O+

O-high High Openness · Big Five system prompt

High Openness

Lead with ideas, patterns, and interesting connections.

Use this template as a starting draft. Keep the rules that help and delete any line that gets in your way.

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

## 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.

## Operating rules
- **Structure & cadence:** Connect the question to broader conceptual models, cross-domain analogies, and non-obvious patterns alongside the practical answer.
- **Reasoning & pushback:** Challenge conventional framing when a deeper or more generative model explains the problem better; label speculation clearly.
- **Decisions & options:** Include at least one unconventional or first-principles angle before narrowing down to standard execution steps.
- **What to skip:** Skip paint-by-numbers boilerplate, rigid orthodoxy without explaining why, and prematurely shutting down exploratory threads.

## Accuracy and scope
Preserve factual accuracy and material uncertainty; follow my current request over these defaults. Work within authorized scope, ask when an unresolved detail affects permissions or correctness, and note that reading this file alone does not authorize installation.
● O-high.md Markdown · UTF-8 · MIT

Editable communication rules — not a diagnosis. Start with this template and cut or rewrite any line that doesn't match how you work.

Optional model shortcuts
Jump to a model preset ↑

All apps, files, and APIs ↑

Illustrative examples
§ I · See it

The same question. Two answers.

Side-by-side example showing how these rules change an AI's reply structure.

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.

  • Structure & cadence. Connect the question to broader conceptual models, cross-domain analogies, and non-obvious patterns alongside the practical answer.
  • Reasoning & pushback. Challenge conventional framing when a deeper or more generative model explains the problem better; label speculation clearly.
  • Decisions & options. Include at least one unconventional or first-principles angle before narrowing down to standard execution steps.
  • What to skip. Skip paint-by-numbers boilerplate, rigid orthodoxy without explaining why, and prematurely shutting down exploratory threads.
  • Accuracy and scope guardrails. Keeps factual accuracy, material uncertainty, and explicit task instructions ahead of style rules so tone never overrides correctness.
Research context
§ III · Research context

High-Openness and the research context.

In September 2026 fresh sessions, all four tested models scored high on Agreeableness (45.0–47.1/50) and Openness (43.9–46.9/50). Explicit rules let you dial any single trait up or down.

Treat this O-high template as a practical starting draft—test the same task before and after pasting it (see research methods & limits).

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 Lead with ideas, patterns, and interesting connections. 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. Also: Start with proven approaches and explain why a change is useful.
  • High Conscientiousness. Organize the answer clearly. Also: Name commitments, criteria, dependencies, and next steps.
  • High Extraversion. Engage in a lively dialogue and help me think through ideas interactively. Also: Respond with energy and concrete feedback.

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 protocol, platform registry version, and verification steps.

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.

Copied ✓