A briefing that keeps itself current

The scenario

There is a question you ask every week. What is this customer’s situation. Where is the migration up to. What do we know about this account. Asking it every week costs a call every week and gives you a slightly different answer each time. Writing the answer down costs nothing and is wrong within days.

Step 1 — Define the standing question

model = client.create_memory_model(
    space_id="accounts",
    name="Acme situation",
    query="What is the current state of the Acme account — blockers, owners, and commitments?",
    trigger={"mode": "delta", "refresh_on_new_memories": True},
)

A memory model is a question plus its maintained answer. refresh_on_new_memories is what makes it standing rather than a snapshot: new memories in the space cause it to rewrite itself.

Step 2 — Read the answer, not the search

current = client.get_memory_model(space_id="accounts", model_id=model["model_id"])
print(current["content"])
print("stale:", current["is_stale"])

is_stale is the honest bit. It tells you the underlying memories have moved since this text was written, so you know whether you are reading a current answer or a recent one.

Step 3 — Force a rewrite when you need it fresh

client.refresh_memory_model(space_id="accounts", model_id=model["model_id"])

Refresh is asynchronous and billed, so trigger it on the cadence you actually need rather than before every read.

Step 4 — See how the answer changed

for entry in client.get_memory_model_history(space_id="accounts", model_id=model["model_id"])["entries"]:
    print(entry["changed_at"], entry["previous_content"][:120])

The history is often more useful than the current text: it is a record of when your understanding of the account changed, which nobody was writing down.

Evals

Create a model, record three relevant memories, refresh, read it.
Record a memory that contradicts the briefing. Check is_stale flips.
Refresh and confirm the new text reflects the contradiction rather than averaging it away.
Read the history and check the previous version is preserved verbatim.

Guardrails

A briefing is a summary, and summaries lose the exception. Do not make an irreversible decision from the model text alone — retrieve the underlying memories when it matters. The model is for orientation, not evidence.

Creating and refreshing cost credits; reading is free. A model refreshed on every write to a busy space is an expensive way to be slightly more current.
A brand-new model briefly has no content. It is generated on the first refresh, and until then there is genuinely nothing to show — render that state rather than an empty string that reads like an answer.
Editing a model’s text does not refresh it, deliberately: a typo fix should not cost a full rewrite.

Built from

Every call above belongs to this runnable script’s territory — memory_basics.py — and the model surface is documented in full at Memory models.

Getting Started

API Essentials

Memory (data plane)

LLM Proxy (drop-in)

Account (control plane)

SDKs & MCP

Integrations

Guides

Use Cases

Changelog

A briefing that keeps itself current

The scenario

Step 1 — Define the standing question

Step 2 — Read the answer, not the search

Step 3 — Force a rewrite when you need it fresh

Step 4 — See how the answer changed

Evals

Guardrails

Built from

​The scenario

​Step 1 — Define the standing question

​Step 2 — Read the answer, not the search

​Step 3 — Force a rewrite when you need it fresh

​Step 4 — See how the answer changed

​Evals

​Guardrails

​Built from

The scenario

Step 1 — Define the standing question

Step 2 — Read the answer, not the search

Step 3 — Force a rewrite when you need it fresh

Step 4 — See how the answer changed

Evals

Guardrails

Built from