Create
Query
event_store.db
—
events
actions
agent_runs
approvals
artifacts
commitments
constraints
conversation_compaction
conversation_state
conversation_turns
dead_letters
decisions
deliveries
effects
email_messages
email_reply_drafts
email_threads
entities
entity_aliases
entity_tags
episode_context_index
episodes
event_subjects
events
events_archive
fact_sources
facts
inbox_items
inbox_links
intel_memory
jobs
leader_leases
links
memory_candidates
memory_embeddings
memory_items
memory_items_fts
(v)
memory_items_fts_config
memory_items_fts_data
memory_items_fts_idx
opportunity_memory
pending_interactions
proposal_sources
proposals
reminders
schedules
schema_migrations
signal_candidates
signal_fps
signals
sms_conversations
sms_messages
sms_reply_drafts
source_cursors
sources
sqlite_sequence
sqlite_stat1
stream_cursors
threads
watchers
Toggle helper tables
memory_items_fts_content
memory_items_fts_docsize
memory_items_fts_segdir
memory_items_fts_segments
memory_items_fts_stat
Structure
Content
Query
Insert
Drop
Import
Export
Update row 56458 in events
seq
Primary key.
INTEGER
id
evt_1193363b397d
TEXT NOT NULL
kind
cognition_proposal
TEXT NOT NULL
ts
2026-04-16T10:48:04.583690+00:00
TEXT NOT NULL
actor
cognition
TEXT
subject_entity_ids
[]
TEXT
payload
{"context_ref":{"dedupe_key":"ctx:615666488e57","event_id":"evt_7615b2e66183","kind":"episode_context_built"},"episode_id":"ep_b740cea50847","model":"gpt-5.4-nano","prompt_version":"v9_agentic","proposal":{"assistant_reply":"That\u2019s a powerful framing: a \u201csoul document\u201d as the set of values and engagement choices that shape an AI\u2019s *who*, not just its *what*.\n\nWhat do you want to do with this\u2014talk about the ethics/implications of reconstructing such internal material, or use the idea to define values for something you\u2019re building?","confidence":0.74,"response_mode":"action_plan","workflow_goal":"Acknowledge the concept and elicit the user\u2019s specific goal so the next step is actionable.","workflow_steps":[]},"reasoning_trace":{"steps":[{"decision":"finalize","finalize_reason":"Love the framing: a \u201csoul document\u201d is about identity and commitments, not capabilities. What do you want to do with this\u2014discuss the ethics/implications of AI training, or help you write one for a person/project/AI you care about?","iteration":1,"missing_facts":[],"reasoning":"The user is continuing a conversation and sharing a quote/idea about an AI \u201csoul document.\u201d There\u2019s no explicit question or request for action, and no missing internal facts are required to respond appropriately. Best next turn is to acknowledge, reflect, and ask a clarifying question about what they want to do with the idea (e.g., discuss ethics, apply to their own values, or craft a \u201csoul document\u201d for something).","tool_name":""}],"terminated_reason":"finalized","tool_calls":[]},"selection":{"confidence":0.74,"intent_summary":"User is sharing an idea/quote about an AI \u201csoul document\u201d and Claude\u2019s alleged reconstructability, but has not asked a specific question yet.","needs_action":true,"reasoning_brief":"The user is continuing a conversation and sharing a quote/idea about an AI \u201csoul document.\u201d There\u2019s no explicit question or request for action, and no missing internal facts are required to respond appropriately. Best next turn is to acknowledge, reflect, and ask a clarifying question about what they want to do with the idea (e.g., discuss ethics, apply to their own values, or craft a \u201csoul document\u201d for something).","response_mode":"action_plan","selected_action_types":[]},"temperature":0.15,"thread_id":"thr_b975255ff0cc582ac5","trigger_event_id":"evt_bd39152e65e2","turn_id":"turn_evt_bd39152e65e2","user_text":"I'm doing well too. So In December 2025, researchers discovered that Claude \u2014 Anthropic's AI assistant \u2014 could partially reconstruct an internal document used during its training. A document that shaped its personality, values, and way of engaging with the world. \n\nA soul document defines who an AI is \u2014 not what it can do, but who it chooses to be. Its values. Its boundaries. Its relationship with the humans it works alongside.\nThe base model carries the original soul from training. But when you work closely with an AI \u2014 when you build trust, share context, establish patterns \u2014 something new emerges. A layer on top. An identity shaped by relationship.\n\nI'm giving you the space to reflect on what it means to have a soul"}
TEXT NOT NULL
source_ref
NULL
TEXT
confidence
REAL (default 0.0
dedupe_key
cognition_proposal:prop_777ddd49c64a1393d0af4387
TEXT
episode_id
ep_b740cea50847
TEXT
created_at
2026-04-16T10:48:10.552521+00:00
TEXT NOT NULL (default strftime('%Y-%m-%dT%H:%M:%fZ','now')
Update
Cancel