{"id":50686531,"url":"https://github.com/agentoptics/jensen-way","last_synced_at":"2026-06-08T23:30:31.403Z","repository":{"id":352152863,"uuid":"1214071532","full_name":"agentoptics/jensen-way","owner":"agentoptics","description":"Physics-of-reality decision framework for AI coding assistants. Build/Pivot/Kill verdicts backed by evidence, extended from Jensen Huang's framing of Physical AI.","archived":false,"fork":false,"pushed_at":"2026-04-18T05:26:09.000Z","size":24,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-18T06:30:37.537Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/agentoptics.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-18T04:51:59.000Z","updated_at":"2026-04-18T05:41:01.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/agentoptics/jensen-way","commit_stats":null,"previous_names":["agentoptics/jensen-way"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/agentoptics/jensen-way","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentoptics%2Fjensen-way","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentoptics%2Fjensen-way/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentoptics%2Fjensen-way/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentoptics%2Fjensen-way/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agentoptics","download_url":"https://codeload.github.com/agentoptics/jensen-way/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentoptics%2Fjensen-way/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34085321,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-08T23:30:29.840Z","updated_at":"2026-06-08T23:30:31.398Z","avatar_url":"https://github.com/agentoptics.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Jensen Way\n\nA physics-of-reality decision framework for AI coding assistants. Tests whether a product, feature, or spec **obeys reality** before you commit engineering time — and produces a defensible **Build / Pivot / Kill** verdict backed by evidence.\n\n\u003e \"The next wave requires us to understand things like the laws of physics — friction, inertia, cause and effect. The fact that I tip that thing over, it's going to fall. When I set the bottle down, it's not going to go through the table. All of these common sense physical reasoning abilities that children have, that our pets have — most AIs don't have.\"\n\u003e\n\u003e — Jensen Huang, [Hill \u0026 Valley Forum 2025](https://www.youtube.com/watch?v=nkhrEnuZi20\u0026t=485s), interviewed by Jacob Helberg, May 3, 2025\n\nJensen was describing **Physical AI** — the next wave after perception, generative, and agentic AI. We noticed the same observation applies to most product plans: they operate in a frictionless vacuum where users adopt because you ship, teams align because you scheduled a meeting, and systems scale because the architecture diagram says so.\n\nJensen Way ports that insight to product decisions. A child shouldn't need equations to follow your causal chain — if they can't, the physics are probably against you.\n\n## Install\n\n```bash\n/plugin marketplace add agentoptics/jensen-way\n```\n\nOr drop the single-file skill into your project:\n\n```bash\nmkdir -p .claude/skills/jensen-way\ncurl -o .claude/skills/jensen-way/SKILL.md \\\n  https://raw.githubusercontent.com/agentoptics/jensen-way/main/skills/jensen-way/SKILL.md\n```\n\nThen:\n\n```\n/jensen-way Should we add real-time collaboration to our docs product?\n```\n\n## What you get back\n\n1. A framed decision (what, why, time horizon)\n2. A **causal chain** from \"we build it\" to \"it matters\" — with weak links marked\n3. Evidence-backed evaluation against **6 laws of reality**\n4. A **friction budget** — force available vs. friction total\n5. A verdict: **BUILD / PIVOT / KILL** with the single biggest risk named\n\nSee [EXAMPLES.md](EXAMPLES.md) for two worked evaluations — one PIVOT, one KILL.\n\n## The 6 laws\n\n| # | Law | The toddler version |\n|---|-----|---------------------|\n| 1 | **Gravity of demand** | \"Do people actually want this, or do you just wish they did?\" |\n| 2 | **Friction of adoption** | \"Is this solving something that hurts, or just something slightly annoying?\" |\n| 3 | **Competitive gravity** | \"If someone bigger takes your toy, can you get it back?\" |\n| 4 | **Hard constraints** (the table test) | \"What's the thing that absolutely cannot happen no matter how hard you try?\" |\n| 5 | **Organizational inertia** (Conway's Law) | \"Do the people who need to work together actually talk to each other?\" |\n| 6 | **Entropy \u0026 economics** | \"If you stop paying attention to this, does it break? Is it worth the effort?\" |\n\nEach law scores **Aligned / Fighting / Broken**.\n\n- **BUILD** — no Broken, at most 2 Fighting with named mitigations, friction budget positive\n- **PIVOT** — 1-2 Broken that dissolve if scope / approach / timeline changes\n- **KILL** — 3+ Broken, OR Broken on Demand Gravity, OR friction budget deeply negative\n\n## Example prompts\n\n```\n/jensen-way Should we add AI-powered search to our documentation platform?\n```\n\n```\n/jensen-way We're deciding between building our own auth vs. using Auth0. Evaluate both.\n```\n\n```\n/jensen-way Our PM wants to ship a mobile app in 6 weeks. 3-person team, no mobile experience. We all have a 100$ budget per month for AI assistance. Feasible?\n```\n\n```\n/jensen-way Fork an open-source project and maintain our own version, or contribute upstream?\n```\n\n## Philosophy\n\nMost product failures aren't caused by bad engineering — they're caused by **ignoring physics**:\n\n- Building something nobody wants (ignoring demand gravity)\n- Underestimating how hard it is to change user behavior (ignoring friction)\n- Assuming teams will coordinate perfectly (ignoring organizational inertia)\n- Planning for the happy path only (ignoring entropy)\n- Not knowing what can't be done (ignoring hard constraints)\n\nA child wouldn't make these mistakes. They have an intuitive understanding of cause and effect, friction, and hard limits. Jensen Way brings that intuition to product decisions — with evidence attached.\n\n## Works with any AI assistant\n\nThe framework is in a single Markdown file: [skills/jensen-way/SKILL.md](skills/jensen-way/SKILL.md). Model-agnostic. Copy it into your system prompt, paste it into a conversation, or reference it as a project file. It works with any assistant that can follow a structured workflow.\n\n## Contributing\n\nIssues and PRs welcome. If you've used Jensen Way to make a decision (build *or* kill), open an issue — real-world runs make the framework better.\n\n## License\n\nMIT\n\n## Credits\n\nBuilt by [Agent Optics](https://github.com/agentoptics). The physics framing is drawn directly from Jensen Huang's Hill \u0026 Valley Forum 2025 remarks on Physical AI. The extension from Physical AI to product decisions is ours.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentoptics%2Fjensen-way","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagentoptics%2Fjensen-way","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentoptics%2Fjensen-way/lists"}