CypherMonkeyAI omni-channel lab

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

Agents · L2 · 20 min

ReAct, at learning depth

Learn in five minutes

  • ReAct interleaves a written reason and an action.
  • The paper is Yao and co-authors, 2022.
  • The reason is not automatically true. It is text.
  • The action still goes through your tool and your cap.
  • You can store the reason in the trace so a reviewer can see it.

A reason that says 'the note contains a date' must be checked against the note. The sentence is not the check.

This section HTML

Visual

T5-R5 diagram

Diagram SVGDiagram PNGDiagram HTML

Flow SVGFlow PNGFlow HTML

Reason, then act

  1. Write a reason: the card has no due date.
  2. Act: call the refuse tool.
  3. Check the card.
  4. If the reason was wrong, the trace shows the mismatch.

This section HTML

Quiz

What does ReAct interleave?

That is the pattern's learning summary.

Is the written reason automatically true?

It is text in the trace.

What still applies to the action?

The pattern does not remove the cap.

This section HTML

Ecosystem

ReAct
A pattern that writes a reason and takes an action in turns.

Sisters: Workflows, State machines, Function calling.

The same loop can sit behind chat or a voice turn. The channel does not remove the cap.

MCP is one way to plug tools into that loop. It is the next track.

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