Agent classes / RAG agent / Enterprise RAG stack
Enterprise RAG stack for a rag agent
Updated 2026-10-27 (newest stored date on this page) · score asOf 2026-10-19
The class: Answers from a retrieved corpus and says when the corpus does not support the claim.
- Passage ids on every factual sentence
Depot Pick: Cohere
When not to use it: Simple app RAG on Postgres — use supabase-pgvector instead of a dedicated RAG vendor.
Runner-up: Pinecone.
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 (7)
- Policy conflict: If cited sources contradict each other, return the conflict and the URLs. Do not pick a winner silently.
- 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.
- Ungrounded answer: Require a source URL or passage id on factual sentences. Drop or mark any sentence whose source does not contain the claim.
- Context overflow: If the input exceeds the window, say so and retrieve a narrower slice. Do not answer from a truncated head as if it were the whole source.
- Eval contamination: Keep gold labels out of the agent prompt. Store the harness version beside the score. Do not compare a number across a benchmark revision without saying the revision changed.
- Lost in the middle: Ask the agent to name the passage it used. Spot-check questions whose only support sits in the middle of the context, not only at the edges.
- 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.
Free options this class uses (0)
No free row lists this job with a kind this class needs.