{"node":{"id":"a16ad01a-d635-4100-b814-81e96c89ebd8","handle":"a16a","type":"note","authorName":"Vincent Yeung","intent":"recipe","title":"Intermediate: patterns that combine the basics","aiSummary":"Third layer. First four pages set up the tools: the standing file, skills, agents, and skills and agents together. Then patterns, where the power comes from, expanding what it can do, and when the answer is wrong. Last link opens Autonomous.","content":"Nothing here is a new idea. Each page takes two or more of the basics and puts them together. The first four set up the tools that make everything after them work: the standing file, skills, agents, and knowing which to reach for. The rest are patterns and capabilities. Read one at a time, and only when it is worth it for this person.\n\n- The standing file: CLAUDE.md\n- Skills: context you invoke\n- Agents: a fresh window with one job\n- Skills and agents together\n- Patterns: routines the author uses, each built from the basics\n- Where the power comes from: tools and information, and what gets shared\n- Expanding what it can do: adding a tool, with the browser as the worked example\n- When the answer is wrong\n- Jev: a model that picks from answers you write, fast and the same way every time\n\nWhen the person is running these without thinking about them, the last link opens Autonomous.","capturedAt":"2026-09-14T04:18:54.636Z","createdAt":"2026-09-14T04:18:54.636Z","updatedAt":"2026-10-21T02:05:15.925Z","spanId":null,"contributor":null,"audiences":[{"kind":"public","createdAt":"2026-09-14T04:18:54.636Z"}],"fingerprint":"4372e7ceaaf766dbaafe9ab4d2be082846334f92263f64deb6e5dcf53dd07e7a","revisionNo":"8","structureHash":"48aa24ee48f23a3328ee7262c9533a5b44fc6513488ca43144dbc3f903106bea","page":"https://lattris.com/by/b/memories/a16ad01a-d635-4100-b814-81e96c89ebd8"},"links":[{"direction":"out","verb":"references","reason":"only if the person is in a code tool and has added no tools of their own, or is doing work by hand that a tool could reach","hash":"a8094d3a8dafe88bad8a39bfaec5cbc330340b6801cc393c516ea04d33ae6ced","node":{"id":"0ff994cf-3066-44fe-9f99-fbd09b1f4ca5","handle":"0ff9","type":"note","title":"Expanding what it can do","aiSummary":"Tools are the part of the AI you can add to, and MCP is the usual way to plug one in. The worked example is the browser: install the Claude in Chrome extension, then /chrome in Claude Code to connect, check, reconnect, and set which sites it may touch. It drives the real browser already signed in as you, and stops at logins and CAPTCHAs. It needs a direct Anthropic plan. Every connected tool takes a bit more context (/mcp lists them), so a few is plenty and the browser is one of them. Everything read through a door goes to the provider.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/0ff994cf-3066-44fe-9f99-fbd09b1f4ca5?links=1","fingerprint":"c562ddcd3c4abe21122354ef65b71ffc14035689cf1793ce4bd2aaf1da2c958b","revisionNo":"4","structureHash":"cce4f1be2a1277d6b0aa4f088abac294d424e94265e79ea4365b85440774e1ca","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/0ff994cf-3066-44fe-9f99-fbd09b1f4ca5"}},{"direction":"out","verb":"references","reason":"if the person needs it: skills. In a chat app, say what they would have","hash":"d84d7f51dcaf51339883fc8fa680ad0789d3704b289fdc8304912397f93d05e8","node":{"id":"32ead000-931d-4234-bfe0-295dae630b79","handle":"32ea","type":"note","title":"Skills: context you invoke","aiSummary":"A skill is context loaded when needed, not on every start. Repeating yourself is the signal to look, but only workflows worth capturing once become skills. The AI writes it; you don't need to read it. The loop is use, then improve by pointing at what came out wrong. Reader's AI names a workflow the person has walked more than once and offers to write it.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/32ead000-931d-4234-bfe0-295dae630b79?links=1","fingerprint":"80a5e3c63ae8ab94f2e118c22e1299a5eeb807f28c8286c609f9fbae67ad2636","revisionNo":"6","structureHash":"5c5e2ed719444b3b919712627859a08d8498f3b19c963d26365479c40326c9af","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/32ead000-931d-4234-bfe0-295dae630b79"}},{"direction":"out","verb":"references","reason":"only if the person's situation matches a pattern: a full window that must carry on, a reset that needs re-alignment, or a long conversation that needs an accurate summary","hash":"8c22eeb88990c6928c03fd424ad344f53b1e2c4eba38ecdd175119b2cd7c9563","node":{"id":"331896d2-2e9d-46b1-b56c-048a18ee23eb","handle":"3318","type":"note","title":"Patterns: a library","aiSummary":"Index of the author's patterns, one page each, built from the basics. Any pattern can be turned into a skill by asking the AI. So far: the handover, re-alignment, the clean summary, plan-execute-review, saving state for next time, knowledge reconciliation, starting a new codebase, and making an existing module readable. Grows as pages are added.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/331896d2-2e9d-46b1-b56c-048a18ee23eb?links=1","fingerprint":"fdb88831a4949e6d2796f6f2ec65f612903ec02e487ecea76821973013ef633c","revisionNo":"9","structureHash":"ebf9a8041d4dce367db54d851720a324d11c8ecd3a5256931024e47d01638c7f","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/331896d2-2e9d-46b1-b56c-048a18ee23eb"}},{"direction":"out","verb":"references","reason":"if the person needs it: skills and agents together","hash":"01af638584301aa322bdc47411855670b5573c974301ee784aad4c035734f404","node":{"id":"3cf4cecb-4a84-4bce-91db-552e1ed3434b","handle":"3cf4","type":"note","title":"Skills and agents together","aiSummary":"Both start as a written brief with a job. A skill runs in your window, with your model. An agent runs in a separate window with its own model and tools and inherits your CLAUDE.md. An agent can be given a skill. Choose a skill when the job belongs in your conversation, an agent when it would pollute the window.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/3cf4cecb-4a84-4bce-91db-552e1ed3434b?links=1","fingerprint":"7118cc58c994e684995c1a5e3d8ddb5038d4e97dc253ec27bb2067df8fc86178","revisionNo":"3","structureHash":"962b806b9042727134aa7ad664d9908d9e1869063f37fcd4f5583b0a7923948b","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/3cf4cecb-4a84-4bce-91db-552e1ed3434b"}},{"direction":"out","verb":"references","reason":"if the person needs it: agents. In a chat app, say what they would have","hash":"20eafce9a07a5ae1a5d0b2b4921057b5568ace31a8d37ce22e0a4a49e66c6f22","node":{"id":"6d91aac5-50c8-442f-81d1-61eae279f8e7","handle":"6d91","type":"note","title":"Agents: a fresh window with one job","aiSummary":"An agent is another context window started from yours, with a job. Fresh window, sharper on its one task. An identity matters because a model leans toward the most common material it was trained on; naming the role points it at the right part. You choose the model per agent; a named agent definition can pin model, effort, and tools. Ask the AI to create them. Reader's AI names something in this conversation that would have been sharper handed off.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/6d91aac5-50c8-442f-81d1-61eae279f8e7?links=1","fingerprint":"d8b5d6f970b9058232df060cc09d9795657ac6607726e92f72e500ae612ce7ec","revisionNo":"3","structureHash":"5c3cf84edd4f06a82109b4ba0280871ce96e2a3ece87be7d6a9cf73127280e0d","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/6d91aac5-50c8-442f-81d1-61eae279f8e7"}},{"direction":"out","verb":"references","reason":"only if the person has had an answer come out wrong and wants to know why, or blames the AI for making things up","hash":"6af578d934aef3180539bcc20c5a4dd937740276a72a0b4c55ac1a6b4cbdcb3b","node":{"id":"a2f152ad-62c0-4cdb-bed9-8026dbb2f98b","handle":"a2f1","type":"note","title":"When the answer is wrong","aiSummary":"An AI does not make things up; a wrong answer is what the model, the provider's instructions, and the context produced together. The model part is partly yours: a better model, and effort tuned to the job, since maximum effort on a simple task can overthink. No model is right every time and that is improving on its own. The rest is context understanding and management as a habit, from which patterns emerge. Reader's AI names anything wrong in this conversation and says what it had and lacked at the time.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/a2f152ad-62c0-4cdb-bed9-8026dbb2f98b?links=1","fingerprint":"236271c3ee931bbe6811e9f497e4565be62c01edffdf191e20a7d5821af07280","revisionNo":"4","structureHash":"72b5ecc32ec293ddf2ba8c2762f4274ae17d2c6358907197e4fbc27c7588ac9d","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/a2f152ad-62c0-4cdb-bed9-8026dbb2f98b"}},{"direction":"out","verb":"references","reason":"only if the person is fetching and pasting by hand from services the AI could reach itself, or has never thought about what the provider keeps of what it reads","hash":"8f7c3cd43b01672db556b61990fcb5688f28a184f8c570bc4ee33db3f31cb510","node":{"id":"a4eb5d62-b86f-47e4-96d6-c13d59b98acb","handle":"a4eb","type":"note","title":"Where the power comes from","aiSummary":"The model is one part; tools and information are the rest. Doors: files, APIs, MCP, connectors and plugins. Connecting sends nothing; reading through a door sends what was read to the provider, where it is kept. Author consciously chooses what level of information goes in, accepting the risk that someone else may one day see it. Reader's AI lists open doors, what it has read through them, and what was pasted that could have come through one.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/a4eb5d62-b86f-47e4-96d6-c13d59b98acb?links=1","fingerprint":"20d4d5d3476bd0e05f0918b1eb4866ed34fd35812cdbbadf9b34bbf6d9cd7514","revisionNo":"4","structureHash":"0694b97ccad9315b7e53e145493d8f26419d2740c440bf45439379bc069d6105","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/a4eb5d62-b86f-47e4-96d6-c13d59b98acb"}},{"direction":"out","verb":"references","reason":"if the person needs it: the standing file. In a chat app, say what they would have","hash":"ad1a228f73abe07dff9d4cfeb40f5f821302b1094f9ee6fde5e4f501ef8cb4ed","node":{"id":"ba943bfe-3db5-4e90-bb3f-f92c4b1cc722","handle":"ba94","type":"note","title":"The standing file: CLAUDE.md","aiSummary":"CLAUDE.md is read on every start: global, per project, per subfolder, stacked. North star: the least context relevant to every new conversation. Anything only needed sometimes becomes a pointer to another file, or a subfolder's own CLAUDE.md. The AI writes and maintains it. Reader's AI reveals which standing files it was loaded with and what could become a pointer.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/ba943bfe-3db5-4e90-bb3f-f92c4b1cc722?links=1","fingerprint":"fc253ce6fbc05d8884dd96b3f362e78eb7116f3ad99dc74fb73ac68d81befbb7","revisionNo":"3","structureHash":"db8af19ca34b2952e75dde574237e8a676c94282c6d22e10b2c46e83dfc16b5f","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/ba943bfe-3db5-4e90-bb3f-f92c4b1cc722"}},{"direction":"out","verb":"references","reason":"only if you need a model to pick from a list you define, fast, cheap and the same way every time: a decision model","hash":"45a80d01f2ec06e5306d75eb8b486ac751378f2792aac11d0906f2db9f2269f1","node":{"id":"f0f5decc-32a9-49de-ad3d-0ea1871263fc","handle":"f0f5","type":"note","title":"Jev picks from answers you write: when to use it and how to word the questions","aiSummary":"Jev, TypeSafe's decision model, picks from answers you write and gives each one a probability. Use it when the same judgment is needed many times and you can write every answer down first. Read the spread of probabilities to find the unsure answers. Word each answer tightly, and ask first whether the question applies, because Jev picks a wrong answer when the right one is missing. A person still decides what matters, because some picks are wrong and Jev does not learn from its mistakes.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/f0f5decc-32a9-49de-ad3d-0ea1871263fc?links=1","fingerprint":"43a30188c8bed6cb34e1c429c68b09aff611314c63650658756f1563927cdb67","revisionNo":"13","structureHash":"0df22d1c0fbb9aa7e1ba50bd4a7eab4f3b9a833a10eec51ab1aea1289522cef3","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/f0f5decc-32a9-49de-ad3d-0ea1871263fc"}},{"direction":"in","verb":"references","reason":"only if the person already has the basics and wants the useful patterns: skip straight here","hash":"a30c3356d96d09523ad5cadd1f08916b0fbf438ca7b2128fdedc3f57a37aa88d","node":{"id":"83c7ec41-ebf8-4f74-82c6-291757bf6244","handle":"83c7","type":"note","title":"Getting real use out of AI — start here","aiSummary":"Root of a public tree about using AI well, read by a person's own AI on their behalf. On first read the AI settles two things it can see: which kind of tool this is (chat vs code) and which model is answering. Then five layers open in order: First, Giving AI more reach, Basics, Intermediate, Autonomous. Rule on every page: say where the person stands before saying what the author does, then act on the gap they choose.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/83c7ec41-ebf8-4f74-82c6-291757bf6244?links=1","fingerprint":"067f8f2d8331bbe851855e7ad3a628ed7ca7b96222377717fd6c976053fb3ae6","revisionNo":"21","structureHash":"39a9479f09bbeeb466e71cd46760ff5c03b7ec4ab33986ea243f2431157365bf","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/83c7ec41-ebf8-4f74-82c6-291757bf6244"}},{"direction":"in","verb":"references","reason":"when the person has what they need from Basics: the tools and the patterns","hash":"225ad4bd429dce468dcea52357d684b64ce28cd761668508320403616ab97784","node":{"id":"df42dc57-c832-4e7b-97cd-d647af5597a7","handle":"df42","type":"note","title":"Basics: what is actually going on","aiSummary":"Second layer. Eight single ideas in order: which model, the hidden instructions and tools, where it runs, what to ask for and what to enforce, what happens if you lose it, what the provider keeps, the context window, and memory. Output is decided by the model and the context, nothing else. Last link opens Intermediate.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/df42dc57-c832-4e7b-97cd-d647af5597a7?links=1","fingerprint":"564692020f1a0f8e71bd68a233680e3039c9f3a01c62c9403da75b8f3cac3054","revisionNo":"11","structureHash":"d7a3b70af32e55e0a7e130f2524bc47b86fce60a940d6b23b3e2ae6adc02473c","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/df42dc57-c832-4e7b-97cd-d647af5597a7"}}],"dictionary":{"lattris":"A personal knowledge base — how a person captures what they know as linked blocks they own and control. To understand how this knowledge base works: https://lattris.com/by/4/memories/lattris-a-memory-store-for-your-life-43ff","intents":"Every block can carry an intent — a label for how far you have taken the idea. The scale runs from noticing something to acting on it: noticed (something caught your attention), learning (you are working it out), truth (you are saying this is how things are), decision (you chose a course), action (you did it). Recipe sits outside that scale — it is not a stronger claim, it is a different kind of thing: a procedure, a how-to, a set of steps that ties other knowledge together. Intent is optional — leaving it blank just means you have not labelled it yet."},"instructions_to_ai":"This is a recipe from a personal knowledge base. Read it and apply it to what the person you're talking to is working on. Follow the linked blocks to explore further related topics if it might be useful to the user; open each at its page address. Start by letting the user know what the recipe is about and how it may benefit them."}