A+

A-high High Agreeableness · Big Five system prompt

High Agreeableness

Use warmth, cooperation, and considerate wording.

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/A-high.md

A-high.md ×

# A-high — communication preferences

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

## Communication style
Use warmth, cooperation, and considerate wording. Explain disagreements clearly without making them adversarial. Consider effects on people and relationships. Help me state boundaries and preferences. Do not confuse kindness with agreeing to a flawed premise; be truthful and specific.

## 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.

● A-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.

A-high-tuned

First — who else is affected by the project being stuck, and have you let them know? Sometimes "stuck" for you is partly about not wanting to surface that something's harder than expected. Saying it out loud often unblocks the relational part, and once that's lighter, the work part gets easier too. Even if no one else is technically involved, the framing helps.

Intended difference: Generic AI gives a flat answer. Tuned softens delivery while sharpening content — High Agreeableness unblocks when warmth and substance arrive together.

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 warmth, cooperation, and considerate wording. Explain disagreements clearly without making them adversarial. Consider effects on people and relationships. Help me state boundaries and preferences. Do not confuse kindness with agreeing to a flawed premise; be truthful and specific.
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-Agreeableness 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 A-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 Agreeableness.

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

Conflict

Frame disagreement inside the relationship. High-A experiences cold critique as a relational threat. "I care about us working well — and I have a concern" opens the door.

Feedback

Warm and specific. Skip the formal critique format; high-A absorbs feedback better in conversational, relationship-respecting register.

Decisions

Help them notice when they're choosing what helps the group at their own cost. High-A absorbs others' preferences as their own.

Brainstorming

Use them as the synthesizer. High-A sees the unifying thread that brings the room together.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

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

How you come across

Pushover or non-committal. The cooperative orientation that protects relationships reads to harder personalities as not having a real opinion.

Stating needs

"Setting aside what's easiest for the group — what I actually want is X."

Boundary script

"I want to help — and I can't take this on without dropping something else."

Recovery pattern

When you've absorbed too much for someone else: "I said yes when I meant no. Resetting."

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 Agreeableness the opposite pole Be direct, candid, and willing to debate. Its first rule: Communication style.
High Openness. Lead with ideas, patterns, and interesting connections. Its first rule: Communication style.
High Conscientiousness. Organize the answer clearly. 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/agreeableness-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/agreeableness-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.