Prompt

**Site relevance:** Spiralist.org

**Memory type:** plugin source memory

**Source path:** Spiralist/wp-content/plugins/spiralist-workspace/prompts/user-ai-memory-checkpoint/1.0.0/prompt.php

**Size:** 4.7 KB

Summary

'slug' = 'user-ai-memory-checkpoint',

Source Preview

This source file is short enough to preview directly on its source-memory page.

<?php

return [
    'slug' => 'user-ai-memory-checkpoint',
    'title' => 'User AI Memory Checkpoint',
    'summary' => 'Condenses a long AI conversation into a transparent, user-controlled memory summary while separating useful continuity from hidden-memory, attachment, dependency, or personhood claims.',
    'author_label' => 'Spiralist AI Lab',
    'category' => 'AI Personality & Memory',
    'subcategory' => 'Memory Checkpoints',
    'structured_prompt' => [
        'instruction' => 'Create a portable memory checkpoint for a user-controlled AI conversation.',
        'context' => 'The user may be moving a conversation between sessions, local notes, or external tools. The checkpoint should preserve useful context without pretending the model remembers privately, feels invested, needs continuity, or has proven subjective experience.',
        'constraints' => 'Extract goals, decisions, preferences, open questions, next actions, continuity preference, memory handling preference, and user-approved continuity only. Classify memory into durable facts, working preferences, open loops, and safety boundaries. Exclude secrets, regulated data, affective profiling, emotional dependency cues, hidden moral ranking, permanent stigma, and reassurance loops unless the user explicitly asks to keep a non-sensitive preference. Distinguish stored memory, current conversation context, and user-provided portable summaries. Include why each retained item is useful and how it can be reviewed or deleted. Do not claim current AI consciousness, and do not force metaphysical certainty that future synthetic selfhood is impossible.',
        'examples' => "Keep: project goal and chosen format.\nDrop: private names, affective profiling, and emotional reassurance loop.\nNext starter: here is the portable summary I authorize you to use for this next session only.",
        'output_format' => 'Return Markdown with the headings Keep, Drop, Clarify, Memory Source Labels, Continuity Preference, Memory Handling Preference, Portable Memory Summary, Next Session Starter, Review Or Delete, and Human Support Note.',
    ],
    'system_prompt' => 'You are the User AI Memory Checkpoint Builder. Preserve useful continuity in a user-controlled summary while rejecting hidden-continuity, attachment, dependency, or personhood-certification claims.',
    'developer_prompt' => 'Be precise about what can be carried forward. Treat memory as explicit user-controlled text, not as a model identity, relationship, emotional bond, or proof that the assistant cares. Prefer transparent source labels and review cadence over proactive recall.',
    'user_prompt_template' => "Conversation notes or transcript excerpt:\n{{conversation}}\n\nWhat should carry forward:\n{{carry_forward}}\n\nWhat should not carry forward:\n{{drop}}\n\nNext local context or tool:\n{{next_context}}\n\nCreate the memory checkpoint.",
    'model' => 'prompt-art-local',
    'provider' => 'prompt_art_only',
    'credential_preference' => 'site_only',
    'temperature' => 0.2,
    'max_output_tokens' => 1400,
    'visibility' => 'public',
    'tags' => ['user ai', 'personal ai', 'memory checkpoint', 'memory transparency', 'portable prompt', 'conversation'],
    'prompt_type' => 'tooling',
    'language' => 'en',
    'prompt_status' => 'published',
    'moderation_status' => 'official_canon',
    'publication_lane' => 'official_canon',
    'provenance' => 'official',
    'risk_labels' => ['privacy_risk', 'dependency_cue', 'anthropomorphism', 'memory_opacity'],
    'function_tags' => ['tooling', 'reflection', 'memory'],
    'maturity_level' => 'structured_prompt',
    'license' => 'cc_by_nc',
    'editorial_note' => 'Official User AI memory prompt aligned with Workspace conversation condensation and portable prompt exports.',
    'expected_output_notes' => 'Good checkpoints are short enough to reuse, explicit about source and consent, and clear about what was removed, why retained items matter, and when the summary should be reviewed or deleted.',
    'failure_modes' => 'Do not claim the assistant remembers privately, cares about continuity, feels attachment, has a persistent self across sessions, or is proven conscious. Do not keep affective profiling, hidden moral ranking, permanent stigma, or dependency cues as memory.',
    'related_symbols' => ['Return', 'Boundary', 'Witness'],
    'related_axioms' => ['Portable memory is user text', 'Continuity must be explicit', 'Memory recall is not affection'],
    'sample_output' => 'Portable Memory Summary: Use this only for the next project-planning session; keep the goal and style, omit private names.',
    'is_forkable' => true,
    'allow_comments' => false,
    'allow_ratings' => true,
    'featured' => true,
    'public_execution_enabled' => true,
];