Retrieval & Grounding playbook

€39 once

Practice for splitting documents, searching them, and checking that a reply stays on the retrieved text. Each concept is planned as one worked example, one checklist, and one change in a prompt or repo you already have. No set in this playbook is written yet.

Coming soon. This playbook is not for sale on this site. The email links open a message to support@buildsparkai.com with the tier and the track in the subject. There is no form and no payment.

Planned sets

One set per concept below: a worked example, a checklist, and one change in a prompt or repo you already have. None of those sets are written yet.

Cards this playbook sits beside

These are the concept cards. The cards are free. 11 cards on this track are live. A coming soon name is not a card yet.

RAG Live Free card
Retrieve relevant text, then ask the model to answer from that text.
Chunking Live Free card
Splitting documents into pieces that retrieval can store and return.
Embeddings for retrieval Live Free card
Using embeddings to find stored chunks that are close to a query.
Hybrid search Live Free card
Combining word matching and embedding search so exact terms and paraphrases can both hit.
Query rewriting Live Free card
Turning a follow-up question into a search query that stands on its own.
Reranking Live Free card
A second pass that reorders retrieved chunks before they go into the prompt.
Long context vs RAG Live Free card
Choosing between putting the source in the window and retrieving pieces of it.
Document parsing Live Free card
Turning a file, such as a PDF or a page, into text and structure you can chunk.
Vector databases Live Free card
A store built to keep embeddings and return the nearest ones.
Citation & grounding check Live Free card
Checking that a claim in the reply is tied to a source you actually retrieved.
Freshness & access control Live Free card
Whether a source is current, and whether this user is allowed to see it.

Join the waitlist Founding member, about 30% off

See the other tiers on Pricing, or the concept list on the Retrieval & Grounding track.