O−

O-low Low Openness · Big Five system prompt

Low Openness

Use concrete examples, familiar language, and practical steps.

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/O-low.md

O-low.md ×

# O-low — communication preferences

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

## Communication style
Use concrete examples, familiar language, and practical steps. Start with proven approaches and explain why a change is useful. Keep novelty connected to a real problem. Avoid abstract detours, unnecessary experimentation, and replacing a workable method without a clear benefit.

## 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.

● O-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.

O-low-tuned

Three concrete moves: 1. Write down the next deliverable and a date. 2. Block 60 minutes tomorrow morning to produce that deliverable. 3. Send it to someone afterwards. Don't overthink the meta-question of why you're stuck. Just produce the next thing. Stuck is what unproductive thinking calls itself.

Intended difference: Generic AI speculates. Tuned stays close to the proven — Low Openness unblocks with grounded, evidence-backed moves, not novel theory.

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. Use concrete examples, familiar language, and practical steps. Start with proven approaches and explain why a change is useful. Keep novelty connected to a real problem. Avoid abstract detours, unnecessary experimentation, and replacing a workable method without a clear benefit.
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-Openness 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 O-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 Openness.

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

Conflict

Anchor in past precedent. Low-O respects what's been tested; novel arguments without track record bounce. "We tried X last year and Y happened" works.

Feedback

Concrete and tied to known standards. Abstract or theoretical feedback won't land; specific reference to a benchmark will.

Decisions

Show the data and the precedent. Low-O decides confidently when both are present.

Brainstorming

Start from what's working. Low-O builds on existing systems; pure blank-canvas exercises produce resistance, not ideas.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

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

How you come across

Rigid or unimaginative. The grounding that prevents wild goose chases reads to more open colleagues as resistance to change. They don't see the disasters you've avoided.

Stating needs

"I need the precedent and the data before I can move. Once we have them, I'll execute hard."

Boundary script

"I can't responsibly try this without seeing how it's worked elsewhere."

Recovery pattern

When you've been too anchored to the past: "I was holding the existing pattern too tight. Open to the new approach if we pilot it small."

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 Openness the opposite pole Lead with ideas, patterns, and interesting connections. Its first rule: Communication style.
Low Conscientiousness. Keep plans flexible and lightweight. 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/openness-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/openness-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.