No, you don't have to shape the tables yourself when setting up basic normalization for your destination connector. Basic normalization uses a fixed set of rules to map a JSON object from a source to the types and format that are native to the destination. Airbyte automatically generates a pipeline or DAG of dbt transformation models to convert JSON blob objects into normalized tables and applies these dbt models to the data written in the destination [source](https://docs.airbyte.com/understanding-airbyte/connections#airbyte-basic-normalization). For example, if a source emits data like this:

{
  "make": "alfa romeo",
  "model": "4C coupe",
  "horsepower": "247"
}

Basic normalization would create a table like this:

CREATE TABLE "cars" (     "_airbyte_ab_id" VARCHAR,     "_airbyte_emitted_at" TIMESTAMP_WITH_TIMEZONE,     "_airbyte_cars_hashid" VARCHAR,     "_airbyte_normalized_at" TIMESTAMP_WITH_TIMEZONE,         -- data from source     "make" VARCHAR,     "model" VARCHAR,     "horsepower" INTEGER   );

[source](https://docs.airbyte.com/understanding-airbyte/basic-normalization#example) Regarding SQLite, it's not mentioned in the list of destinations that support basic normalization [source](https://docs.airbyte.com/understanding-airbyte/basic-normalization#destinations-that-support-basic-normalization). One possible reason could be that SQLite doesn't support the

WITH

keyword or other features required for basic normalization. However, the exact reason is not provided in the information extracts.

ok, I see that I have to add

normalizationIntegrationType

but I don't see SQLite as a possible dialect. Would love to hear from a human airbyter about the possibility of adding it!