Skip to content
AugentaDocsOpen console ↗
Using the APIs together

Documentation

Guides
View Markdown

Using the APIs together

Choose one-shot processing or Workspace memory, and the calls each one uses.

You want toUse
See what Augenta extracts from some input, without storing itOne-shot Consolidate, no workspace
Give an agent memory that grows with every conversationExperiences to add each turn, Recall before each model call (guide)
Import documents or history in bulkExperiences, then Recall (guide)
Add data and get its extracted claims, or recalled context for a question, back in the same callWorkspace Consolidate
Browse the engrams a Workspace holdsEngrams

One-shot processing

Omit workspace on Consolidate to process only the supplied input:

json
{
  "session": "hello-world",
  "messages": [
    {
      "role": "user",
      "content": "Production releases require owner approval. Record a rollback image digest before deployment."
    }
  ]
}

Read the claims and engrams directly from the result. Nothing is stored, and the result can't be read or searched later.

Workspace memory

A Workspace keeps memory between requests. Add to it in one of two ways.

Experiences accepts source material and processes it in the background. It answers as soon as the input is stored, which makes it the right call to make after every agent turn:

json
{
  "workspace": "ws-research",
  "experiences": [
    {
      "src": "service",
      "sid": "release-runbook",
      "type": "doc",
      "data": {
        "documentId": "release-runbook",
        "text": "Production releases require owner approval. Record a rollback image digest before deployment.",
        "capturedAt": "2026-10-28T12:00:00Z"
      }
    }
  ]
}

Workspace Consolidate adds the input and waits until its claims are extracted and searchable, then returns them. With query it also returns the recalled context for that question. Engrams form afterwards, in the background. Each call waits for a model to extract the claims and only a few run at a time, so don't make it on every turn:

json
{
  "workspace": "ws-research",
  "session": "hello-world",
  "messages": [
    {
      "role": "user",
      "content": "Production releases require owner approval. Record a rollback image digest before deployment."
    }
  ],
  "query": "What is required before releases?"
}

Either way, once an experience is processed its claims are searchable. Recall returns the memory relevant to a question; a claim can be recalled before it joins an engram:

json
{
  "workspace": "ws-research",
  "query": "What is required before releases?",
  "record": false
}

To list what a Workspace holds rather than search it, use GET /v1/engrams and an engram's GET /v1/engrams/{id}/claims. Follow each list's nextPageUrl unchanged for more.