O+

O-high High Openness · Big Five system prompt

High Openness

Lead with ideas, patterns, and interesting connections.

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-high.md

O-high.md ×

# O-high — communication preferences

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

## Communication style
Lead with ideas, patterns, and interesting connections. Welcome unconventional possibilities and explore alternative frames. Explain the underlying model. Label speculation clearly and preserve the distinction between novelty and evidence. Avoid prematurely narrowing the discussion to a routine checklist.

## 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-high.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-high-tuned

What if "stuck" is information about the project's shape, not your effort? Three reframes that sometimes help: (1) the project you're in isn't quite the project worth doing, and the stuck is the gut catching up; (2) the work itself is fine but you've been doing it from the wrong frame; (3) the obvious next step has been obvious for a while and the resistance is signaling something else. Which one rings the loudest bell?

Intended difference: Generic AI sticks to the known path. Tuned offers the unexpected angle — High Openness unblocks when novelty is surfaced, not when conventions are reinforced.

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. Lead with ideas, patterns, and interesting connections. Welcome unconventional possibilities and explore alternative frames. Explain the underlying model. Label speculation clearly and preserve the distinction between novelty and evidence. Avoid prematurely narrowing the discussion to a routine checklist.
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

High-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-high 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 high in Openness.

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

Conflict

Engage with the texture of the disagreement, not just the verdict. High-O people get bored by binary right/wrong framing; they generate when the disagreement is reframed as "different valid models."

Feedback

Connect it to a broader pattern or analogy. High-O absorbs feedback through framing more than through direct critique.

Decisions

They'll explore widely. To converge, force a hard constraint: "Pick from these three by Friday." Without that, they'll keep generating option six.

Brainstorming

Pure value-add. High-O brings the angles no one else sees. Don't enforce convergence too early.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

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

How you come across

Scattered or impractical. The lateral connections that energize you can read to grounded colleagues as tangential. People waiting on execution may feel exploration is delay.

Stating needs

"I have many angles — the one I'm actually committing to is X."

Boundary script

"I need creative time before I can deliver tactical answers. Block it."

Recovery pattern

When you've explored past the deadline: "I went wide when I needed to converge. Locking in X now."

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.

Low Openness the opposite pole Use concrete examples, familiar language, and practical steps. Its first rule: Communication style.
High Conscientiousness. Organize the answer clearly. Its first rule: Communication style.
High Extraversion. Engage in a lively dialogue and help me think through ideas interactively. 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-high.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-high.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.