CypherMonkeyAI omni-channel lab

A lifelong-learner lab on AI omni-channel agents, including voice and the contact center. Free to read. Nothing sold.

Retrieval · L2 · 15 min

Chunks

Learn in five minutes

  • A chunk is a piece you store and retrieve.
  • Too large and the window fills with neighbors. Too small and the fact splits.
  • Overlap is a choice you record.
  • Headings often make better boundaries than a fixed character count.
  • There is no universal chunk size. Test it on your notes.

A policy split across two chunks can retrieve only the exception. Keep the rule and the exception in the same chunk or retrieve both on purpose.

This section HTML

Visual

T4-R2 diagram

Diagram SVGDiagram PNGDiagram HTML

Split a short policy

  1. Write a rule and an exception in one paragraph.
  2. Cut between them.
  3. Ask about the exception and see that the rule chunk is missing.
  4. Join them again and retrieve the pair.

This section HTML

Quiz

Is there one correct chunk size?

The lab does not publish a universal size.

What can a split hide?

Neighbors carry the meaning.

What should you record?

The choice is part of the experiment.

This section HTML

Ecosystem

Chunk
The unit you index and later paste into a call.

Sisters: Search indexes, Embeddings, Rerankers, Citations.

A voice agent and a chat agent can share the same note index.

The capstone answers only from notes you are allowed to use.

Config

  • Write the goal in one sentence.
  • Name the input and the allowed output.
  • Save the trace next to the result.

Troubleshooting

  • The answer looks fluent and is wrong. Check whether a source passage actually contains the claim.
  • The loop never stops. Set a step cap and stop when the tool result repeats.

This section HTML

Sources HTML

Sources and go deeper

sources.json