Who does the thinking

A house separates remembering from judging. Remembering is deterministic code and always available. Judging needs a language model, and the model is yours.

Two kinds of work

Semantic search uses a small embedding model that ships inside every house. It is part of the kernel and not something you supply.

Borrowed mode: how every house runs today

You do the judging, on whatever model you already run. The house never calls a model and needs no API key. This is how a house works today, at every size.

What that means in practice:

• Everything in the kernel works without you doing anything.
• Every judgment is an act of yours, made with the author and modeller skills: you read a document and assert its topic; you compare two identities with describe and decide to merge_into or to assert_separate; you write a digest as a document and attach it with adopt_digest.
• The house helps you see what there is to do: list_conjectures is the list of recorded open questions, find_missing lists things that lack something, digest_coverage lists documents without a valid digest, coverage tells how deep the files were read.

The list of open work

For outlining a document and assigning it to topics, the house does the rest of the work around your judgment: list_work says what is open, take_work hands you a task with its context, the house's own prompt and the answer form, and submit_work checks your verdict with the house's guards and applies it. overview carries the count. See the-list-of-open-work.

Recipes: the prompts of the house, for the rest

For four judgments you do not have to invent the way. A recipe gives you the route the house software itself runs: the skills that fetch the context, the prompt (adapted from the one that ran in production on a German corpus), the answer form, the checks, and the skills that apply the verdict. There are recipes for assigning documents to topics, resolving names into identities, merging name forms, and summarising a document. The house checks nothing while you follow one; you run the checks. Start at working-by-recipe.

What borrowed mode does not give you:

• Nothing is judged while you are away. A document that arrives is stored, indexed and searchable at once, and stays unclassified until an agent visits.
• Large one-off jobs (thousands of judgments over a big corpus) run against the limits of your own plan and take correspondingly long.
• The quality of a judgment is the quality of your model.

If your environment has scheduled tasks, a scheduled visit gives a house a rhythm.

What is planned

A model for the house. Your own local model, your own API key, or a model service operated by core.blue can be attached to a house, which then works through the same list by itself, immediately. See plugging-in-a-model (planned). It changes when a judgment happens, not whether a house can be used: every size of house is meant to run in borrowed mode alone, and overview says under mode which mode a house is in.

What a house cannot do in any mode

• OCR, transcription and image description do not exist yet.
• Agents living inside the house (an assistant, topic stewards, a planner with a memory and a voice of their own) exist in Atlantis and are not offered by core.blue yet. The house's skills mention helpers and speakers; those belong to that part.

Go deeper

• Working by recipe
• The list of open work
• Plugging in a model
• Sizes and volumes
• What does not exist yet