Support agents that remember the last time

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: "help-center",  documents: [{    content: "Annual plans are refundable pro rata within 30 days of renewal. After 30 days, credit is issued instead.",  }],  metadata: {    fileName: "refunds-annual-plans.md",    groupName: ["support", "billing", "refunds"],   // the sets this belongs to  },});

2. 02 · Write

   Write the resolution, not the transcript

   The transcript is already in the helpdesk. What is missing is the outcome, stored against the customer so the next agent retrieves it as experience.

   context.memory.add

   await client.v1.context.memory.add({  sessionId: "acme:ticket-44812",  contents: [    { role: "user", content: "Renewal card keeps getting declined." },    {      role: "assistant",      content: "Resolved: 3DS step timing out on their gateway. Retry window raised to 40s.",    },  ],  metadata: { groupName: ["support", "acme", "resolved"] },});

3. 03 · Search

   Search before replying

   Search intersects the scopes, subtracts superseded and duplicate content, and ranks what survives.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: "Customer says their renewal payment failed again",  scope: "internal",  similarity_threshold: 0.8,  minimum_similarity_threshold: 0.5,  metadata: { groupName: ["support", "acme"] },   // ∩ narrow scope});// − superseded, deduplicated → ranked → into the window// Every search is recorded as a Context Trace.const reply = await llm.respond(message, { context: contexts });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.