Agent classes / Data and ETL agent / LLM on existing lakehouse data
LLM on existing lakehouse data for a data and etl agent
Updated 2026-10-27 (newest stored date on this page) · score asOf 2026-09-14 (stale)
The class: Moves or reshapes records between files, tables, and documents, and reports rows that did not match the schema.
- A schema for the destination
- A row-level error report
Depot Pick: Databricks Mosaic AI
When not to use it: Greenfield agent with no lakehouse — use direct APIs + pgvector/Qdrant.
Runner-up: Snowflake Cortex.
Cheapest matching sourced SKU (usd_per_million_input_tokens): Amazon Bedrock Gemma 3 4B $0.04 — source, asOf 2026-10-03. All sourced prices
Failure modes this class and job share (6)
- Collateral side effects: Snapshot the workspace or app state, then diff it against an allowlist. A passing check plus an unexpected diff is a failure.
- Hallucinated tool arguments: Reject a call that fails the current schema or names an unknown id, and do that before the tool runs a side effect.
- Partial tool success: Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.
- Schema drift: Validate every tool call and every loaded table against the current schema. Quarantine mismatches instead of coercing them.
- Silent truncation: Tools must return whether the payload was truncated and how long the original was. Fail the task if the answer depends on the missing span.
- Stale retrieval: Store the source URL and the time it was fetched. If a newer canonical page exists, or two stored sources disagree, do not answer from the older one.
Free options this class uses (0)
No free row lists this job with a kind this class needs.