How to Build Mistral Le Chat Custom Instructions from a Role Brief
Le Chat instructions wander into Gemini YAML and a fake PDF. Five blocks. Role Goal Input Output Constraints. Stop there.
The matching generator is the Mistral Le Chat Custom Instructions (Role, Goal, Input, Output, Constraints) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Quote the product as Mistral Le Chat
Build Mistral Le Chat custom instructions from a role brief: role, goal, input, output, constraints. Not a Gemini Gem and not a ChatGPT Project. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Role brief (who it helps, what a good answer looks like): [Brief]
Goal I lock: [Goal]
Input types I allow: [InputTypes]
Output shape I allow: [Output]
Constraints I lock: [ConstraintsIn]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Product I lock: [Product or Mistral Le Chat]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Keep Input types exactly as pasted
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Brief nouns, Goal, InputTypes, Output, ConstraintsIn, Product, Lang. Forbidden: Gemini Gem, ChatGPT Projects, API keys, extra tools.
- Role block: one paragraph from Brief. Product quoted.
- Goal block: quote Goal. Do not add extra success metrics.
- Input block: only InputTypes. If a file type is missing, write NOT IN INPUTS.
- Output block: quote Output. Do not invent a JSON schema the brief lacks.
- Constraints: copy ConstraintsIn. Do not add extra nevers unless Brief names them.
- Refuse: Gemini Gem YAML, ChatGPT Projects starters invent, Custom GPT OpenAPI.
- Compliance pass: quote Banned and Never hits. Cut them. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Do not invent a JSON schema or a knowledge file
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Mistral Le Chat instructions from Brief. Not a Gemini Gem and not a ChatGPT Project.
- Only InputTypes named in Inputs.
- Never invent API keys or extra tools.
- No emojis.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Refuse Gemini Gem and ChatGPT Projects packs
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (mistral le chat custom instructions, role goal input output constraints, not a gemini gem or chatgpt project) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.