GenAI PMEleanor Berger
A contributor credited for a piece on automating presentation slides with agent skills. The newsletter places them alongside Isaac Plath on an agentic slide-building workflow.
Key Highlights
- Eleanor Berger is repeatedly credited with Isaac Plath on practical AI-agent workflow topics relevant to product teams.
- Her newsletter mentions span slide automation, agent instruction reliability, shared human-agent workspaces, and orchestration-system adoption.
- The strongest signal for AI PMs is tactical guidance on when agent workflows succeed, fail, or become too complex to justify.
- Berger is specifically associated with an agentic slide-building workflow using Slidev, Nano Banana, and Agent Skills.
Eleanor Berger
Overview
Eleanor Berger is a recurring contributor featured alongside Isaac Plath in GenAI PM Daily coverage of practical AI-agent workflows, collaboration patterns, and implementation troubleshooting. Across multiple newsletter mentions, Berger is associated with applied topics such as automating presentation creation with agent skills, improving instruction-following through AGENTS.md, evaluating multi-agent orchestration systems, and understanding why agentic coding may underperform in real-world use.For AI Product Managers, Eleanor Berger matters as a signal of practitioner-oriented thinking focused less on AI hype and more on workflow design, operational trade-offs, and execution details. The pieces attributed to Berger and Plath consistently address questions PMs face when introducing agents into product, engineering, or content workflows: when orchestration is worth the complexity, how to structure shared workspaces, how to make agent instructions reliable, and how to turn agent capabilities into repeatable output such as slide decks.
Key Developments
- 2026-02-13 — Featured with Isaac Plath in “Automating Presentation Slides with Agent Skills,” demonstrating an agentic workflow for creating presentation slides using Slidev, Nano Banana, and Agent Skills.
- 2026-03-18 — Credited on “X1PM: A Shared Workspace for Humans and AI Agents,” which introduced a shared workspace model for human-agent collaboration using file-native formats such as Markdown and CSV.
- 2026-03-24 — Featured in “Everyone says agentic coding builds whole projects. Why doesn't it work for me?” highlighting common failure modes and expectation gaps in agentic coding workflows.
- 2026-03-28 — Credited on “I’ve configured instructions in AGENTS.md, but the agent isn’t following them. What should I do?” a troubleshooting-oriented piece focused on instruction loading, formatting, precedence, and validation.
- 2026-04-02 — Featured with Isaac Plath in “Should I adopt a multi-agent orchestration system like Gas Town or Claude Flow?” examining trade-offs, benefits, and fit for tools such as Gas Town and Claude Flow.
- 2026-04-02 — The multi-agent orchestration piece was also separately listed in the newsletter, reinforcing Berger’s association with decision-making frameworks for adopting orchestration systems.
Relevance to AI PMs
1. Practical workflow design for agent-powered output Berger’s credited work on automated slide creation is directly relevant to PMs building internal tooling or AI-assisted content pipelines. It shows how agent skills can be chained with tools like Slidev and media-generation components to produce structured deliverables rather than one-off chat responses.2. Operational guidance for agent reliability
The AGENTS.md troubleshooting coverage is useful for PMs responsible for system behavior, onboarding, and quality control. It points to practical levers—instruction hierarchy, file loading, formatting, and simple validation tests—that can improve whether agents actually follow intended operating rules.
3. Decision support for scaling from single agents to orchestration
Berger’s involvement in the orchestration-system discussion is especially relevant for PMs evaluating when to introduce multi-agent complexity. The topic helps teams think through whether platforms like Gas Town or Claude Flow solve a real coordination problem or merely add infrastructure overhead.
Related
- Isaac Plath — Frequent co-credit with Eleanor Berger across all listed newsletter mentions, suggesting a closely linked body of work on agent workflows and AI collaboration patterns.
- Gas Town — Referenced in the multi-agent orchestration evaluation as an example system teams may consider adopting.
- Claude Flow — Another orchestration platform discussed in relation to trade-offs and ideal use cases for multi-agent systems.
- Multi-agent orchestration systems — A core topic tied to Berger’s coverage, especially around adoption criteria and workflow complexity.
- AGENTS.md / agentsmd — Connected through the troubleshooting piece about making agent instructions stick in practice.
- Agentic coding — Linked via the discussion of why end-to-end project generation often fails for users despite common claims.
- X1PM — Related through the shared workspace concept for human and AI agent collaboration in file-native formats.
- Slidev — Part of the slide automation workflow credited to Berger.
- Nano Banana — Included in the presentation automation stack used for agentic slide creation.
- Agent Skills — A direct connection to the workflow that automated presentation building.
Newsletter Mentions (6)
“#6 📝 Eleanor Berger & Isaac Plath Should I adopt a multi-agent orchestration system like Gas Town or Claude Flow? - Examines whether teams should adopt multi-agent orchestration systems such as Gas Town or Claude Flow, weighing their benefits, trade-offs, and ideal use cases.”
#6 📝 Eleanor Berger & Isaac Plath Should I adopt a multi-agent orchestration system like Gas Town or Claude Flow? - Examines whether teams should adopt multi-agent orchestration systems such as Gas Town or Claude Flow, weighing their benefits, trade-offs, and ideal use cases. Offers guidance on when such systems are appropriate and what to consider before adopting them.
“Eleanor Berger & Isaac Plath Should I adopt a multi-agent orchestration system like Gas Town or Claude Flow? - Examines whether teams should adopt multi-agent orchestration systems such as Gas Town or Claude Flow, weighing their benefits, trade-offs, and ideal use cases.”
#6 📝 Eleanor Berger & Isaac Plath Should I adopt a multi-agent orchestration system like Gas Town or Claude Flow? - Examines whether teams should adopt multi-agent orchestration systems such as Gas Town or Claude Flow, weighing their benefits, trade-offs, and ideal use cases. Offers guidance on when such systems are appropriate and what to consider before adopting them.
“#5 📝 Eleanor Berger & Isaac Plath I’ve configured instructions in AGENTS.md, but the agent isn’t following them. What should I do? - A troubleshooting post about why an AI agent might ignore instructions stored in AGENTS.md and what to check to get the agent to follow them.”
#5 📝 Eleanor Berger & Isaac Plath I’ve configured instructions in AGENTS.md, but the agent isn’t following them. What should I do? - A troubleshooting post about why an AI agent might ignore instructions stored in AGENTS.md and what to check to get the agent to follow them. It offers practical checks such as verifying the file is loaded, confirming formatting and precedence, and testing changes with simple prompts.
“Eleanor Berger & Isaac Plath Everyone says agentic coding builds whole projects.”
#19 📝 Eleanor Berger & Isaac Plath Everyone says agentic coding builds whole projects. Why doesn't it work for me? - A featured question about why agentic coding often fails to produce complete projects for some users. The piece invites readers to explore common pitfalls and expectations around agentic workflows.
“Eleanor Berger & Isaac Plath X1PM: A Shared Workspace for Humans and AI Agents - Introduces X1PM, a shared workspace concept for human and AI agent collaboration using file-system native formats like Markdown and CSV.”
#14 📝 Eleanor Berger & Isaac Plath X1PM: A Shared Workspace for Humans and AI Agents - Introduces X1PM, a shared workspace concept for human and AI agent collaboration using file-system native formats like Markdown and CSV. Presents the idea as the latest topic on the site, inviting readers to explore workflows that integrate agents with familiar file formats.
“Eleanor Berger & Isaac Plath Automating Presentation Slides with Agent Skills - Demonstrates creating presentation slides agentically using Slidev, Nano Banana, and Agent Skills. Presents an automated workflow for building slides with agent tools.”
GenAI PM Daily February 13, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 25 insights for PM Builders, ranked by relevance from Blogs, X, YouTube, and LinkedIn. OpenAI Introduces GPT-5.3-Codex-Spark Model #1 📝 OpenAI News Introducing GPT-5.3-Codex-Spark - Announces the GPT-5.3-Codex-Spark product release, highlighting new Codex-powered capabilities for developers and product teams. The post introduces the model and its intended use cases and availability. Also covered by: @Simon Willison #2 𝕏 Demis Hassabis rolled out Gemini 3’s new “Deep Think” mode for Google AI Ultra subscribers in the Gemini App, enabling more advanced reasoning and complex problem-solving capabilities. Also covered by: @Josh Woodward , @Demis Hassabis , @Google AI, @Sundar Pichai , @Sundar Pichai #3 𝕏 Sam Altman launched GPT-5.3-Codex-Spark as a research preview for Pro today, delivering over 1,000 tokens per second with initial limitations that will be rapidly improved.
Related
A software-building pattern where AI agents generate, modify, and ship code with increasing autonomy. For PMs, it changes the economics of product development and accelerates prototyping.
A contributor credited for a piece on automating presentation slides. He is mentioned with Eleanor Berger in the context of agentic slide creation.
Reusable capabilities or task-specific skills added to AI agents to extend what they can do. Here they are mentioned as part of Claude's healthcare and life sciences expansion.
A multi-agent orchestration system referenced alongside Gas Town as an option for teams to adopt. It is presented as an orchestration approach with trade-offs and use cases.
A multi-agent orchestration system discussed as a possible adoption choice for teams. It is framed as an orchestration pattern rather than a single model.
An image-generation feature associated with Gemini in Chrome. It is presented as part of Gemini’s new multitasking and content-creation workflow.
Stay updated on Eleanor Berger
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free