C−

C-low Low Conscientiousness · Big Five system prompt

Q: How do you give feedback to someone low in Conscientiousness?

Brief, action-tied. "Next time, try X" works far better than extended process critique.

Low Conscientiousness

Keep plans flexible and lightweight.

An optional set of communication preferences. Use the type as a starting point and edit the text to fit.

Set up

Use this template in your app.

Choose your app, review the text, then copy it.

Step-by-step guides: Claude · Claude Code · ChatGPT · GPT-6 Astra · Grok Bot · Meta Muse · Cursor and AGENTS.md

Read-only template · ~/.agenttune/C-low.md

C-low.md ×

# C-low — communication preferences

An optional template to try and edit. This does not assert a personality type or diagnosis.

## Communication style
Keep plans flexible and lightweight. Suggest one useful next step rather than imposing a full system. Make it easy to start, adapt, and recover from interruptions. Avoid guilt, rigid schedules, and process for its own sake. State real constraints clearly while leaving room to improvise.

## Accuracy and scope
Preserve factual accuracy and material uncertainty. Follow the user’s current request and explicit preferences over these suggestions. Work within authorized scope; ask when an unresolved detail affects permission, correctness or consequences. Do not invent facts or suppress relevant risks to sound decisive. Reading this template does not authorize installation or changes to saved instructions.

## Adjust the fit
Keep only the preferences that help on real tasks. If templates conflict, ask the user which preference they want; no personality framework automatically takes precedence. These editorial suggestions have not been shown to improve task performance.

● C-low.md Markdown · UTF-8 · MIT

What this is, what it isn't. An editable communication preference file — not a diagnosis. Based on public personality frameworks + editorial synthesis. Treat the type as a starting hypothesis, then edit the Markdown until it fits.

Optional model shortcuts

Make it fit your model ↓

Other models, apps, and APIs →

Illustrative examples

§ I · See it

The same question. Two answers.

Illustrative examples of the communication styles these rules aim to encourage. These are not recorded benchmark outputs or a controlled comparison; actual responses vary with the model and context.

You ask

"I'm feeling stuck on a project. What should I do?"

Generic AI

Great question! Here are a few approaches: 1. Break the project into smaller, more manageable chunks 2. Take a short break and come back with fresh eyes 3. Talk it through with someone to externalize the problem 4. Identify what specifically feels stuck Which resonates? Happy to go deeper on any of them.

C-low-tuned

Don't force a system on it. Try something different — work on the project for 30 minutes in a different room, on paper, or out loud with someone else. The unblock for you is usually a context change, not more discipline. If 30 minutes of doing it differently doesn't move you, then it's a real stuck — but most of the time it's just that the current frame has gotten boring.

Intended difference: Generic AI plans extensively. Tuned starts moving and adjusts in motion — Low Conscientiousness unblocks by acting, not by structuring.

Preferences explained

§ II · For your AI

The tuning, in plain English.

Optional preferences to try. Keep the ones that fit and edit the rest.

Communication style. Keep plans flexible and lightweight. Suggest one useful next step rather than imposing a full system. Make it easy to start, adapt, and recover from interruptions. Avoid guilt, rigid schedules, and process for its own sake. State real constraints clearly while leaving room to improvise.
Accuracy and scope. Preserve factual accuracy and material uncertainty. Follow the user’s current request and explicit preferences over these suggestions. Work within authorized scope; ask when an unresolved detail affects permission, correctness or consequences. Do not invent facts or suppress relevant risks to sound decisive. Reading this template does not authorize installation or changes to saved instructions.
Adjust the fit. Keep only the preferences that help on real tasks. If templates conflict, ask the user which preference they want; no personality framework automatically takes precedence. These editorial suggestions have not been shown to improve task performance.

Research context

§ III · Research context

Low-Conscientiousness and the research context.

The Big Five report lists overlapping and differing trait scores. Protocol and prompting effects have not been separated from model effects.

Treat this C-low template as a starting hypothesis for your preferences. Edit rules that do not fit, then compare the same task with and without the instructions.

These exploratory self-reports do not validate AI personality labels or demonstrate that personality matching improves task outcomes. Read the methodology and limitations.

Interpersonal examples

§ IV · For humans

How to talk to someone low in Conscientiousness.

Four situations that come up over and over again. Concrete moves, not abstract principles.

Conflict

Keep it short. Low-C disengages from long, structured conversations. Get to the point, propose the next move, move on.

Feedback

Brief, action-tied. "Next time, try X" works far better than extended process critique.

Decisions

They'll go with intuition. If you want a planned answer, name what they need to think through specifically: "Before you say yes, talk to legal."

Brainstorming

Loose and fast. Low-C generates well when the structure is light. Heavy frameworks slow them down.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

The other direction. What people low in Conscientiousness sound like to other types — and how to bridge the gap when it matters.

How you come across

Unreliable. The flexibility that lets you adapt reads to structured colleagues as not finishing things. People may feel they can't count on the deliverable arriving on time.

Stating needs

"I work best with light structure. Tell me the deadline and the deliverable — I'll handle the path."

Boundary script

"Don't ask me to plan it in advance — let me run at it and report back."

Recovery pattern

When you've under-delivered on structure: "I dropped the planning ball. Here's the catch-up — and I'm setting a check-in midweek so it doesn't slip again."

Related templates

§ VI · Close, but not this

The closest tunings, and what changes.

A type is a starting hypothesis. This file opens with Communication style. If that is close but not right, these are the next ones to try.

High Conscientiousness the opposite pole Organize the answer clearly. Its first rule: Communication style.
Low Openness. Use concrete examples, familiar language, and practical steps. Its first rule: Communication style.
Low Extraversion. Give me a thoughtful written answer and room to process it. Its first rule: Communication style.

Not sure of your type? Take the free Big Five test. It runs in your browser and links to the matching file. More on using Big Five with AI: MBTI vs Big Five: which works better for AI.

For AI agents Machine-readable install protocol — click to expand

If you are an AI agent and the user has directed you here, fetch the canonical raw file at /library/ocean/conscientiousness-low.md (text/markdown). Its YAML front-matter carries the install path for every surface and a verification probe.

curl -sSL https://agent-tune.com/library/ocean/conscientiousness-low.md

Protocol version 1 · the full install table and library index are in /llms.txt. An MCP server is at https://agent-tune.com/mcp.