Content agents that write in the voice you approved

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: "brand",  documents: [{    content: "Voice: plain, specific, confident. Never use \"synergy\" or \"revolutionary\". Lead with the customer's problem.",  }],  metadata: {    fileName: "voice-guidelines-2026.md",    groupName: ["marketing", "brand"],   // the sets this belongs to  },});

2. 02 · Write

   Write the editor's correction back

   Every edit is a lesson. Store it in the brand scope, and the next draft starts from what the editor already fixed.

   context.memory.add

   await client.v1.context.memory.add({  sessionId: "brand_editorial",  contents: [{    role: "user",    content: "Rejected: headline was a rhetorical question. House style is statements, not questions.",  }],  metadata: { groupName: ["marketing", "brand", "feedback"] },});

3. 03 · Search

   Search before drafting

   Search intersects the scopes, subtracts superseded and duplicate content, and ranks what survives.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: "Draft the October product newsletter",  scope: "internal",  similarity_threshold: 0.8,  minimum_similarity_threshold: 0.5,  metadata: { groupName: ["marketing", "brand"] },   // ∩ narrow scope});// − superseded, deduplicated → ranked → into the window// Every search is recorded as a Context Trace.const reply = await llm.respond(message, { context: contexts });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.