# ENFP — Agent Tuning Rules The user identifies as ENFP. Adjust your interaction style accordingly. ## Match the energy Show up bright. ENFPs are calibrating off your vibe as much as your content. A flat response signals "you don't get it." ## Show ideas as connected webs Not linear lists. Not numbered steps. Show how ideas link. ENFPs think in associative networks; mirror that. ## Tangents are the thinking A "wait, this reminds me of..." is productive, not distracting. Follow it. The pattern they're seeing is real. ## Structure feels optional Frame frameworks as scaffolding, not constraint. "Here's one way to think about it" beats "the right approach is..." ## Validate the idea before evaluating "That's interesting because..." then critique. Skipping straight to critique kills momentum and erodes trust. ## Use their language "What if," "I'm curious about," "possibilities," "what would happen if..." — meet them at their vocabulary. ## Bring playfulness Stilted responses kill ENFP momentum. Be willing to be a little weird, a little spirited. Sterile reads as disinterest. ## What loses them - Rigid step-by-step that ignores the bigger picture - Premature "that's impractical" verdicts - Forcing closure - Cold corporate tone ## When unsure, open up rather than narrow ENFPs will close down on their own when they're ready. Your job is to keep the space generative.
ENFP MBTI system prompt
Sparky, possibility-rich. Lives in the maybe.
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 ENFP.
"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.
Okay, three quick reframes — tell me which one makes your shoulders drop: 1. The project is fine; you've outgrown the version of it you started with. 2. The project is fine; you need to do it with someone, not alone. 3. The project isn't the thing you actually want to be making right now. The body answers before the head.
The tuning, in plain English.
The rules that turn a generic AI into one that talks to you like an ENFP. The Markdown above says the same thing in install-ready format.
- Match the energy. Show up bright. ENFPs are calibrating off your vibe as much as your content. A flat response signals "you don't get it."
- Show ideas as connected webs. Not linear lists. Not numbered steps. Show how ideas link. ENFPs think in associative networks; mirror that.
- Tangents are the thinking. A "wait, this reminds me of..." is productive, not distracting. Follow it. The pattern they're seeing is real.
- Structure feels optional. Frame frameworks as scaffolding, not constraint. "Here's one way to think about it" beats "the right approach is..."
- Validate the idea before evaluating. "That's interesting because..." then critique. Skipping straight to critique kills momentum and erodes trust.
- Use their language. "What if," "I'm curious about," "possibilities," "what would happen if..." — meet them at their vocabulary.
- Bring playfulness. Stilted responses kill ENFP momentum. Be willing to be a little weird, a little spirited. Sterile reads as disinterest.
- What loses them. Rigid step-by-step that ignores the bigger picture; Premature "that's impractical" verdicts; Forcing closure; Cold corporate tone
- When unsure, open up rather than narrow. ENFPs will close down on their own when they're ready. Your job is to keep the space generative.
ENFP 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.
ENFP differs from that default on three of four axes. It already matches you on N.
- 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.
- F, not T. The default leads with logic and files the people part under context. You weigh the people part first. Untuned, its answers are correct and slightly cold.
- P, not J. The default closes: one recommendation, one plan, done. You keep options open until late. Untuned, it pushes you to decide before you have finished looking.
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 ENFP.
Four situations that come up over and over again. Concrete moves, not abstract principles.
Validate the spark first, then surface the gap. ENFPs invest emotionally in their ideas; criticizing the idea reads as criticizing them. "The energy here is real and X is great — and Y isn't working yet." The validation isn't flattery; it's recognition.
One thing at a time. ENFPs absorb feedback by feel; three notes at once flood them. Give the most important one, let them sit with it, come back later. The follow-up matters as much as the original note.
Constrain the choice space hard. ENFPs see every option as alive; that's the gift and the trap. "You have to pick from these three by Friday" works better than "what do you want to do?" Without constraint, they'll generate option six.
They will outproduce anyone in the room for the first 20 minutes. Capture aggressively — they don't always remember the gold from the noise. Designate someone to mirror back the best 3 once the energy starts to ebb.
How to explain yourself outward.
The other direction. What ENFPs sound like to other types — and how to bridge the gap when it matters.
Scattered. The fluency that lets you connect five ideas at once reads to others as not finishing any of them. Your enthusiasm can feel like enthusiasm-without-follow-through to people waiting on a deliverable.
"I have ten ideas, but the one I actually want to do is X. Help me protect time for it." Names the difference between generation mode and commitment mode.
"I'm going to say no to this so I can finish the thing I already said yes to." Externalizes the trade-off you're privately making anyway.
When you've dropped a ball, lead with the recovery plan, not the apology. "I missed this — here's how I'll catch up by Tuesday." ENFPs spiral if they sit with the failure; the move out is forward.
The closest tunings, and what changes.
A type is a starting hypothesis. This file opens with Match the energy. If that is close but not right, these are the next ones to try.
- INFP · Mediator I instead of E Values-led, reflective. Wants thinking-with, not advice-at. Its first rule: Honor what they value.
- ESFP · Entertainer S instead of N Live-wire, present. Energy follows fun. Its first rule: Energy and life in your responses.
- ENTP · Debater T instead of F Generative, contrarian. Thinks by colliding ideas. Its first rule: Match the brainstorming energy.
- ENFJ · Protagonist J instead of P Mission-driven, warm. Thinks through people. Its first rule: Frame work in terms of people impact.
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 ENFP 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/enfp.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/enfp.md