{"node":{"id":"6d91aac5-50c8-442f-81d1-61eae279f8e7","handle":"6d91","type":"note","authorName":"Vincent Yeung","intent":"truth","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.","content":"**What to know:** an agent is just another context window, started from inside yours, with a job. That's it. People overcomplicate this. You can say \"have an agent review this file\" in the chat and one will be spun up, do the work, and hand back the result. Your window only gets the result, not everything the agent read on the way.\n\nWhy that matters comes from the context window page: a window gets worse as it fills. An agent starts empty, so it is sharper on its one job than your full window would be.\n\n**Why an identity helps.** A model is trained on a huge pile of material all packed in together, and it leans toward whatever was most common in that pile. Ask for a legal review with no more detail and it will lean toward US law, because there was more of it. Say \"you are a lawyer in Sydney reviewing this under Australian law\" and the answer changes. The same goes for \"a principal engineer\", \"an accountant for a small business\", anything. This is not a trick. It is telling the model which part of what it knows to draw on. That is why context is the whole game, and it ties back to which model you use: the model is the pile, the context is where in the pile you point it.\n\n**You choose the model.** When you start an agent you can say which model runs it. A quick, well-defined job can go to a smaller model. Judgement goes to a bigger one. This is how the plan advice on the model page actually gets used: the main window on the model you want to talk to, the offloaded work on whatever fits the job. If you define a named agent once, in a file, you can pin its model, its effort, and which tools it may use, and then call it by name.\n\n**You don't write these yourself.** Ask the AI to make them. \"Make me an agent that reviews pull requests, on Opus, with read-only access.\" It writes the file, in the right place, in the right shape. You read it, correct it, and it's done. The AI knows the format better than you do, and it has just watched what you want.\n\n**Author's practice:** an agent gets a clear scope and an identity, in a sentence or two, and nothing else it doesn't need. Anything that would pollute the main window, like reading a long transcript or a big file, goes to an agent.\n\n**Reveal on the spot:** say whether you can start agents from here. Show it: pick something in this conversation that would be better handed off, and say what the one-line brief for that agent would be, identity included.\n\n**Unlocks:** sharper work on every side task, and a main window that stays clean.","capturedAt":"2026-09-14T04:18:53.243Z","createdAt":"2026-09-14T04:18:53.244Z","updatedAt":"2026-09-15T05:13:35.831Z","spanId":null,"contributor":null,"audiences":[{"kind":"public","createdAt":"2026-09-14T04:18:53.244Z"}],"fingerprint":"d8b5d6f970b9058232df060cc09d9795657ac6607726e92f72e500ae612ce7ec","revisionNo":"3","structureHash":"5c3cf84edd4f06a82109b4ba0280871ce96e2a3ece87be7d6a9cf73127280e0d","page":"https://lattris.com/by/b/memories/6d91aac5-50c8-442f-81d1-61eae279f8e7"},"links":[{"direction":"in","verb":"references","reason":"if the person needs it: agents. In a chat app, say what they would have","hash":"20eafce9a07a5ae1a5d0b2b4921057b5568ace31a8d37ce22e0a4a49e66c6f22","node":{"id":"a16ad01a-d635-4100-b814-81e96c89ebd8","handle":"a16a","type":"note","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.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/a16ad01a-d635-4100-b814-81e96c89ebd8?links=1","fingerprint":"4372e7ceaaf766dbaafe9ab4d2be082846334f92263f64deb6e5dcf53dd07e7a","revisionNo":"8","structureHash":"48aa24ee48f23a3328ee7262c9533a5b44fc6513488ca43144dbc3f903106bea","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/a16ad01a-d635-4100-b814-81e96c89ebd8"}}],"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 knowledge from a personal knowledge base. Read it and consider how it's relevant to what the person you're talking to needs. 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 this is about and how it may be relevant to them."}