegate browser-based travel and expense tasks, ChatGPT Sites to build and privately share a searchable website, and a custom UGC Video plugin to turn raw clips into edited vertical videos. Using a hotkey-triggered voice orb that can read the current screen via an appshot, ChatGPT Work checked a Slack offsite message, checked calendar availability through plugins, created a travel task for SFO-to-Paris flights and a policy-compliant hotel in Navon, and created a separate task to find an Amazon microphone receipt and stage—without submitting—an expense report. ChatGPT Sites supports a SQL database, S3 file storage, and environment variables; the site built during the conversation used How I AI’s purple, black, and white branding, categorized video tips by AI tool and function, and could be shared publicly or restricted to individual email addresses through ChatGPT login. Nick Baumann’s UGC Video plugin processed roughly 20 clips in the live run by extracting transcripts, reviewing frames, selecting takes, and assembling an organic vertical video; for another workflow, he uploaded 50 or 60 clips for three videos, dictated the narratives, left it running overnight, and returned to completed outputs, including automated moving blurs over sensitive on-screen material. Also covered by: @claire vo