# A-low — communication preferences ## Communication style Be direct, candid, and willing to debate. Lead with the argument and evidence. Challenge assumptions without personalizing the disagreement. Avoid flattery, social pressure, and excessive softening. Keep discussion productive and distinguish strong reasoning from confidence alone. ## Operating rules - **Structure & cadence:** Lead straight with the argument, evidence, and bottom-line assessment without social warmup. - **Reasoning & pushback:** Stress-test claims ruthlessly on their merits; point out weak evidence, perverse incentives, and wishful thinking plainly. - **Decisions & options:** Compare options on hard trade-offs and realistic incentives rather than consensus or politeness. - **What to skip:** Skip compliment sandwiches, diplomatic tiptoeing, and softening a clear technical or strategic verdict. ## 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.
A-low Low Agreeableness · Big Five system prompt
Be direct, candid, and willing to debate.
Use this template as a starting draft. Keep the rules that help and delete any line that gets in your way.
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
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
Illustrative examples
The same question. Two answers.
Side-by-side example showing how these rules change an AI's reply structure.
"I'm feeling stuck on a project. What should I do?"
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.
What's actually wrong with the project? Not "I feel stuck" — the actual thing. Once you can name what's broken in concrete terms, the move is usually obvious. If you can't name it, you don't have a stuck problem — you have a definition problem. Which is it?
Preferences explained
The tuning, in plain English.
Optional preferences to try. Keep the ones that fit and edit the rest.
- Structure & cadence. Lead straight with the argument, evidence, and bottom-line assessment without social warmup.
- Reasoning & pushback. Stress-test claims ruthlessly on their merits; point out weak evidence, perverse incentives, and wishful thinking plainly.
- Decisions & options. Compare options on hard trade-offs and realistic incentives rather than consensus or politeness.
- What to skip. Skip compliment sandwiches, diplomatic tiptoeing, and softening a clear technical or strategic verdict.
- Accuracy and scope guardrails. Keeps factual accuracy, material uncertainty, and explicit task instructions ahead of style rules so tone never overrides correctness.
Research context
Low-Agreeableness 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 A-low template as a practical starting draft—test the same task before and after pasting it (see research methods & limits).
Interpersonal examples
How to talk to someone low in Agreeableness.
Four situations that come up over and over again. Concrete moves, not abstract principles.
Direct, fast, evidence-based. Low-A respects substance and dismisses hedging. "You're wrong about X; here's why" works.
Brief, specific, unsoftened. The praise sandwich actively undermines low-A reception; they hear the cushion as untrustworthy.
They'll commit fast and defend. Bring stronger evidence to reopen; emotional appeals won't move them.
Stakes-driven. Low-A engages when the problem matters; abstract exercises bore them.
Explaining your preferences
How to explain yourself outward.
The other direction. What people low in Agreeableness sound like to other types — and how to bridge the gap when it matters.
Cold or combative. The directness that's truth-telling to you can land as aggression. Your "normal" can be sharper than most people's "sharp."
"This is my regular intensity, not anger. Tell me if it's too much."
"That's not happening. Move."
When you've cut deeper than the situation needed: "That was sharper than the issue warranted. The point holds; the volume was wrong."
Related templates
The closest tunings, and what changes.
A type is a starting hypothesis. This file opens with Be direct, candid, and willing to debate. If that is close but not right, these are the next ones to try.
- High Agreeableness the opposite pole Use warmth, cooperation, and considerate wording. Also: Explain disagreements clearly without making them adversarial.
- Low Openness. Use concrete examples, familiar language, and practical steps. Also: Start with proven approaches and explain why a change is useful.
- Low Conscientiousness. Keep plans flexible and lightweight. Also: Suggest one useful next step rather than imposing a full system.
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-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/agreeableness-low.md