Teach it your vocabulary

The scenario

In your company a “run” is a manufacturing batch, not a jog. “Churn” means something precise with a formula behind it. “The platform” is one specific system, not a metaphor. Default extraction reads your text as general English and stores general English, which is why recall on domain-heavy corpora feels slightly blunt. What this recipe shows that no other does: changing how text becomes memory in the first place, rather than changing how you search it afterwards.

Step 1 — See what a space does today

print(client.get_extraction_settings(space_id="ops"))

Step 2 — Add guidance

guidance is additive: it rides alongside the default instructions rather than replacing them, which makes it the safe knob.

client.set_extraction_settings(
    space_id="ops",
    mode="verbose",
    guidance=(
        "A 'run' is a manufacturing batch with an id like R-2214. "
        "Always keep batch ids and line numbers verbatim. "
        "'The platform' means the order management system, never a metaphor."
    ),
)

mode trades thoroughness for cost: verbose stores more per chunk, so it costs more and recalls more.

Step 3 — Replace the guidelines entirely, if you must

custom_prompt replaces the guidelines block rather than adding to it, and only takes effect with mode="custom". It is powerful and it is how people break extraction — start with guidance.

Step 4 — Undo

client.reset_extraction_settings(space_id="ops")

Reset clears the whole surface, not just your guidance. If the space was created with a file-retrieval strategy, resetting drops that too and every later upload quietly degrades to default extraction. Prefer writing the fields you want over resetting.

Evals

Extraction changes are hard to judge by feel, so measure:

Record twenty representative sentences in a scratch space with defaults.
list_memories and read what was actually stored — this is the step people skip, and it is the only direct view of extraction’s output.
Apply guidance, record the same twenty into a second space, and compare.
Check the specific thing you asked for: are batch ids preserved verbatim?

Never tune extraction against the space you care about. Use a scratch space — settings change future writes only, so an experiment leaves a permanent, mixed corpus behind.

Guardrails

Only future writes are affected. Nothing re-extracts what is already stored; a change to guidance leaves a space with two eras in it.
A typo in mode is refused, not stored. Anything other than concise, verbose, verbatim or custom is a 422 naming the four. The free-text fields are taken as written, so read them back with get_extraction_settings after a change.
More is not better. verbose on a chatty space produces memories about pleasantries, which crowd out the ones that matter.

Getting Started

For Agents

Anona CLI

API Essentials

Memory (data plane)

LLM Proxy (drop-in)

Account (control plane)

SDKs & MCP

Integrations

Guides

Use Cases

Legal

Changelog

Teach it your vocabulary

The scenario

Step 1 — See what a space does today

Step 2 — Add guidance

Step 3 — Replace the guidelines entirely, if you must

Step 4 — Undo

Evals

Guardrails

​The scenario

​Step 1 — See what a space does today

​Step 2 — Add guidance

​Step 3 — Replace the guidelines entirely, if you must

​Step 4 — Undo

​Evals

​Guardrails

The scenario

Step 1 — See what a space does today

Step 2 — Add guidance

Step 3 — Replace the guidelines entirely, if you must

Step 4 — Undo

Evals

Guardrails