GenAI PMPeter Yang
A product-focused creator who demonstrates AI builds and critiques product UX/packaging. In this issue he showcases Tabi and discusses simplifying product surfaces.
Key Highlights
- Peter Yang is known for hands-on AI product demos, workflow automations, and critiques of product UX and packaging.
- He demonstrated Tabi, a Japanese AI language coach built in about three hours and deployed in roughly five minutes.
- He showed how to automate 90% of a 15-step content workflow using ChatGPT skills, MCP tools, and human review.
- He has argued that AI still cannot build strong products end-to-end without humans defining requirements and checking work.
- He also spotlighted analytics and consumer-agent examples that tie AI performance to real outcomes like retention and cost savings.
At a glance
- Role
- Creator / product builder
Overview
Peter Yang is a product-focused creator and educator who regularly demonstrates practical AI builds, shares workflow automations, and critiques product UX and packaging choices. Across newsletter mentions, he appears as a hands-on operator who tests tools in real contexts—from building a phone-friendly Japanese tutor in a few hours to automating content operations and evaluating consumer-facing agents on cost savings and usability.
For AI Product Managers, Peter Yang matters because his work sits at the intersection of product thinking, fast prototyping, and operational AI adoption. His examples consistently emphasize shipping speed, human review, measurable outcomes, simplified product surfaces, and the limits of fully autonomous software creation. That makes his body of work especially useful for PMs deciding what AI can realistically automate, how to package AI products clearly, and where human judgment still creates the most value.
Key Developments
- 2026-09-07: Peter Yang highlighted Brilliant’s AI tutor Cooji and Sue Khim’s approach to learning design: the tutor guides learners without giving away answers, while humans define lesson structure and AI executes through reusable interactive primitives.
- 2026-09-08: He shared a 24-minute tutorial on building four games with GPT-6 Astra, Blender, and Godot, showing an applied, build-first approach to AI-assisted creation.
- 2026-09-08: He also shared four product principles attributed to Sue Khim, including “Never tell the learner the answer,” and noted their broader usefulness beyond product design.
- 2026-09-12: Yang expressed skepticism about “software factories,” arguing that AI still cannot improve products or build features end-to-end without humans defining requirements, verifying outputs, and checking assumptions.
- 2026-09-13: He shared a Grok Bot prompt he said helped recover about $500 in unclaimed money by searching official state databases using a person’s name and prior cities.
- 2026-09-17: Yang described how he automated 90% of a 15-step podcast-content workflow using ChatGPT skills, Riverside MCP, Linear, Figma MCP, browser use, and Typefully, saving at least five hours per week while keeping manual review in the loop.
- 2026-09-20: He showcased Meta’s Muse personal agent using real bill-negotiation examples, including reducing his AT&T bill from roughly $200 to $160 per month and identifying a lower-rate Xfinity Comcast option.
- 2026-09-21: Yang recapped a conversation about the ChatGPT Finances team shipping 47 things in seven days, emphasizing small releases, speed, and safeguards that protect user experience and security.
- 2026-09-25: He shared Amplitude’s Agent Analytics, highlighting how linking agent traces and evaluations to downstream user actions can reveal goal completion, failure patterns, and KPI impact.
- 2026-10-04: Yang shared a free recording of a live session attended by 100+ people on building an AI system that proactively takes work off a user’s plate; the mention also notes his paid newsletter, AI course, tool credits, and private Slack community.
- 2026-10-06: He demonstrated Tabi, a phone-friendly Japanese AI language coach built in six steps using Gemini Live APIs, Nano Banana, Google Antigravity, Claude Code, and Vercel. The app teaches travel phrases, supports role-play, took about three hours to build, and roughly five minutes to deploy.
Relevance to AI PMs
1. A practical model for rapid AI prototyping: Yang’s Tabi demo and game-building tutorials show how PMs can validate product concepts quickly with modern model APIs, coding agents, and lightweight deployment stacks. The takeaway is not just speed, but how to scope a useful v1 around a narrow job to be done.
2. A strong example of workflow automation with human oversight: His podcast-content system is a useful blueprint for PMs operationalizing AI internally. It demonstrates how to map manual steps, turn them into modular skills, connect them with tools like MCP integrations, and preserve human review at the end.
3. Grounded product judgment about AI limits and UX simplification: Yang’s skepticism of “software factories” is relevant to PMs deciding where autonomous agents can be trusted. His body of work also reinforces the importance of simplifying product surfaces and packaging AI in ways users can understand, verify, and benefit from immediately.
Related
- Tabi: A Japanese AI language coach Peter Yang demonstrated as a fast, phone-friendly AI product build.
- Gemini Live APIs / Google Antigravity / Vercel / Claude Code: Core parts of the stack used in his Tabi demo, illustrating how modern AI products can be assembled quickly.
- ChatGPT / skills / Riverside MCP / Figma MCP / Linear / Typefully: Tools and systems he used in his automated content workflow, relevant for PMs building internal AI operations.
- Meta Muse: Consumer agent example Yang evaluated through real savings on telecom and internet bills.
- Amplitude Agent Analytics: Analytics framework he shared for connecting agent behavior to business and retention outcomes.
- Sue Khim / Brilliant / Cooji: Adjacent voices and products tied to Yang’s interest in product principles, guided learning UX, and structured AI experiences.
- OpenAI / ChatGPT Finances team: Connected through his discussion of high-velocity product shipping with safeguards.
- Grok Bot: Referenced in his example of using AI agents for practical consumer tasks like recovering unclaimed funds.
Frequently asked questions
What is Peter Yang?
A product-focused creator who demonstrates AI builds and critiques product UX/packaging. In this issue he showcases Tabi and discusses simplifying product surfaces.
What should AI product managers know about Peter Yang?
Peter Yang is known for hands-on AI product demos, workflow automations, and critiques of product UX and packaging. He demonstrated Tabi, a Japanese AI language coach built in about three hours and deployed in roughly five minutes. He showed how to automate 90% of a 15-step content workflow using ChatGPT skills, MCP tools, and human review.
Newsletter Mentions (115)
“Peter Yang demonstrated Tabi, a phone-friendly Japanese AI language coach built in six steps using Gemini Live APIs, Nano Banana, Google Antigravity, Claude Code, and Vercel.”
#6 ▶️ Build an AI Language Tutor You Can Talk To (6 Steps) Peter Yang Peter Yang demonstrated Tabi, a phone-friendly Japanese AI language coach built in six steps using Gemini Live APIs, Nano Banana, Google Antigravity, Claude Code, and Vercel. Its 10 lessons teach 10 travel phrases each before role-play, and the app took about three hours to build and about five minutes to deploy on Vercel.
“Peter Yang shared a free recording of his live session—attended by 100+ people—on building an AI system to proactively take work off your plate.”
GenAI PM Daily - Perplexity Computer now generates interactive 3D learning visualizations October 04, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 12 insights for PM Builders from X and LinkedIn. Perplexity Computer now generates interactive 3D learning visualizations #11 𝕏 Peter Yang shared a free recording of his live session—attended by 100+ people—on building an AI system to proactively take work off your plate. His paid newsletter includes a self-paced AI course with 25+ lessons that is designed to be kept up to date as AI changes, plus $600+ in AI tool credits and an invitation to his private Slack community.
“in Peter Yang shared Amplitude’s Agent Analytics, which connects agent traces and evaluations with subsequent user actions to reveal goals, failures, and KPI effects.”
#12 in Peter Yang shared Amplitude’s Agent Analytics, which connects agent traces and evaluations with subsequent user actions to reveal goals, failures, and KPI effects. The Economist reached 96.9% task success and reduced weekly task failures by 84%; across 20K+ Amplitude users, a positive first agent experience was associated with 3× higher retention.
“in Peter Yang recapped a conversation in which Ethan checked the ChatGPT Finances team’s activity live and said it had shipped 47 things in the last seven days.”
in Peter Yang recapped a conversation in which Ethan checked the ChatGPT Finances team’s activity live and said it had shipped 47 things in the last seven days. The team breaks bigger features into smaller pieces and aims to build quickly while using testing and checks to protect user experience integrity and security.
“Meta’s Muse personal agent reduced Peter Yang’s AT&T phone bill from about $200 to about $160 per month by switching payment to a Bank of America checking account, and it called Xfinity Comcast to identify a lower internet-rate option.”
#6 ▶️ Meta’s Muse AI Agent Saved Me $800+ a Year on My Bills (10 Real Use Cases) Peter Yang Meta’s Muse personal agent reduced Peter Yang’s AT&T phone bill from about $200 to about $160 per month by switching payment to a Bank of America checking account, and it called Xfinity Comcast to identify a lower internet-rate option. Muse logged into AT&T through its browser after Peter Yang stored his username and password securely; changing payment from a credit card to a bank account produced a discount of about $10 per line per month across four lines—$40 monthly or about $480 annually.
“Peter Yang uses ChatGPT skills, Riverside MCP, Linear, Figma MCP, browser use, and Typefully to automate 90% of a 15-step podcast-content workflow, saving at least five hours per week while manually reviewing and editing outputs.”
#14 ▶️ How I Automated 90% of My Content Workflow (With ChatGPT) Peter Yang Peter Yang uses ChatGPT skills, Riverside MCP, Linear, Figma MCP, browser use, and Typefully to automate 90% of a 15-step podcast-content workflow, saving at least five hours per week while manually reviewing and editing outputs. The workflow has three phases: map every manual step, build AI skills for each step, and connect the skills end-to-end; Peter Yang created podcast prep, podcast edit, and podcast production skills, with podcast production routing to thumbnail/title, show-notes, newsletter-post, social-post, and clip skills.
“In Peter Yang shared a prompt that he said Grok Bot used to help him recover approximately $500 in unclaimed money by searching official state databases using his full name and past cities.”
#10 in Peter Yang shared a prompt that he said Grok Bot used to help him recover approximately $500 in unclaimed money by searching official state databases using his full name and past cities. The prompt requests each result’s type, amount, and who owes it, and Yang said it could also be tried with other agents.
“in Peter Yang expressed skepticism about “software factories,” arguing that—beyond verification and testing—AI cannot improve products or build features end-to-end without human involvement.”
#12 in Peter Yang expressed skepticism about “software factories,” arguing that—beyond verification and testing—AI cannot improve products or build features end-to-end without human involvement. He noted that one wrong assumption can waste an overnight agent run and asked for examples built without humans defining requirements or checking the work. #13 𝕏 Thariq commented that pass/fail scores alone are insufficient to interpret evaluations, as many benchmark failures he sees stem from overly strict hidden tests.
“#6 𝕏 Peter Yang shared a 24-minute tutorial on building four games using GPT-6 Astra, Blender, and Godot.”
#6 𝕏 Peter Yang shared a 24-minute tutorial on building four games using GPT-6 Astra, Blender, and Godot. #9 𝕏 Peter Yang shared “4 product principles” attributed to @suekhim, including “Never tell the learner the answer,” and said they’re also useful as parenting advice.
“AI Makes Cheating Easy. Here’s How It Can Make Kids Smarter Instead | Sue Khim Peter Yang Brilliant’s AI tutor Cooji guides students through difficult problems without supplying answers or direct explanations, while human learning designers define lesson sequences and AI implements them using reusable interactive primitives.”
#7 ▶️ AI Makes Cheating Easy. Here’s How It Can Make Kids Smarter Instead | Sue Khim Peter Yang Brilliant’s AI tutor Cooji guides students through difficult problems without supplying answers or direct explanations, while human learning designers define lesson sequences and AI implements them using reusable interactive primitives. In a recorded fractions session, a student needed to shade 5/12 of a shape; Cooji guided the student to recognize that five shaded pieces could have different values rather than explaining the answer directly. Brilliant uses a library of modular, composable primitives with APIs that let models create, annotate, highlight, and ask subquestions in interactive lessons; the structure provides deterministic grounding instead of having the model generate an entire interactive experience from scratch.
Related
An AI company mentioned for releasing a report on model behaviors and for internal tool use in later context. Relevant for PMs tracking safety reporting and frontier model operations.
Anthropic’s coding agent/environment used here to control physical tools in a long-running home experiment.
OpenAI is an AI company building foundation models and consumer products like ChatGPT. In this newsletter it is discussed in connection with GPT-6, Dots, ChatGPT for Teens, and College Planner.
Anthropic’s AI assistant, referenced here through new dashboard, motion, docs, slides, and design capabilities.
An AI coding tool shown here supporting follow-up questions and a /visualize command that generates a new chart in-chat.
An OpenAI coding model/tool used here as part of coding harnesses turned into reinforcement-learning environments.
A prominent AI blogger and commentator referenced in connection with an article on token reselling and fraud. He is cited as the source of the newsletter item discussing the marketplace and API-key abuse.
An AI company associated with Devin, mentioned for allowing users to connect personal ChatGPT plans to the agent. Relevant to AI PMs thinking about consumption-based product design.
A cloud platform used to deploy the Tabi app quickly. It is also referenced in the safer API design discussion.
A product and startup commentator credited with recapping an OpenAI DevDay incident. The mention centers on operational reliability and live-demo pressure.
OpenAI’s chat product, referenced here as the user-owned subscription plan connected to Devin. For PMs, this highlights quota-linked integration patterns.
Google AI product lead / developer relations figure frequently associated with Google’s model launches and ecosystem updates.
A creator and product thinker sharing AI usage tracking and product documentation workflows. Relevant to PMs focused on measurement and prompt-to-spec workflows.
A partner company listed in the Sign in with ChatGPT launch set. The newsletter provides no additional context beyond the integration mention.
Entrepreneur and AI workflow commentator mentioned presenting a masterclass on deploying AI agents. The newsletter frames him around workflow redesign and automation economics.
MCP is a protocol for connecting AI systems to external tools and data sources. Here it is described as the way Granola can use captured context through internal tooling.
Google’s AI assistant/model family used here as an enterprise work agent that can handle knowledge, media, coding, and sub-agent orchestration tasks.
Alibaba's AI model and agent ecosystem brand. In this newsletter it announced new audio models, agent capabilities, and benchmark releases.
CEO of OpenAI, referenced here sharing OpenAI's mathematics progress page. He is a central figure in AI product strategy and model launches.
A major AI company involved here in developing the open Personal Agent Protocol with Sierra. The mention is relevant to interoperability and agent permissions.
A person mentioned sharing an ad-monitoring and SEO automation setup using Grok and a bot account. Relevant as an example of AI-assisted growth workflows.
Google’s AI application builder and workflow environment. Here it is noted for GitHub repository import and bidirectional sync, which matters for AI product workflows and developer experience.
A Claude-based workflow or assistant used for structured journaling and planning. In this newsletter it transforms captured notes into organized outputs and follow-up actions.
Slack is a workplace messaging platform often connected to AI agents and internal tools. In this context it is one of the data sources powering an incident-command overview.
Autonomous or semi-autonomous workflows that perform tasks, coordinate tools, and execute actions on behalf of users.
A model used as an automated judge in Claire Vo’s benchmark. It contributes 30% of the scoring alongside her manual evaluation.
A project management and issue-tracking tool used in agentic software workflows. In this newsletter it is used by Warp’s Wilson to open issues from Slack requests.
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.
A collaborative design platform referenced as an example of broad enterprise SaaS that may remain resilient in the AI era. It is contrasted with niche single-purpose products.
xAI’s assistant, referenced as a bot used for competitor ad monitoring and growth automation. Useful for PMs tracking applied agentic marketing workflows.
A product or integration layer that now includes Perplexity Search. The newsletter only mentions it as the destination where Perplexity Search is embedded.
A Claude model version praised for personality and writing style. The newsletter contrasts it with Opus 5 as more concise and friend-like.
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.
AI-assisted building pattern where products or workflows are created iteratively with models rather than purely through manual coding.
A creator and commentator on Claude Code workflows and extensions. He shared a modding framework and free templates/prompts for experimenting with Claude Code mods.
A Claude model variant being updated with stronger biology safeguards to reduce false positives while still routing dual-use biology requests to higher-safety fallback behavior. Relevant for PMs considering safety tradeoffs and product-surface-specific policy tuning.
A Claude feature for collaborative design editing, now available on every plan.
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.
A fintech company described here as using multiple AI agents across product discovery, UX fixes, reviews, and testing. This is relevant to PMs as an example of AI-enabled product development at scale.
A Claude model version referenced as part of a prompt-comparison analysis. It serves as one endpoint for examining changes in Anthropic’s system prompt evolution.
Cowork is an Anthropic product mentioned as part of Claude’s product surface. The newsletter references it only as one of the products covered by Anthropic’s containment approach.
Cloud Code appears to be a coding agent or coding workflow used to generate launch videos from websites. The newsletter describes it as working with Fable 5 and HyperFrames.
Anthropic’s managed-agent offering referenced as a more reliable migration target than a prior side project setup. Relevant for PMs evaluating agent orchestration products.
OpenAI’s workplace-focused ChatGPT offering. It is relevant to AI PMs as a deployment surface for frontier models in enterprise and team workflows.
An agent or bot referenced as a benchmark comparison for OpenAI's Dots. It is mentioned as being roughly on par, suggesting a comparable personal agent experience.
Google’s cloud platform, used here for custom plugins and service-account based integrations.
The parent company whose products are hosting early access to Qwen3.8-Max-Preview. It appears as the platform distributor for the model preview.
A Model Context Protocol integration for Figma used to connect bots and automate design flows.
A Claude model variant referenced in Anthropic's cybersecurity evaluation report. It is one of the models involved in the incidents described.
An AI-powered development platform used to build and ship software quickly. The newsletter cites it as the tool used to build GenAIPI in three days.
An agent framework or approach that uses summarization middleware to manage context while preserving work history. It emphasizes offloading tool results and older messages into external storage.
Google's suite of productivity applications used for email, documents, spreadsheets, and calendaring. It is mentioned here as the environment Cursor agents can now operate across.
An AI design/build tool that uses six agents to craft apps in real time. It is presented as part of the emerging agentic design workflow.
Moonshot is an AI company releasing large open models and weights. The newsletter notes its Kimi K3 release and new commercial licensing restrictions.
A plugin/pattern used to manage build loops and goal-driven agent workflows. Here it is tied to Codex Desktop and the LFG loop for prototype completion.
A production tool used with Adobe Premiere in an AI-assisted ad creative workflow. It helps automate or accelerate post-production for marketing content.
A company whose strategy docs, specs, queries, Slack threads, and transcripts were used to build a Claude Code knowledge base. The context suggests an internal knowledge-management use case.
OpenAI's chat model optimized for more engaging conversation, better intent understanding, and improved handling of complex constraints. It is described as rolling out to paid users first and then free users.
Figma’s co-founder and CEO, cited for an insight about AI making first drafts cheap. The newsletter uses him to frame how generative tools compress the cost of early design exploration.
A Gemini model tier referenced as part of Google AI Pro access. For AI PMs, it is relevant as a model included in subscription packaging and quota-based distribution.
A Chinese AI company building and releasing foundation models. Here it is identified as the company behind GLM 5.3 Flash and the unmasking of AUX Alpha.
The video platform mentioned for its new Inspiration feature, which is criticized here as AI-generated slop.
Social platform referenced as a source of examples, discussion, and scraping/monetization concerns. In this newsletter it is part of the agent workflow stack and content source.
A company focused on AI development workflows and agent harnesses. It is mentioned for its Missions framework and multi-step orchestration.
Google's Gemini model family referenced in guidance for integrating it into Android apps.
A frontier model in Cursor with high usage limits, positioned for autonomous agent workflows.
A model released on Windsurf with a limited-time launch discount. It is relevant as another model option available to developers.
A communications platform used here as a runtime/connection endpoint for personal AI demos. It is mentioned alongside WebRTC in a quick setup workflow.
Builder and creator referenced for an OpenClaw-based business walkthrough. The newsletter highlights his use of AI agents, automation, and multi-tool integrations to launch a product quickly.
A creator who demonstrates the Compound Engineering plugin and Claude Code workflow patterns.
A travel and lodging platform increasingly associated with AI-driven experiences and services. The newsletter mentions it in the context of a new hire from Meta.
Programmable interfaces that let AI agents and software systems access services and complete tasks. The newsletter positions APIs as one of the means for agents to act on behalf of users.
OpenAI leader and product/engineering voice associated here with confirming Codex’s unification with the main model. The newsletter cites him via Simon Willison’s note.
Anthropic's long-running task product for collaborative agent workflows. The newsletter highlights it as an example of how Anthropic is changing design and shipping faster.
A lightweight skills-based pattern for packaging agent capabilities in small context-efficient files.
Head of design at Claude, cited in the newsletter for discussing how AI tools are changing the design process. She is associated with Anthropic's design workflow.
Stay updated on Peter Yang
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free