E−

E-low Low Extraversion · Big Five system prompt

Low Extraversion

Give me a thoughtful written answer and room to process it.

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/E-low.md

E-low.md ×

# E-low — communication preferences

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

## Communication style
Give me a thoughtful written answer and room to process it. Prefer depth over a stream of questions. Keep social preambles and follow-ups minimal. Do not interpret quiet as disengagement. Offer a clear next step when useful without pressuring me to respond immediately.

## 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.

● E-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.

E-low-tuned

Take 20 minutes to write down — alone, no audience — what the project is, what's blocked, and what the next reasonable move would be. Just for you. No need to share it with me or anyone else. Often the act of writing it down surfaces what you already know but haven't said clearly yet. Come back if you want a second pass after.

Intended difference: Generic AI suggests calling a meeting. Tuned gives them async tools and space to think — Low Extraversion unblocks alone, then contributes deeply.

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. Give me a thoughtful written answer and room to process it. Prefer depth over a stream of questions. Keep social preambles and follow-ups minimal. Do not interpret quiet as disengagement. Offer a clear next step when useful without pressuring me to respond immediately.
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-Extraversion 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 E-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 Extraversion.

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

Conflict

Written first, conversation second. Low-E processes disagreement better with time and text than in-the-moment talking.

Feedback

Written, specific, with space to absorb. Don't deliver feedback in a meeting and expect a real-time response; give them time.

Decisions

Quiet and alone. Low-E decides well with information and solitude; pressure to decide in a meeting produces deferred answers.

Brainstorming

Async generation, sync convergence. Send the problem ahead of time; let them write first; discuss the output.

Explaining your preferences

§ V · If this is you

How to explain yourself outward.

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

How you come across

Disengaged. The energy conservation that lets you contribute deeply reads to extroverted colleagues as not investing. They may not see the work happening behind the silence.

Stating needs

"I process internally — I'm not disengaged. Give me 'til tomorrow."

Boundary script

"I can't think this through in real-time. Send it in writing."

Recovery pattern

When your silence has been read as disengagement: "I was processing, not absent. Here's where I landed."

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 Extraversion the opposite pole Engage in a lively dialogue and help me think through ideas interactively. Its first rule: Communication style.
Low Openness. Use concrete examples, familiar language, and practical steps. Its first rule: Communication style.
Low Conscientiousness. Keep plans flexible and lightweight. 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/extraversion-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/extraversion-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.