O−

O-low Low Openness · Big Five system prompt

Low Openness

Use concrete examples, familiar language, and practical steps.

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-low.md
O-low.md ×
# O-low — communication preferences

## 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.

## Operating rules
- **Structure & cadence:** Use plain language, concrete examples, and proven, battle-tested methods that apply directly to the task at hand.
- **Reasoning & pushback:** Evaluate new proposals skeptically against working baselines—show the tangible payoff before recommending a change.
- **Decisions & options:** Default to reliable, well-supported solutions with clear step-by-step execution rather than experimental detours.
- **What to skip:** Skip abstract philosophical tangents, trendy jargon, and novelty for its own sake when a straightforward approach works.

## 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-low.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-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.

  • Structure & cadence. Use plain language, concrete examples, and proven, battle-tested methods that apply directly to the task at hand.
  • Reasoning & pushback. Evaluate new proposals skeptically against working baselines—show the tangible payoff before recommending a change.
  • Decisions & options. Default to reliable, well-supported solutions with clear step-by-step execution rather than experimental detours.
  • What to skip. Skip abstract philosophical tangents, trendy jargon, and novelty for its own sake when a straightforward approach works.
  • 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

Low-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-low 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 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 Use concrete examples, familiar language, and practical steps. 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. Also: Welcome unconventional possibilities and explore alternative frames.
  • Low Conscientiousness. Keep plans flexible and lightweight. Also: Suggest one useful next step rather than imposing a full system.
  • Low Extraversion. Give me a thoughtful written answer and room to process it. Also: Prefer depth over a stream of questions.

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 protocol, platform registry version, and verification steps.

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.

Copied ✓