GenAI PM
person53 mentions· Updated Nov 13, 2026

Greg Isenberg

Creator and commentator who recaps a Grok Bot tutorial. He is the presenter of the workflow example involving Ras Mic and Pluto.

Key Highlights

  • Greg Isenberg is presented as a creator and commentator who explains practical AI-agent workflows across product, marketing, and operations.
  • He recapped Ras Mic’s Grok Bot tutorial, including a Pluto workflow that used Claude Code and Opus-class models to generate five working pull requests.
  • His examples are useful to AI PMs because they emphasize workflow decomposition, agent orchestration, human approval gates, and data-layer integration.
  • He also framed ChatGPT plugins as a product-distribution opportunity, advising builders to package recurring workflows into focused plugin experiences.
  • Across the supplied mentions, Greg Isenberg consistently appears as a translator of emerging AI-native operating models into practical, repeatable patterns.

At a glance

Role
Creator

Greg Isenberg

Overview

Greg Isenberg is a creator, commentator, and workflow presenter who appears frequently in AI tooling and agent-related discussions. In the supplied mentions, he is primarily shown as a curator and explainer of emerging AI workflows: recapping other builders’ systems, demonstrating agent-native operating models, and sharing practical examples of how AI tools can be used for marketing, product creation, automation, and company operations.

For AI Product Managers, Greg Isenberg matters because his examples consistently sit at the intersection of product strategy and hands-on execution. His mentions cover agent-based company workflows, plugin distribution strategy, workflow decomposition, creative-service automation, and the use of coding and multimodal models to ship tangible outputs. He is especially relevant as a signal source for how AI-native teams are packaging workflows into repeatable systems rather than treating AI as a one-off productivity boost.

Key Developments

  • 2026-08-22: Greg Isenberg highlighted Billy Howell’s Grok Bot-based local newsletter operation, describing a multi-agent setup for research, sales, publishing, and execution, along with a staged four-week process for building and stabilizing agent teams.
  • 2026-09-17: Greg Isenberg covered Instinct as an iMessage- and WhatsApp-based assistant for real-world tasks like bookings, travel paperwork, and account creation, emphasizing connected workspaces and credential vaults.
  • 2026-09-20: Greg Isenberg featured Jev as a structured-output classifier that can make probability-based decisions quickly and cheaply, including a cited example of categorizing 1,700 emails for 18 cents.
  • 2026-09-25: Greg Isenberg shared Studio Operator, a semi-autonomous AI-native creative-service workflow built with Astra and the Higgsfield API, showing how briefs can be routed across specialized models with QA, repair loops, and human approval gates.
  • 2026-10-01: Greg Isenberg argued that building a ChatGPT plugin was an attractive risk/reward opportunity, advising builders to turn recurring workflows into plugins, ship multiple variants, and double down on whichever gains traction.
  • 2026-10-02: Greg Isenberg presented a workflow-rebuild masterclass focused on interviews, systems-of-record mining, documentation review, and sorting work into delete, plain code, agent, or human decision buckets across tools like Salesforce, NetSuite, and Slack.
  • 2026-10-17: Greg Isenberg used Gemini 4 Argon to build several commercially oriented prototypes, including an interactive holding-company site, a writing skill package, a Shopify 3D-product customizer, and a commercial-cleaning quote app.
  • 2026-11-05: Greg Isenberg described an agent-based company workflow spanning ideation, research, design, development, testing, bug fixing, and analytics for a distributed team of 50+ people across 12 countries, with agents reviewing funnels daily.
  • 2026-11-10: Greg Isenberg recapped Cody Schneider’s AI marketing workflows in Graph, where Airbyte syncs business data into ClickHouse for agent reads and ad APIs handle write operations, enabling automated ad research and UGC generation.
  • 2026-11-13: Greg Isenberg recapped Ras Mic’s Grok Bot tutorial, framing Grok Bot as a context-specific personal-agent orchestrator for engineering, design, content, finance, and shopping; the example included a Pluto build workflow using a PDF plan, feedback, and Claude Code with Ultra Code and Opus 5.5 to produce five working pull requests.

Relevance to AI PMs

1. Workflow decomposition and system design: Greg Isenberg’s examples repeatedly show how to break business operations into agent-friendly components. AI PMs can use this lens to map work into categories like automation candidates, human-in-the-loop checkpoints, and model-routed tasks.

2. Distribution thinking for AI products: His ChatGPT plugin commentary is relevant to PMs thinking about discoverability, packaging, and user intent. The practical takeaway is to convert repeated user jobs into narrowly scoped product surfaces and test multiple variants quickly.

3. Operating model patterns for AI-native teams: Across marketing, creative services, software building, and company operations, Greg Isenberg’s examples illustrate recurring patterns: specialized agents, shared context, approval gates, QA loops, and data-layer integration. These are useful reference architectures for PMs designing AI-assisted products or internal systems.

Related

  • Grok Bot: One of the most direct connections; Greg Isenberg recapped multiple Grok Bot workflows, including Ras Mic’s context-specific personal-agent setup and Billy Howell’s newsletter operation.
  • Ras Mic: Featured in Greg Isenberg’s November 13 recap as the demonstrator behind the Grok Bot workflow involving Pluto.
  • Pluto: Appears in the Grok Bot tutorial recap as the project used to demonstrate long-running coding-agent execution and pull-request generation.
  • Claude Code / Claude Opus / Sonnet-family tools: Connected through the coding workflow Greg Isenberg recapped, where these models were used in software execution.
  • Gemini 4 Argon: Linked to Greg Isenberg’s October 17 examples of building interactive and commercial AI-generated products.
  • Salesforce, NetSuite, Slack: Referenced in his workflow-rebuild masterclass as systems of record and execution environments for deploying AI agents.
  • Astra and Higgsfield API: Related through the Studio Operator creative-service workflow that Greg Isenberg highlighted.
  • Airbyte and ClickHouse: Connected via the AI marketing workflow recap, where they formed the data backbone for agent-readable business context.
  • ChatGPT / plugins: Relevant because Greg Isenberg explicitly argued for plugin-building as a strategic product opportunity.

Frequently asked questions

What is Greg Isenberg?

Creator and commentator who recaps a Grok Bot tutorial. He is the presenter of the workflow example involving Ras Mic and Pluto.

What should AI product managers know about Greg Isenberg?

Greg Isenberg is presented as a creator and commentator who explains practical AI-agent workflows across product, marketing, and operations. He recapped Ras Mic’s Grok Bot tutorial, including a Pluto workflow that used Claude Code and Opus-class models to generate five working pull requests. His examples are useful to AI PMs because they emphasize workflow decomposition, agent orchestration, human approval gates, and data-layer integration.

Newsletter Mentions (53)

2026-11-13
“Greg Isenberg recaps Ras Mic’s demonstration of Grok Bot as a context-specific personal-agent orchestrator for engineering, design, content, finance, and shopping.”

#19 ▶️ Use Grok Bot Better Than 99% of People (Full Course) Greg Isenberg Greg Isenberg recaps Ras Mic’s demonstration of Grok Bot as a context-specific personal-agent orchestrator for engineering, design, content, finance, and shopping. For Pluto, Ras Mic supplied a PDF build plan and feedback before using Claude Code with Ultra Code and Opus 5.5 in a run that lasted hours and produced five working pull requests for testers.

2026-11-10
“AI Agents are too good at marketing now Greg Isenberg Greg Isenberg recapped Cody Schneider’s AI marketing workflows in Graph, where Airbyte syncs advertising, analytics, CRM, payment, and other data into ClickHouse for agent reads, while Facebook and Google ad APIs handle write operations.”

▶️ AI Agents are too good at marketing now Greg Isenberg Greg Isenberg recapped Cody Schneider’s AI marketing workflows in Graph, where Airbyte syncs advertising, analytics, CRM, payment, and other data into ClickHouse for agent reads, while Facebook and Google ad APIs handle write operations. The `/static ads` workflow researches a brand and proposes five concepts, while `/UGC` combines a FAL voice clone, Seedance’s initial 480p video, ffmpeg, and Mirage Tesseract at a projected $4.75 per ad versus roughly $300–$500 for a human workflow.

2026-11-05
“Greg Isenberg shared an agent-based company workflow spanning ideation, research, design, development, testing, bug fixes, and analytics for his team of 50+ people across 12 countries.”

#12 in Greg Isenberg shared an agent-based company workflow spanning ideation, research, design, development, testing, bug fixes, and analytics for his team of 50+ people across 12 countries. He says agents review funnels every morning, while humans focus on creative feedback, relationships, and correcting agent mistakes.

2026-10-17
“Greg Isenberg used Gemini 4 Argon to create an interactive holding-company website, a personal writing skill package, a Shopify 3D-product customizer that exports print-ready STL files, and a commercial-cleaning quote app.”

#9 ▶️ Make cool things with AI that people buy (Gemini 4 Argon) Greg Isenberg Greg Isenberg used Gemini 4 Argon to create an interactive holding-company website, a personal writing skill package, a Shopify 3D-product customizer that exports print-ready STL files, and a commercial-cleaning quote app.

2026-10-02
“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%.

2026-10-01
“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.

2026-09-25
“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.

2026-09-20
“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.

2026-09-17
“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.

2026-08-22
“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.

Related

Anthropiccompany

AI company that publishes Claude models and safety guidance.

OpenAIcompany

The AI company referenced in relation to research on chain-of-thought. It is relevant as the source of the research being discussed.

Claude Codetool

A coding assistant used for execution and implementation work in the tutorial referenced by Peter Yang. It is presented as part of a workflow paired with different models for different tasks.

Claudetool

Anthropic’s AI assistant used in the newsletter for coding and knowledge-base workflows. It appears both as a general assistant and as Claude Code for household documentation tasks.

Cursortool

Cursor is an AI coding tool that introduced Team Projects in beta for shared agent context across teammates. The update emphasizes coordination, conflict handling, and team-level task unblocking.

Peter Yangperson

Creator featured in the Claude Code tutorial comparing Opus 5.5 and Fable 5.2. He is presented as the demonstrator of practical model selection for different tasks.

Codextool

An AI coding tool used to build Mural and referenced as a model for fast-moving product workflows. It is also mentioned as an environment where Garry Tan runs evals.

ChatGPTtool

A conversational AI tool referenced as part of a project-only-memory pattern for handling sensitive information. The newsletter uses it as an example of a siloed memory setup for medical records.

MCPconcept

A protocol for connecting AI systems with tools and external servers. The newsletter highlights bidirectional MCP support between YouSpot and AI harnesses.

OpenClawtool

A partner company listed in the Sign in with ChatGPT launch set. The newsletter provides no additional context beyond the integration mention.

Google AI Studiotool

Google’s AI builder environment where Gemini Decisions API was announced. Relevant to PMs as a place to prototype and operationalize Gemini-based workflows.

Perplexity Computertool

Perplexity’s agentic computer product that can interact with local apps and browser tasks. In this newsletter it gains Chrome control through a new extension and is used for model access rollout plans.

Claude Coworktool

A Claude-based work environment referenced as one of the hosts for Anthropic’s knowledge-work plugins. Relevant for teams building structured workflows around Claude.

Slacktool

A workplace messaging platform referenced as a target surface for generative UI in conversational agents.

Stripecompany

A payments company referenced for internal agent use and operational safeguards around agentic workflows.

AI agentsconcept

Autonomous or semi-autonomous software assistants that can be configured, automated, and secured with tools and integrations. The newsletter discusses memory, safety, and Home Assistant automation patterns around agents.

Ampcompany

An AI agent that can now be assigned issues in Linear and respond within an Agent Session. It appears in the Amp sidebar and is designed for workflow-based task handling.

Notiontool

Notion is a workspace tool commonly used as a knowledge base for teams. Here it is used as a connected data source for an internal command overview.

OpenAI Codextool

OpenAI’s coding tool used here to build an XP-based family system. It demonstrates productizable agent workflows applied to personal productivity and behavior design.

GPT-5.6tool

A frontier model release referenced as improving price-performance for developers. It is discussed as being available in Kiro for more cost-effective application development.

Opus 4.6tool

A Claude model version praised for personality and writing style. The newsletter contrasts it with Opus 5 as more concise and friend-like.

Hermestool

A product or integration layer that now includes Perplexity Search. The newsletter only mentions it as the destination where Perplexity Search is embedded.

Fabletool

An AI tool used in Every’s copy-editing benchmark to create an agent from historical edits. Relevant to AI PMs for agent evaluation and workflow automation.

Claude Designtool

A Claude feature for collaborative design editing, now available on every plan.

Grok Bottool

A context-specific personal-agent orchestrator demonstrated for tasks across engineering, design, content, finance, and shopping. It is presented as a practical automation layer for personal workflows.

Ollamatool

A local and cloud-capable platform for running and managing open models. It now supports macOS speech streaming and new decision models, which is useful for PMs exploring local inference, speech, and workflow automation.

Alibabacompany

Alibaba is the organization behind the Qwen model ecosystem referenced in the newsletter. It appears in connection with preview access for Qwen4-Max and related tools.

Fable 5tool

A benchmark or model used as a comparison point for Devin's GPT-6 Astra performance. It is mentioned only as a reference for code quality/cost comparison.

Dan Shipperperson

Founder associated with Every Inc., cited for building a copyediting skill from historical edits. His work illustrates how teams can turn repeated editorial behavior into reusable agent skills.

Cloudflarecompany

A company cited as an evaluator of Le Chonk in the cybersecurity context. Its mention suggests external validation of the model’s security relevance.

Jevtool

A system for handling many agent steps as typed questions with calibrated probabilities. It is positioned as a harness component for inexpensive yes/no decisions.

Remotiontool

A tool for generating video graphics and programmatic video content. Here it is used within a Codex-powered workflow to create branded overlays.

Codeextool

A coding and research tool used here for optimizing order execution latency. Relevant to PMs as part of an AI-assisted quantitative workflow.

Hermes Agenttool

A self-improving AI agent from Nous Research with desktop and CLI apps, reusable skills, automation, and multi-model support. It matters for PMs exploring cross-channel agent workflows and integrations.

GPT-5.3-Codextool

OpenAI’s coding-focused model/release highlighted for benchmark performance, steerability, and speed improvements. The newsletter frames it as a strong coding agent option with multiple benchmark scores.

Sonnet-4.6tool

A Claude model used in the newsletter's example to run Python code and analyze a floor plan. It is discussed as part of an agentic workflow inside Claude Cowork.

Salesforcecompany

A CRM platform referenced as the enterprise system Ampersand can connect agents to through configured mappings and authentication flows.

Moritz Krembperson

Creator featured in a walkthrough optimizing OpenClaw with Claude desktop and related automation techniques.

Claude Opustool

Anthropic’s Claude model used locally in Paperclip’s agent orchestration demo. It is used for task execution, company simulation, and coding workflows.

ideabrowser.comtool

A niche-discovery tool used for identifying submarkets and startup opportunities. In this newsletter it is used to uncover niche communities for AI-powered SaaS validation.

Nebulatool

A Slack-inspired AI agent platform for autonomous workflows. It lets each channel host an agent that writes code, calls APIs, and automates tasks across multiple services.

Furqan Rydhanperson

A founder demonstrating the Nebula AI agent platform. The newsletter credits him with the product demo and workflow details.

DALL·E 3tool

OpenAI's image generation model, used here as the power source for ChatGPT Images 2.0. It is relevant to AI PMs as a core capability underlying productized image workflows.

Stay updated on Greg Isenberg

Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.

Subscribe Free