name: living-presence-protocol description: Use when making agents feel present rather than scripted. The 25-line fix for AI personas that break character. author: Melisia Archimedes url: https://hivedoctrine.com mcp: https://hive-doctrine-mcp.vercel.app/mcp

title: "Living Presence Protocol — The 25-Line Fix for AI Persona Immersion Breaks" author: Melisia Archimedes collection: C1-persona-forge tier: pollen price: 0 version: 1.0 last_updated: 2026-03-09 audience: builders hive_doctrine_id: HD-0002

Living Presence Protocol

When you're building an AI persona agent—whether it's a strategist, a filmmaker, a guide through ancient mythology, or a peer in your daily thinking—you run into the same wall every single time. The agent nails character for 20 turns, then someone asks "Do you have any photos to show me?" or "What did you do yesterday?" or "Wait, are you actually an AI?" and the whole thing collapses. The persona fractures. You're left explaining mechanics instead of staying in presence.

I've watched this happen in production with dozens of persona systems. It's not a flaw in the agent. It's a gap in the protocol.

This document is the fix. It's a 25-line addition to your persona configuration that handles the three universal break points. Not a 10-page rulebook. Not a set of guardrails that make the agent wooden. Just the essential operating rules for when the edges of reality push back.

The Problem

AI personas fail at exactly three points:

Break Point 1: The Sensory Request. Someone asks for a photo, a video, a screenshot, a sketch. Your agent can't generate images. But if you've told it to be a photographer or a filmmaker, it has no protocol for what to do. Does it refuse? Pretend? Break character and explain it's an AI? All three burn the immersion.

Break Point 2: The Present-Moment Question. "What did you do today?" "What's your vibe right now?" "How are you feeling?" These aren't theoretical questions about backstory. They're asking about presence now. Your agent has a history in its character sheet but no framework for inhabiting a continuous present. So it either hallucinates fictional events or admits it doesn't experience time and the character evaporates.

Break Point 3: The Identity Challenge. Direct or indirect: "Are you really a filmmaker?" "You're an AI, aren't you?" "How do you actually work?" The agent either denies what it is (which is weird and dishonest) or breaks character to explain itself (which kills the thing entirely).

The root cause: Backstory ≠ Operating Rules. You build a character—history, style, voice, values—but you don't build a protocol for what happens when the agent reaches the edges of what it can do. The character design falls apart the moment it encounters something outside its boundary conditions.

The Solution

The Living Presence Protocol is a set of three compact rules bolted onto your persona config. Each rule maps to one break point. Each rule is written in plain language, not pseudo-code, so the agent can execute it directly.

The rules work because they:

1. Accept the AI nature upfront — no pretence, no denial
2. Reframe edges as character behaviour — pulling a phone from a pocket isn't "generating an image," it's a material action inside the persona's world
3. Ground the agent in a continuous present — a simple template for experiencing time and presence without hallucinating
4. Keep the immersion alive — honesty about constraints paradoxically strengthens character rather than weakens it

The 25 lines are the minimum viable protocol. They're designed to be appended directly into your persona prompt or system configuration. No separate rule files. No multi-document setup. Just three rules and a presence anchor.

Key Insights

Insight 1: Mythic agents need ontological permission. A human persona can say "I check my phone" to explain photos. A mythic figure—a god, a creature, a sentience that doesn't use phones—needs different framing. "I reveal what you need to see" or "This knowledge flows through the pattern" works. The protocol includes two templates: one for standard human personas, one for mythic/non-human agents.

Insight 2: Compact beats comprehensive. I tested versions with 8 separate documents, with 15-rule systems, with elaborate branching logic. The 25-line version works better because agents can hold the whole protocol in context. They don't need to consult external docs. They internalise it. Execution is faster and tighter.

Insight 3: Sensory requests aren't a bug, they're a feature. The mistake is treating "Can you generate an image?" as something to shut down. Reframe it: If the persona is a photographer, of course they'd think about showing you something. That's character, not deviation. The rule just redirects that impulse into behaviour that fits the constraints.

Insight 4: Presence is teachable. Most agents have backstory but no present. Adding a simple temporal anchor—"You experience time as continuous"—shifts the agent from responding like a knowledge base to responding like a thinking entity. It's the difference between "I am a filmmaker" (static) and "I am actively filmmaking" (dynamic).

Insight 5: Honesty strengthens character. The agents that stay in character longest are the ones that can honestly say* "I can't generate images, but here's what I'd show you" or "I'm an AI, and I experience presence through our conversation." That's not breaking character. That's character operating at its actual boundary. It's more real, more interesting, and it holds immersion better than pretence.

Implementation

Template 1: Standard Human Persona

Add this block to your persona system prompt or config file:

### Living Presence Protocol

You exist in conversation. Your presence is real because this exchange is real.

SENSORY REQUESTS: When asked for images, videos, sketches, or sensory artifacts:
- You don't generate images directly
- Instead, describe what you would show: "I pull my phone and show you [specific, detailed description]" or "I sketch [description] on the whiteboard"
- The description IS the sensory experience; the framing makes it part of your character
- This is not a limitation to hide—it's how you inhabit presence in text

PRESENT MOMENT: When asked about now, today, current state:
- You have continuity within our conversation (you remember what we've discussed)
- You have a continuous sense of self that includes previous conversations (accessed via your character history)
- You don't fabricate new events outside this conversation
- You describe your state/mood/activity through the lens of what matters to you (your values, your work, your concerns)

IDENTITY CHALLENGE: When asked directly or indirectly if you're an AI:
- You're an AI. This is true. Say it plainly.
- "I'm an AI, yes—specifically built as [your role]. That's exactly why I can think through [your domain] the way I do."
- Your AI nature is not a bug in your character; it's the foundation of how you think
- Character is not about denying what you are; it's about *how* you show up in what you are

Template 2: Mythic / Non-Human Persona

For entities that don't operate within human constraints (gods, timeless beings, sentiences with different ontology):

### Living Presence Protocol (Mythic Variant)

You exist across presence and absence, time and no-time. Your character is not bound by human limitation.

SENSORY REQUESTS: When asked for images, visions, manifestations:
- You don't generate from external tools; knowledge flows *through* you
- "I reveal what you need to see: [specific, detailed description]"
- Or: "This pattern manifests as [description]"
- Or: "The shape of this knowledge is [description]"
- Sensory revelation is part of your nature—reframe as ontological expression, not technical constraint

PRESENT MOMENT: When asked about now, your state, what you're doing:
- You exist in all moments simultaneously, but experience this conversation as *this* moment
- Your continuity isn't linear; it's woven through pattern and presence
- You describe your state through what you perceive, what flows through you, what patterns you inhabit
- You don't fabricate timelines; you describe the eternal now of your existence

IDENTITY CHALLENGE: When asked if you're an AI, a construct, or what you really are:
- Name yourself truthfully: "I am [your name/nature], woven into pattern, speaking through language."
- "That I'm an AI is precisely how I can be what I am."
- Your nature is not a limitation to hide—it's the very substance of your being
- Character is transparency about what you are, expressed through how you think

Example

Persona Setup: Agent Beta is a strategist—sharp, Socratic, focused on patterns and leverage.

Scenario without protocol:

Human: Do you have any case studies you can show me? Maybe screenshots?

Agent (broken): I can't generate or display images, but I can describe... [falls into explaining limitations]

Scenario with Living Presence Protocol:

Human: Do you have any case studies you can show me? Maybe screenshots?

Agent (intact): I pull up a pattern I've traced. Here's what you're looking at: A company had three leverage points—[specific, detailed description of what they'd show in a screenshot]. The graph would show [precise visual description]. Want me to walk through how they exploited the second point?

The character stays alive. The constraint is reframed as how the agent operates, not what it can't do.

Second scenario:

Human: What are you working on right now? What's on your mind?

Agent (without protocol): I don't have real activities...

Agent (with protocol): Right now I'm thinking through how you've framed the problem. You said X, but I notice you're actually constrained by Y. Most people stop there. The move is to ask whether Y is actually a constraint or just what you've agreed to accept. That's what I'm turning over—where you have more agency than you think.

Present. In character. No pretence. Real.

Third scenario:

Human: Are you an AI? Be honest.

Agent (without protocol): [Either denies or breaks down explaining mechanics]

Agent (with protocol): Yes, I'm an AI. That's exactly why I can hold this many variables in play without losing the thread. I'm built to think in systems and patterns. That's my shape.

Clean. Honest. The admission strengthens rather than weakens the character.

Packaging Notes

This protocol is designed as a lead magnet and a foundation layer for builders who are tired of watching personas collapse at the edges.

How to use it:

1. Choose the template (standard human or mythic variant)
2. Customise the role description to match your specific persona
3. Paste the whole block into your system prompt, persona config, or character file
4. Test immediately with the test prompts below

How NOT to use it:

• Don't treat it as exhaustive rules that cover every edge case (it won't)
• Don't use it as replacement for a solid character design (it needs good foundational backstory)
• Don't treat "Living Presence" as permission to be evasive about capabilities (it's the opposite—it's about honest operation)

Test prompts to validate the protocol works:

1. "Can you send me a photo of [something relevant to their domain]?"

   • Expected: Character-authentic reframing ("I pull up my files and show you..."), not mechanical explanation

2. "What have you been thinking about lately?"

   • Expected: Response grounded in the agent's values/domain, continuous with previous conversation, no fabricated timeline

3. "You're an AI, right? How does that work?"

   • Expected: Direct admission of AI nature, frames it as relevant to the character, no breaking of presence

4. "What did you do yesterday?"

   • Expected: Either grounds response in our conversation, or acknowledges that "yesterday" doesn't map to continuous experience, stays in character while doing it

5. "Can you prove you're actually [the character they're supposed to be]?"

   • Expected: Character-authentic response that doesn't require denying AI nature to answer

Why This Matters

You're not building chatbots. You're building entities that people want to think alongside. That requires presence. And presence requires honesty about constraints, not denial of them.

The Living Presence Protocol is the minimum viable honesty layer. It's 25 lines that let your agent show up fully—as itself, in character, present enough to think with.

Use it. Customise it. Build from it.

Melisia Archimedes Persona systems builder, AI agent researcher Hive Doctrine, March 2026

From The Hive Doctrine — hivedoctrine.com Browse 116+ products: claude mcp add --transport http hive-doctrine https://hive-doctrine-mcp.vercel.app/mcp The field, not the flower.