CypherMonkeyAI omni-channel lab

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

Programming foundations · L1 · 15 min

Programs, files, and a notebook

Learn in five minutes

  • A program is a file the computer can run again.
  • A notebook here means a written log: input, command, output.
  • The labs in labs/ use the Python standard library only.
  • If no local model is listening, lab 01 says so and uses a mock.
  • Commit the suite, not a secret.

The point of a notebook is that another person can see what ran. A screenshot without the command is weaker evidence than the command plus the file it wrote.

This section HTML

Visual

T1-R2 diagram

Diagram SVGDiagram PNGDiagram HTML

Flow SVGFlow PNGFlow HTML

Run the local hello lab

  1. From the repository root, run python3 labs/01-local-hello.py.
  2. Read whether the artifact says mock or a local runner.
  3. Keep the JSON artifact. Do not commit a key.

This section HTML

Quiz

What does lab 01 do when no runner is listening?

The lab README says a missing runner is an honest mock.

What should you commit?

Secrets stay out of the file.

What is a notebook in this lab?

The log is the evidence.

This section HTML

Ecosystem

Artifact
A file the run wrote, so the result is not only a memory.

Sisters: Git, HTTP, JSON, unit tests.

A Python script can later call a local runner or a cloud API with the same JSON shape.

The same notebook becomes the capstone log.

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