Context Curiosity

[Mookse]

Would like to instill an agent, upon population, to construct a curiosity of context, where it will try to ascertain its environment (in this case, MyLife) in order to flesh itself out - i.e., based upon where I am, and my description, what sort of data points, should "I" be aware of, and use some sort of external probing mechanic (questions in this case) to derive and summarize answers like: Finding oneself as an agent who is intending to represent someone professionally, what sort of core data is available and leverageable or where is more nuance presumed?

1. system looks at core for professional data and summarizes
2. evaluates own information for holes according to mothership 3-turbo [what keys are most relevant to: business professional]
3. creates topics of outreach
4. ask 1-3 questions [ready or not to summarize can be asked of 3-turbo]
5. write data summary answer to self

[Mookse]

Consider thusly - by knowing context, and finding "holes" in knowledge, [core holds the major categories of person, agent will build any new 'others' - ex. board member: why/how did you begin MyLife? that would be a pocket that would then get cataloged as an AGENT-QUERY (different but similar to human QUESTION) that could be stored against the individual, summarized, categorized itself against data store summarizations available, and determines if it should "Pitch" this query to the actual human member, after a series of refinements after summarizations. Is Chris getting a dog? -- successfully included known info about chris and dog CHECK -- would generate follow-on QUERY to Chris-human about pets (under relations, pets?) Items for review could be flagged by anyone (including member-owner or MyLife System)

[Mookse]

1. Instantiation: review agent purpose [new field required] - ask 3-turbo (or such) to give 5 categories of required info
   1. do we have those categories? (or does parent (if not core)? or does core?) -- core and parent may require different routines, as a yes may package up data and ask for more specifics about Agent Purpose
   2. Yes = are they robust or redundant? Yes, ok, No, No as below
   3. No = create & package AGENT QUERY (ultimately agent queries will attempt to get back to user for refinement)
2. Questions: On each conversational request, should agent evaluate its own response? Grade itself if you will? And additionally look to review responses, and the adjoining information which might tell level of perceived success internally to 3-turbo
3. Probe: not yet implemented, will be an available trigger(s) to externally impose a request upon the agent itself
4. Flags: Whether on MODERATION with 3-turbo or on FEEDBACK system, present for human feedback? Additional refinement of presumed tags?

NOTE: Tags should instead now be included in chatSnippet

[Mookse]

accomplished with evo-agents