Care agents that remember the patient between visits

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: "care-guidelines",  documents: [{    content: "Post-operative knee recovery: weight-bearing as tolerated from day 2. Physiotherapy three times a week for six weeks.",  }],  metadata: {    fileName: "post-op-knee-recovery.md",    groupName: ["clinic", "ortho", "guidelines"],   // the sets this belongs to  },});

2. 02 · Write

   Write where the patient is in their plan

   The next conversation needs to know what happened in the last one. Write progress against the patient, not into a transcript nobody reads.

   context.memory.add

   // De-identified reference, never a name or record number.await client.v1.context.memory.add({  sessionId: "patient_ref_20931",  contents: [{    role: "assistant",    content: "Week 3 of physiotherapy. Reported pain 3/10, down from 6/10. Next review due in two weeks.",  }],  metadata: { groupName: ["clinic", "ortho", "patient_ref_20931"] },});

3. 03 · Search

   Search before responding

   Search intersects the scopes, subtracts superseded and duplicate content, and ranks what survives.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: "Patient asks whether they can start cycling again",  scope: "internal",  similarity_threshold: 0.8,  minimum_similarity_threshold: 0.5,  metadata: { groupName: ["clinic", "ortho"] },   // ∩ narrow scope});// − superseded, deduplicated → ranked → into the window// Every search is recorded as a Context Trace.const reply = await llm.respond(message, { context: contexts });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.