One-Bot workflow

Practice a real-life language conversation

A short role-play, corrections with explanations and a few items to review next time.

Designed for: Language learners who want short practice and useful corrections

Set up Professor Download the workflow guide

Try a sample first

See what a useful result looks like

Illustrative example, not a recorded Bot run. This sample was written to explain the task; your Bot's answer needs checking.

Your first request

Fictional learner: beginner Spanish. Scenario: ordering a coffee. My first answer is 'Yo querer un café, por favor.' Use text only and correct gently.

Example result

A polite option is 'Quisiera un café, por favor.' For a simpler version, 'Un café, por favor' works. 'Querer' is the infinitive; it does not fit after 'yo' here. Next turn: '¿Con leche o solo?' Pronunciation has not been assessed.

Check the answer

Stay at the requested level.
Give a correction and a chance to respond.
Do not claim fluency or pronunciation results from a text sample.

Choose where to try it

Already have an assistant? Copy the sample task into its chat. For a continuing role, review Professor's instructions and limits first.

Set up Professor ChatGPT setup Grok Bot setup Other apps

These are setup guides, not automatic imports. Available tools and account access differ by app.

Inspired by a use shared by @jenyadyo , found through Bot Usecases, curated by KP. The sample above is Bot Cabinet's own fictional example.

Community report; this adaptation has not been runtime-tested.

Full workflow and setup details

Before you begin

Gather the information the Bot needs

Start with the fictional records below
For your own task, choose only the records you want the Bot to use
Remove private details you do not need for the task

Operating guide

Know when to run it and who leads

Lead Bot: Professor
Typical first run: 15–30 minutes for a first manual run
When to run it: When a person supplies the approved brief and starts the workflow

Use this workflow when you need a short role-play, corrections with explanations and a few items to review next time.

Access for the first run

The approved inputs listed on this page
Only the files, sources, and services required for this run
No sending, publishing, spending, or live-system changes without approval

Run the first version one step at a time

Give one Bot the complete job

Use one Bot for the first run. Add a specialist only when the job becomes complicated enough to need a separate role, different access, or independent review.

Professor

Ask my target language and level, then run a short practical role-play one turn at a time. Explain corrections and finish with a short review. Do not claim to have assessed pronunciation from text

Produces: A short role-play, corrections with explanations and a few items to review next time.

Use the approved inputs I provide. Ask my target language and level, then run a short practical role-play one turn at a time. Explain corrections and finish with a short review. Do not claim to have assessed pronunciation from text. Return this result: A short role-play, corrections with explanations and a few items to review next time.. Ask me about missing information before you continue.

Overall request

Ask my target language and level, then run a short practical role-play one turn at a time. Explain corrections and finish with a short review. Do not claim to have assessed pronunciation from text Use only the records I supply. Label missing or uncertain information. Do not connect accounts, browse, send, submit, publish, spend money or create a schedule. Return a draft for my review.

Use this as the complete first-run request.

Decisions for a person

Check the result against the supplied records
Approve any account connection, schedule or outside action separately
Review anything before it is sent, submitted, purchased or published

First test

Try the workflow with low-risk material

Stay at the requested level. Give a correction and a chance to respond. Do not claim fluency or pronunciation results from a text sample.

Check the result

Check the result against your original material. You make the decisions listed below. Stay at the requested level. Give a correction and a chance to respond. Do not claim fluency or pronunciation results from a text sample.

If the workflow stalls

If the result is incomplete, mark the missing information and ask the same Bot to correct it. Add another Bot only when a genuinely separate role or independent check would help.

Set it up in Hermes Desktop

Begin with one Bot and one manual run

Open the linked starter page, download its .tar.gz profile, and import it from the Profiles screen in Hermes Desktop.
Review the profile’s SOUL.md, Bot Passport, and requested access.
Run the complete request in that Bot’s chat with low-risk material and review the result.
Add a schedule, outside connection, or optional specialist only after the manual version works.

Read the official Bot Mode guide