{
  "schemaVersion": "1",
  "revision": "22ce5d34dbcb5a78",
  "id": "factory-vision-and-automation-discussion",
  "slug": "vision-and-automation-discussion",
  "title": "Product vision and earned automation — discussion and evidence",
  "summary": "Detailed companion accounts of concepts, questions, demonstrations, exercises, and unresolved observations.",
  "category": "Team practice",
  "tags": [
    "vision-and-automation",
    "discussion",
    "evidence"
  ],
  "sources": [
    {
      "label": "Published evidence reference",
      "url": "https://proud-anchor-53zn.here.now/resource-manifest.json"
    },
    {
      "label": "Recorded discussion",
      "url": "https://proud-anchor-53zn.here.now/watch.html"
    }
  ],
  "sourceUnits": [
    "resource-manifest.json#videoEvidence.concepts[187]",
    "resource-manifest.json#videoEvidence.concepts[188]",
    "resource-manifest.json#videoEvidence.concepts[189]",
    "resource-manifest.json#videoEvidence.concepts[190]",
    "resource-manifest.json#videoEvidence.concepts[191]",
    "resource-manifest.json#videoEvidence.concepts[192]",
    "resource-manifest.json#videoEvidence.concepts[193]",
    "resource-manifest.json#videoEvidence.concepts[194]",
    "resource-manifest.json#videoEvidence.concepts[195]",
    "resource-manifest.json#videoEvidence.concepts[196]",
    "resource-manifest.json#videoEvidence.concepts[197]",
    "resource-manifest.json#videoEvidence.concepts[198]",
    "resource-manifest.json#videoEvidence.concepts[199]",
    "resource-manifest.json#videoEvidence.questionsAndAnswers[63]",
    "resource-manifest.json#videoEvidence.questionsAndAnswers[64]",
    "resource-manifest.json#videoEvidence.questionsAndAnswers[65]",
    "resource-manifest.json#videoEvidence.questionsAndAnswers[66]",
    "resource-manifest.json#videoEvidence.questionsAndAnswers[67]",
    "resource-manifest.json#videoEvidence.exercises[18]",
    "resource-manifest.json#videoEvidence.timeline[905]",
    "resource-manifest.json#videoEvidence.timeline[908]",
    "resource-manifest.json#videoEvidence.timeline[909]",
    "resource-manifest.json#videoEvidence.timeline[911]",
    "resource-manifest.json#videoEvidence.timeline[912]",
    "resource-manifest.json#videoEvidence.timeline[913]",
    "resource-manifest.json#videoEvidence.timeline[914]",
    "resource-manifest.json#videoEvidence.timeline[915]",
    "resource-manifest.json#videoEvidence.timeline[916]",
    "resource-manifest.json#videoEvidence.timeline[917]",
    "resource-manifest.json#videoEvidence.timeline[920]",
    "resource-manifest.json#videoEvidence.timeline[922]",
    "resource-manifest.json#videoEvidence.timeline[923]",
    "resource-manifest.json#videoEvidence.timeline[924]",
    "resource-manifest.json#videoEvidence.timeline[925]",
    "resource-manifest.json#videoEvidence.timeline[926]",
    "resource-manifest.json#videoEvidence.timeline[927]",
    "resource-manifest.json#videoEvidence.timeline[928]",
    "resource-manifest.json#videoEvidence.timeline[929]",
    "resource-manifest.json#videoEvidence.timeline[930]",
    "resource-manifest.json#videoEvidence.timeline[931]",
    "resource-manifest.json#videoEvidence.timeline[932]",
    "resource-manifest.json#videoEvidence.timeline[933]",
    "resource-manifest.json#videoEvidence.timeline[937]",
    "resource-manifest.json#videoEvidence.timeline[938]",
    "resource-manifest.json#videoEvidence.timeline[939]",
    "resource-manifest.json#videoEvidence.timeline[940]",
    "resource-manifest.json#videoEvidence.timeline[941]",
    "resource-manifest.json#videoEvidence.timeline[945]",
    "resource-manifest.json#videoEvidence.timeline[948]",
    "resource-manifest.json#videoEvidence.timeline[949]",
    "resource-manifest.json#videoEvidence.timeline[950]",
    "resource-manifest.json#videoEvidence.timeline[951]",
    "resource-manifest.json#videoEvidence.uncertainties[61]",
    "resource-manifest.json#videoEvidence.uncertainties[64]",
    "resource-manifest.json#videoEvidence.demos[113]",
    "resource-manifest.json#videoEvidence.demos[114]",
    "resource-manifest.json#videoEvidence.demos[115]",
    "resource-manifest.json#videoEvidence.demos[116]"
  ],
  "collection": "factory",
  "categoryId": "team-practice",
  "wordCount": 1605,
  "url": "/topics/factory-vision-and-automation-discussion/",
  "markdownUrl": "/markdown/factory-vision-and-automation-discussion.md?raw=1&v=22ce5d34dbcb5a78",
  "jsonUrl": "/api/v1/documents/factory-vision-and-automation-discussion.json",
  "headings": [
    {
      "id": "concepts-and-distinctions",
      "text": "Concepts and distinctions",
      "level": 2
    },
    {
      "id": "notebooklm-artifact-generation",
      "text": "NotebookLM Artifact Generation",
      "level": 3
    },
    {
      "id": "real-time-voice-brainstorming-vs-static-audio-overviews",
      "text": "Real-Time Voice Brainstorming vs. Static Audio Overviews",
      "level": 3
    },
    {
      "id": "multi-agent-terminal-orchestration",
      "text": "Multi-Agent Terminal Orchestration",
      "level": 3
    },
    {
      "id": "mermaid-diagrams-for-agent-context",
      "text": "Mermaid Diagrams for Agent Context",
      "level": 3
    },
    {
      "id": "documentation-drift",
      "text": "Documentation Drift",
      "level": 3
    },
    {
      "id": "sliding-scale-prompt-alignment",
      "text": "Sliding Scale Prompt Alignment",
      "level": 3
    },
    {
      "id": "google-ai-subscription-tiers",
      "text": "Google AI Subscription Tiers",
      "level": 3
    },
    {
      "id": "agent-primitive-task-overhead",
      "text": "Agent Primitive Task Overhead",
      "level": 3
    },
    {
      "id": "documentation-drift-2",
      "text": "Documentation Drift",
      "level": 3
    },
    {
      "id": "vision-md-specification-concept",
      "text": "vision.md Specification Concept",
      "level": 3
    },
    {
      "id": "vision-document-vision-md",
      "text": "Vision Document (VISION.md)",
      "level": 3
    },
    {
      "id": "agentic-automation",
      "text": "Agentic Automation",
      "level": 3
    },
    {
      "id": "developer-voice-dictation-workflows",
      "text": "Developer Voice Dictation Workflows",
      "level": 3
    },
    {
      "id": "questions-and-answer-status",
      "text": "Questions and answer status",
      "level": 2
    },
    {
      "id": "can-a-single-mermaid-graph-effectively-serve-both-machine-context-injection-and-human-readable-documentation-or-should-we-treat-element-facing-context-architecture-entirely-separate-from-human-facing-notes",
      "text": "Can a single mermaid graph effectively serve both machine context injection and human readable documentation, or should we treat element-facing context architecture entirely separate from human-facing notes?",
      "level": 3
    },
    {
      "id": "can-a-single-mermaid-graph-effectively-serve-both-machine-context-injection-and-human-readable-documentation-or-should-we-treat-element-facing-context-architecture-entirely-separate-from-human-facing-notes-2",
      "text": "Can a single mermaid graph effectively serve both machine context injection and human readable documentation, or should we treat element-facing context architecture entirely separate from human-facing notes.",
      "level": 3
    },
    {
      "id": "does-that-require-ultra-subscription-do-you-find-value-in-the-ultra-subscription",
      "text": "Does that require ultra subscription? Do you find value in the ultra subscription?",
      "level": 3
    },
    {
      "id": "does-video-analysis-require-an-ultra-subscription-and-is-ultra-worth-it",
      "text": "Does video analysis require an Ultra subscription, and is Ultra worth it?",
      "level": 3
    },
    {
      "id": "what-s-the-name-of-the-document-again-the-one-for-documentation",
      "text": "What’s the name of the document again? The one for documentation",
      "level": 3
    },
    {
      "id": "exercises",
      "text": "Exercises",
      "level": 2
    },
    {
      "id": "observed-actions-and-statements",
      "text": "Observed actions and statements",
      "level": 2
    },
    {
      "id": "unresolved-notebooklm-mcp-integration-with-gemini-cli-anti-gravity",
      "text": "Unresolved: NotebookLM MCP integration with Gemini CLI ('anti-gravity')",
      "level": 3
    },
    {
      "id": "unresolved-exact-bash-script-loop-generated-inside-claude-code-scratchpad",
      "text": "Unresolved: Exact bash script loop generated inside Claude Code scratchpad",
      "level": 3
    },
    {
      "id": "demonstration-detail-05-26-03",
      "text": "Demonstration detail: 05:26:03",
      "level": 3
    },
    {
      "id": "demonstration-detail-05-33-13",
      "text": "Demonstration detail: 05:33:13",
      "level": 3
    },
    {
      "id": "demonstration-detail-05-33-19",
      "text": "Demonstration detail: 05:33:19",
      "level": 3
    },
    {
      "id": "demonstration-detail-05-39-29",
      "text": "Demonstration detail: 05:39:29",
      "level": 3
    }
  ],
  "markdown": "# Product vision and earned automation — discussion and evidence\n\nDetailed companion accounts of concepts, questions, demonstrations, exercises, and unresolved observations.\n\nThese are the companion’s accounts of the recorded discussion. Model capabilities, subscription rules, prices, version-specific flags, and predictions are contextual claims, not current guidance. An observed action is not proof that the attempted result succeeded. Distinct answers and uncertainties remain separate.\n\n## Concepts and distinctions\n\n### NotebookLM Artifact Generation\n\nIngesting workshop transcripts and notes into Google NotebookLM to auto-generate slide decks, summaries, mind maps, and audio podcasts.\n\n### Real-Time Voice Brainstorming vs. Static Audio Overviews\n\nComparing pre-rendered podcast summaries with interactive, real-time voice conversations (e.g. ChatGPT Voice Mode) for exploratory engineering discussions.\n\n### Multi-Agent Terminal Orchestration\n\nArchitecting AI workflows where a manager pane coordinates specialized daemons (server log, source code, browser proof) using CLI tools like cmux.\n\n### Mermaid Diagrams for Agent Context\n\nA markdown-based structural diagramming syntax previously used to force models into structural alignments, now viewed by the presenter as a limiter.\n\n### Documentation Drift\n\nThe challenge where text documentation, wikis, or initial architectural specs become rapidly outdated due to active code iteration by AI models.\n\n### Sliding Scale Prompt Alignment\n\nA prompt design strategy enabling the developer to modulate how tightly the agent must adhere to strict refactoring bounds versus creative performance improvement.\n\n### Google AI Subscription Tiers\n\nEvaluating Google AI Pro vs Ultra tiers, including usage multipliers, storage limits, and bundled services like YouTube Premium.\n\n### Agent Primitive Task Overhead\n\nConversational agents like Gemini on Android failing at introductory examples (e.g. setting timers) when forced into complex agent execution loops.\n\n### Documentation Drift\n\nThe misalignment that occurs when documentation, wikis, or architectural diagrams lag behind actual code changes and team decisions.\n\n### vision.md Specification Concept\n\nA proposed project file (vision.md) defining high-level product goals, user experience, demographics, and values without prescribing technical restrictions for AI agents.\n\n### Vision Document (VISION.md)\n\nA high-level document defining the ultimate ideal state and objectives of a product, providing direction for AI agents regardless of tech stack changes.\n\n### Agentic Automation\n\nDelegating complex multi-step creative or research workflows (such as image simplification or GitHub repository analysis) to AI agents.\n\n### Developer Voice Dictation Workflows\n\nUsing speech-to-text dictation software (Super Whisper, WhisperFlow, Handy) to stream natural language prompts directly into CLI agent interfaces.\n\n## Questions and answer status\n\n### Can a single mermaid graph effectively serve both machine context injection and human readable documentation, or should we treat element-facing context architecture entirely separate from human-facing notes?\n\n**Status: partial.** John begins explaining that human readability and machine prompt context requirements differ in code/context projects; the full explanation continues in the next shard.\n\n### Can a single mermaid graph effectively serve both machine context injection and human readable documentation, or should we treat element-facing context architecture entirely separate from human-facing notes.\n\n**Status: answered.** John explains that keeping fixed mermaid diagrams for agents is an anti-pattern because it unnecessarily limits the agent from finding better architectural configurations.\n\n### Does that require ultra subscription? Do you find value in the ultra subscription?\n\n**Status: partial.** John is unsure of the precise distinction in value-add between Pro and Ultra subscription tiers, which leads him to perform a live search query.\n\n### Does video analysis require an Ultra subscription, and is Ultra worth it?\n\n**Status: answered.** Video analysis is available on Google AI Pro. Ultra offers higher usage limits, but Pro combined with YouTube Premium family sharing provides the primary value for his workflow.\n\n### What’s the name of the document again? The one for documentation\n\n**Status: answered.** John answers that the file is vision.md (or agents.md), as confirmed in the discussion.\n\n## Exercises\n\n- **Try:** Browse the shared NotebookLM workspace to review workshop sources and generated artifacts.\n  **Basis:** John posts link in chat at 05:26:41 and invites attendees: 'So if you want to browse this, I was able to dump in all of this text and everything in here' (05:26:40).\n\n## Observed actions and statements\n\nThese timestamped observations retain troubleshooting detail and the limits of what was visible. Commands mentioned here are observations, not vetted installation instructions; use the topic’s prepared recipes for runnable examples.\n\n- [05:27:10](https://proud-anchor-53zn.here.now/watch.html?t=19630#recording-player) — John compares NotebookLM Audio Overviews to real-time ChatGPT voice mode.\n\n- [05:28:38](https://proud-anchor-53zn.here.now/watch.html?t=19718#recording-player) — John exits slideshow view and comments on Google's strengths in notebook/video assets vs lagging coding features.\n\n- [05:29:02](https://proud-anchor-53zn.here.now/watch.html?t=19742#recording-player) — John reads a participant's question regarding single Mermaid graph context injection vs separate human notes.\n\n- [05:29:31](https://proud-anchor-53zn.here.now/watch.html?t=19771#recording-player) — John Lindquist contrasts writing documentation for agents versus writing it for human developers.\n\n- [05:29:39](https://proud-anchor-53zn.here.now/watch.html?t=19779#recording-player) — John states that he no longer advocates for Mermaid diagrams to exist beyond an initial prompt pass.\n\n- [05:30:10](https://proud-anchor-53zn.here.now/watch.html?t=19810#recording-player) — John mentions that Fable models can be smarter than the user, so strict adherence to human diagrams restricts alternative better solutions.\n\n- [05:31:06](https://proud-anchor-53zn.here.now/watch.html?t=19866#recording-player) — a participant notes agreement in chat that initial concepts, wikis, or mermaid diagrams cause documentation drift.\n\n- [05:31:06](https://proud-anchor-53zn.here.now/watch.html?t=19866#recording-player) — John states that modern AI experts consider AgentsMD and ClaudeMD to be anti-patterns because they limit instead of guardrail.\n\n- [05:31:55](https://proud-anchor-53zn.here.now/watch.html?t=19915#recording-player) — John explains his experimentation with adding a sliding scale to initial user prompts to control adherence to established patterns vs code improvement.\n\n- [05:32:51](https://proud-anchor-53zn.here.now/watch.html?t=19971#recording-player) — John receives and reads a question about whether this method requires an Ultra subscription and its value add.\n\n- [05:33:19](https://proud-anchor-53zn.here.now/watch.html?t=19999#recording-player) — Chrome browser shows Google search result AI Overview comparing Google AI Pro ($19.99/mo) and Google AI Ultra ($200-$250/mo).\n\n- [05:33:29](https://proud-anchor-53zn.here.now/watch.html?t=20009#recording-player) — John Lindquist discusses usage limits, YouTube Premium, and Google Drive storage.\n\n- [05:33:34](https://proud-anchor-53zn.here.now/watch.html?t=20014#recording-player) — John highlights text under Google AI Ultra regarding 20 TB - 30 TB Drive/Photos storage capacities.\n\n- [05:33:39](https://proud-anchor-53zn.here.now/watch.html?t=20019#recording-player) — John highlights text detailing YouTube Premium individual plan and Google Home Premium Advanced perks.\n\n- [05:33:43](https://proud-anchor-53zn.here.now/watch.html?t=20023#recording-player) — John highlights text describing 20x higher usage limits across Gemini, Project Genie, and Google Antigravity.\n\n- [05:33:58](https://proud-anchor-53zn.here.now/watch.html?t=20038#recording-player) — John states he believes video analysis is available on the Pro plan.\n\n- [05:34:07](https://proud-anchor-53zn.here.now/watch.html?t=20047#recording-player) — John explains sharing YouTube Premium across 5 different Google accounts for family members.\n\n- [05:34:32](https://proud-anchor-53zn.here.now/watch.html?t=20072#recording-player) — John states he derives the most value from video analysis in Gemini and YouTube family sharing.\n\n- [05:34:40](https://proud-anchor-53zn.here.now/watch.html?t=20080#recording-player) — John describes using Gemini on Android via side button for checking email and scheduling events.\n\n- [05:34:53](https://proud-anchor-53zn.here.now/watch.html?t=20093#recording-player) — John notes Gemini fails on simple tasks like timers because it invokes an agent workflow.\n\n- [05:35:12](https://proud-anchor-53zn.here.now/watch.html?t=20112#recording-player) — John reads audience comment regarding wikis, diagrams, agent constraints, and documentation drift.\n\n- [05:35:25](https://proud-anchor-53zn.here.now/watch.html?t=20125#recording-player) — John agrees documentation drift is an important problem in evolving projects.\n\n- [05:35:33](https://proud-anchor-53zn.here.now/watch.html?t=20133#recording-player) — John emphasizes that code is the source of truth.\n\n- [05:36:05](https://proud-anchor-53zn.here.now/watch.html?t=20165#recording-player) — John proposes placing a vision.md file in repositories to outline ideal product scenarios, target demographics, and experiences.\n\n- [05:36:34](https://proud-anchor-53zn.here.now/watch.html?t=20194#recording-player) — John highlights that vision.md should provide broad aspirational guidance rather than technical restrictions.\n\n- [05:36:55](https://proud-anchor-53zn.here.now/watch.html?t=20215#recording-player) — John explains that a vision document defines the ideal end goal of a product so agents can keep moving towards it.\n\n- [05:37:31](https://proud-anchor-53zn.here.now/watch.html?t=earlier-generation1#recording-player) — John tells a story about using Fable AI agent to convert a student roadrunner crayon drawing into a printable white graphic for elementary school t-shirts.\n\n- [05:37:39](https://proud-anchor-53zn.here.now/watch.html?t=earlier-generation9#recording-player) — a participant asks in chat: 'What’s the name of the document again?'\n\n- [05:39:15](https://proud-anchor-53zn.here.now/watch.html?t=20355#recording-player) — John answers that the file is vision.md or agents.md.\n\n- [05:39:37](https://proud-anchor-53zn.here.now/watch.html?t=20377#recording-player) — John launches Claude Code v2.1.212 using command cl3.\n\n- [05:39:49](https://proud-anchor-53zn.here.now/watch.html?t=20389#recording-player) — John uses Super Whisper voice dictation to speak prompt to Claude Code asking to search for VISION.md files using gh cli.\n\n- [05:40:04](https://proud-anchor-53zn.here.now/watch.html?t=20404#recording-player) — John discusses voice dictation tools, mentioning Super Whisper, WhisperFlow, and Handy.\n\n- [05:40:12](https://proud-anchor-53zn.here.now/watch.html?t=20412#recording-player) — Claude Code executes gh search code command to find VISION.md files on GitHub.\n\n### Unresolved: NotebookLM MCP integration with Gemini CLI ('anti-gravity')\n\nPresenter mentions this speculatively ('I think it's an MCP between Notebook and The Gemini agent? Once they get it inside of anti-gravity...').\n\n**Discriminating evidence:** Presenter conjecture on potential future features; no external verification required.\n\n### Unresolved: Exact bash script loop generated inside Claude Code scratchpad\n\nThe right edge of the terminal command text is cut off by the window boundary.\n\n**Discriminating evidence:** Recorded verified visible command prefix; left full script unextrapolated.\n\n### Demonstration detail: 05:26:03\n\n- Navigate to notebooklm.google.com\n- Open share modal and set public link access\n- Copy and post notebook URL to Zoom chat\n- Inspect Sources panel and Studio artifact section\n- Launch full-screen presentation mode for 'The Orchestrated Developer' slide deck\n- Page through 12 generated presentation slides\n\n**Tools observed:** NotebookLM, Google Chrome.\n\n**Command or prompt observations (not a verified recipe):**\n\n```text\ncmux --json tree\ncmux new-split right\ncmux read-screen\n```\n\n### Demonstration detail: 05:33:13\n\n- Opened a new Google Chrome browser tab.\n- Typed 'google pro vs ultra' into the address bar.\n\n**Tools observed:** Google Chrome Omnibox.\n\n### Demonstration detail: 05:33:19\n\n- Browsed Google Search AI Overview comparing Google AI plans.\n- Highlighted plan details on screen.\n- Opened a new tab and typed VISION.md into address bar to check search results.\n\n**Tools observed:** Google Chrome, Google Search.\n\n### Demonstration detail: 05:39:29\n\n- Switched to Ghostty terminal\n- Ran cl3 to open Claude Code CLI v2.1.212\n- Dictated prompt using Super Whisper\n- Observed Claude Code executing gh search code and gh api script\n\n**Tools observed:** Ghostty, tmux, Claude Code v2.1.212, Super Whisper, GitHub CLI.\n\n**Command or prompt observations (not a verified recipe):**\n\n```text\ncl3\nDo a gh cli search for \"VISION.md\". Please show all the variations on how people are using these files and what their purposes are.\ngh search code --filename VISION.md --limit 50 --json repository,path | jq -r '.[] | \"\\(repository.nameWithOwner)\t\\(path)\"' | sort -u\n```"
}
