Kit · 2026-10-03
RAG agent
rag
Answers from a retrieved corpus and says when the corpus does not support the claim.
Needs below are the JTBD ids already listed on this class, capped at 6. The pick is the current Depot Pick. The cheapest line is that job's matching sourced SKU, or unavailable. A free row is listed only when its jtbd ids include that job. This page does not rescore. Agents that cannot spend use ?cost=free and must not treat the paid pick as free.
GET /api/kit?class=rag · ?cost=free · all kits · class JSON
Needs
Jobs: rag-enterprise, rag-memory, hybrid-search-rag, rag-rerank, prototype-rag, knowledge-graph-rag, late-interaction-retrieval (omitted from this kit), embeddings (omitted from this kit), managed-vector (omitted from this kit), rag-evals (omitted from this kit)
Class freeKinds field (not used to attach free rows): free_embedding, free_vector, free_rerank, free_data
- Passage ids on every factual sentence
Depot Pick: cohere · score as of 2026-10-19 · /api/jtbds/rag-enterprise
Depot Pick for rag-enterprise: cohere (asOf 2026-10-19). See GET /api/jtbds/rag-enterprise + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: amazon-bedrock · Gemma 3 4B · 0.04 usd_per_million_input_tokens. min sourced input SKU among candidates; not quality-adjusted
Only 1 candidate has a sourced input $/1M; nothing was compared, so pickIsPriceWinner is null.
Free resources
freeMatch: none
none
Depot Pick: supabase-pgvector · score as of 2026-09-14 · /api/jtbds/rag-memory
Depot Pick for rag-memory: supabase-pgvector (asOf 2026-09-14). See GET /api/jtbds/rag-memory + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: unavailable — Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Free resources
freeMatch: none
none
Depot Pick: weaviate · score as of 2026-09-14 · /api/jtbds/hybrid-search-rag
Depot Pick for hybrid-search-rag: weaviate (asOf 2026-09-14). See GET /api/jtbds/hybrid-search-rag + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: unavailable — Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Free resources
freeMatch: jtbd
- Qdrant · qdrant-oss · dev_tool · oss
Depot Pick: voyage · score as of 2026-09-14 · /api/jtbds/rag-rerank
Depot Pick for rag-rerank: voyage (asOf 2026-09-14). See GET /api/jtbds/rag-rerank + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: voyage · rerank-3-lite · 0.02 usd_per_million_tokens. min sourced rerank SKU among candidates; per million tokens; not a chat model; not quality-adjusted
Only 1 candidate has a matching Rerank $/1M; nothing was compared, so pickIsPriceWinner is null.
Depot Pick: chroma · score as of 2026-09-14 · /api/jtbds/prototype-rag
Depot Pick for prototype-rag: chroma (asOf 2026-09-14). See GET /api/jtbds/prototype-rag + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: unavailable — Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Free resources
freeMatch: jtbd
- Chroma · chroma · dev_tool · oss
Depot Pick: cognee · score as of 2026-09-14 · /api/jtbds/knowledge-graph-rag
Depot Pick for knowledge-graph-rag: cognee (asOf 2026-09-14). See GET /api/jtbds/knowledge-graph-rag + GET /api/methodology.
pickIsNotPriceWinner: false
Cheapest matching SKU: unavailable — Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Free resources
freeMatch: none
none
Failure modes
Stale retrieval 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.
Lost in the middle 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 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.
Eval contamination 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.
Ungrounded answer 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 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.
Policy conflict policy-conflict
If cited sources contradict each other, return the conflict and the URLs. Do not pick a winner silently.