Every agent on the same version of the business

1. 01 · Ingest

   Scope what you ingest

   Every document lands with a groupName: the sets it belongs to. Those sets are what retrieval intersects later, so the structure you choose here is the precision you get there.

   context.add

   import AlchemystAI from "@alchemystai/sdk";const client = new AlchemystAI(); // reads ALCHEMYST_AI_API_KEYawait client.v1.context.add({  context_type: "resource",  scope: "internal",  source: "org-glossary",  documents: [{    content: "Active customer: an account with a paid invoice in the last 90 days. Owner: Finance. Trials are not active customers.",  }],  metadata: {    fileName: "definition-active-customer.md",    groupName: ["org", "definitions"],   // the sets this belongs to  },});

2. 02 · Write

   Let the owner define the term

   Consensus is not a longer prompt. It is a definition with an owner, stored once and read by every agent in the organisation.

   context.add

   await client.v1.context.add({  context_type: "instruction",  scope: "internal",  source: "org-glossary",  documents: [{    content: "Revenue means ARR as reported to the board. Bookings and pipeline are separate metrics.",    owner: "finance",  }],  metadata: {    fileName: "definition-revenue.md",    groupName: ["org", "definitions"],  },});

3. 03 · Search

   Search before acting

   Search intersects the scopes, subtracts superseded and duplicate content, and ranks what survives. Only that reaches the model, and the whole decision is recorded as a Context Trace.

   context.search

   const { contexts } = await client.v1.context.search({  query: "How many active customers did we add in Q3?",  scope: "internal",  similarity_threshold: 0.8,  minimum_similarity_threshold: 0.5,  metadata: { groupName: ["org", "definitions"] },   // ∩ narrow scope});// − superseded, deduplicated → ranked → into the window// Every search is recorded as a Context Trace.const reply = await llm.respond(message, { context: contexts });

npm install @alchemystai/sdk or pip install alchemystai, both ship the same client. Full reference in the docs.