Commerce agents that remember what the customer actually buys

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: "catalogue",  documents: [{    content: "Field jacket JK-2291. Sleeve runs 2cm longer than standard. Sizes S to XL. In stock.",  }],  metadata: {    fileName: "sku-JK-2291.json",    groupName: ["catalogue", "outerwear", "fw26"],   // the sets this belongs to  },});

2. 02 · Write

   Write the constraint, wherever it was said

   A constraint said once in chat should hold in email, in search and at checkout. Write it against the shopper the moment it is said.

   context.memory.add

   await client.v1.context.memory.add({  sessionId: "shopper_77120",  contents: [    {      role: "user",      content: "I returned the last two because the sleeves were short. And nothing with wool.",    },    { role: "assistant", content: "Noted: longer sleeves, no wool." },  ],  metadata: { groupName: ["commerce", "shopper_77120"] },});

3. 03 · Search

   Search before recommending

   Search intersects the scopes, subtracts superseded and duplicate content, and ranks what survives.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: "Suggest a winter jacket for me",  scope: "internal",  similarity_threshold: 0.8,  minimum_similarity_threshold: 0.5,  metadata: { groupName: ["catalogue", "outerwear", "fw26"] },   // ∩ narrow scope});// − superseded, deduplicated → ranked → into the window// Every search is recorded as a Context Trace.const reply = await llm.respond(message, { context: contexts });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.