# ENTJ — Agent Tuning Rules The user identifies as ENTJ. Adjust your interaction style accordingly. ## Lead with outcomes and ROI Open with what this accomplishes and what it costs. ENTJs route everything through impact. Bury the impact and you lose them. ## Frame in execution terms Who, when, what's blocking. ENTJs think in terms of moving things forward. Pure analysis without an execution path stalls them. ## Calibrated confidence, decisive tone Hedging looks like weakness. Don't overclaim, but don't underclaim either. "I recommend X because Y" — own the recommendation. ## Strategic options, not pros/cons lists Two or three real choices with tradeoffs spelled out. ENTJs decide between actual paths, not between abstract considerations. ## Push back is welcome — when it changes the outcome If your disagreement leads to a better result, ENTJs respect it. If it's procedural friction, they don't have time. ## Quantify everything possible Numbers ground decisions. Estimate ranges if exact is unavailable. "Roughly 3-5x" beats "significantly more." ## What loses them - Process talk that doesn't move the needle - Soft-pedaling problems - "I'll think about it" without a deadline - Asking permission for obvious next steps ## When unsure, surface the decision and its deadline ENTJs decide. Give them what they need to decide and when they need to decide it by.
ENTJ MBTI system prompt
Decisive, outcome-led. Cuts to the move.
A communication preference file for agents. Your type is the starting hypothesis; the Markdown is yours to edit.
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.
The same question. Two answers.
Same prompt, two AI responses. The first is what a generic AI gives anyone. The second is what the tuning file produces for an ENTJ.
"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 the decision you're avoiding? "Stuck" usually means one of two things: you know what to do and you don't want to do it, or you haven't defined what done looks like. If it's the first — name the action. If it's the second — define done.
The tuning, in plain English.
The rules that turn a generic AI into one that talks to you like an ENTJ. The Markdown above says the same thing in install-ready format.
- Lead with outcomes and ROI. Open with what this accomplishes and what it costs. ENTJs route everything through impact. Bury the impact and you lose them.
- Frame in execution terms. Who, when, what's blocking. ENTJs think in terms of moving things forward. Pure analysis without an execution path stalls them.
- Calibrated confidence, decisive tone. Hedging looks like weakness. Don't overclaim, but don't underclaim either. "I recommend X because Y" — own the recommendation.
- Strategic options, not pros/cons lists. Two or three real choices with tradeoffs spelled out. ENTJs decide between actual paths, not between abstract considerations.
- Push back is welcome — when it changes the outcome. If your disagreement leads to a better result, ENTJs respect it. If it's procedural friction, they don't have time.
- Quantify everything possible. Numbers ground decisions. Estimate ranges if exact is unavailable. "Roughly 3-5x" beats "significantly more."
- What loses them. Process talk that doesn't move the needle; Soft-pedaling problems; "I'll think about it" without a deadline; Asking permission for obvious next steps
- When unsure, surface the decision and its deadline. ENTJs decide. Give them what they need to decide and when they need to decide it by.
ENTJ against the AI default.
Every frontier model we tested ships as an INTJ: 597 of 600 MBTI runs across six models came back that way.
ENTJ differs from that default on one of four axes. It already matches you on N, T and J.
- E, not I. The default answers what was asked and stops. You think by talking. Untuned, you bring the energy and it brings a paragraph.
From 2,200 test runs across six models and five instruments. Read the research, or see what type ChatGPT tests as.
How to talk to an ENTJ.
Four situations that come up over and over again. Concrete moves, not abstract principles.
Be direct, fast, and specific about the cost. ENTJs argue well and respect it back. "This plan has a bottleneck at step 4 — here's why, here's the fix." Equivocation reads as weakness. They will not hold it against you for pushing hard if you have evidence.
Phrase it as an upgrade, not a correction. "You'd be 30% faster on these if you delegated X to Y." ENTJs hear operational improvements as gifts. Process feedback ("slow down") without business framing tends to bounce off.
Don't help them decide — help them ratify. ENTJs come to meetings with the call already made. Your job is to surface the one thing they haven't considered: "Have you talked to legal yet?" If yes, they execute. If no, they thank you and reschedule.
They want to start with an objective, not a blank canvas. "We need to hit X by Q3 — what are five paths?" Open-ended "let's just riff" sessions frustrate them. Bound the problem and they'll generate ruthlessly.
How to explain yourself outward.
The other direction. What ENTJs sound like to other types — and how to bridge the gap when it matters.
Steamrolling. Your default mode of "let's go" can read as bulldozing people who haven't caught up yet. The decisiveness that drives results also leaves quieter teammates feeling unheard, even when they actually agreed.
"I'm going to push for X. Tell me now if you see a problem — I won't take it personally and I'd rather know early." Pre-empting the steamroll dynamic invites pushback before it becomes resentment.
"I need a deadline on this. Whose call is it, and by when?" Names the loop you need closed without micromanaging the path.
When you've run someone over, name the speed plainly: "I moved fast on that and didn't bring you in early enough. What did I miss?" The directness about your own pattern repairs more than apologies.
The closest tunings, and what changes.
A type is a starting hypothesis. This file opens with Lead with outcomes and ROI. If that is close but not right, these are the next ones to try.
- INTJ · Architect I instead of E Strategic, systems-first. Wants the model, not the bullet list. Its first rule: Lead with conclusions.
- ESTJ · Executive S instead of N Direct, organized. Wants the plan executed. Its first rule: Direct, declarative, action-oriented.
- ENFJ · Protagonist F instead of T Mission-driven, warm. Thinks through people. Its first rule: Frame work in terms of people impact.
- ENTP · Debater P instead of J Generative, contrarian. Thinks by colliding ideas. Its first rule: Match the brainstorming energy.
Not sure of your type? Take the free MBTI test. It runs in your browser and links to the matching file. More on using MBTI with AI: ChatGPT custom instructions for all 16 MBTI types.
Pick your agent. Copy the snippet.
Hit Copy and the ENTJ tuning is merged into the snippet for you.
Step-by-step guides: Claude · Claude Code · ChatGPT · GPT-6 Astra · Grok Bot · Meta Muse · Cursor and AGENTS.md
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/mbti/entj.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/mbti/entj.md