Country: Burkina Faso
You are in the Burkina Faso edition. Type your country to switch.
Nigeria
Africa
Loading every country…
No country matches. Check the spelling, or choose "Any country" for the Global edition.
You are learning in the Burkina Faso edition, with examples in cfa francs and from Burkina Faso.
Your learning profile
AI agents and automation basics · Lesson 5 of 9
Memory, retrieval and knowledge
Agents work from what is placed in front of them for each task, plus anything the system retrieves from stored knowledge. This lesson explains context and long-term memory, embeddings and vector search in plain words, retrieval-augmented generation, stale documents and access rights.
This lesson is complete in writing. A video for it is on its way.
What you will learn
- By the end you can tell short-term context from long-term memory and name the risks of each.
- You can explain embeddings and vector search in plain words.
- You can describe retrieval-augmented generation and improve a retrieval prompt.
- You can keep a knowledge base current and make sure retrieval respects access rights.
Key terms in this lesson
- Personal data
- Any information that identifies you or could be linked to you, such as your name, account numbers, address, ID number or voice.
- Embedding
- A long list of numbers that represents the meaning of a piece of text, so that texts with similar meanings end up with similar lists even when the words differ.
- Vector database
- A database that stores embeddings alongside their text and quickly finds the stored items closest in meaning to a new question or passage.
- Citation
- A precise reference to the source of a fact, quote or idea, so that others can find and check it.
- Data provenance
- Where a piece of data came from and how it has been handled since, so that its reliability can be judged.
- Access control
- The rules and systems that decide who can see or change which data and systems, usually based on each person's role.
- Step 1: Short-term context and long-term memory, not started
- Step 2: Embeddings and vector search in plain words, not started
- Step 3: Retrieval-augmented generation in practice, not started
- Step 4: Stale or wrong documents, not started
- Step 5: Access rights in retrieval, not started
About 9 min of reading
Step 1 of 5
Short-term context and long-term memory
Opening this step…
Step 2 of 5
Embeddings and vector search in plain words
This step opens when you finish the one above.
Step 3 of 5
Retrieval-augmented generation in practice
This step opens when you finish the one above.
Step 4 of 5
Stale or wrong documents
This step opens when you finish the one above.
Step 5 of 5
Access rights in retrieval
This step opens when you finish the one above.
Key takeaways
The key takeaways open when you finish every step.
Lesson quiz
5 questions. You need 85% to pass.
The quiz opens when you finish every step.
Read first
Stockertim Learn is education. It explains how investing works and never recommends buying or selling anything.
Popular this week: Basics: BeginnerStock market: Intermediate