Closing gaps: teach vs. task

connect a data source ──► creates a pack
                                │
     teach (add knowledge) ─────┤
                                ▼
                          ask the pack ◄─── your questions
                                │
                     can't answer = a gap
                          ┌─────┴─────┐
                   knowledge-miss   data-miss
                     → teach          → task (curate)
                          └──► ask again ◄──┘

This loop is the steady state of operating a pack. Answer questions with ask. When it can’t, that’s a gap, and it tells you enough to route it:

• An answer that says it lacks a definition is a knowledge-miss → teach.
• An answer that can’t find or resolve the data (“no rows”, “couldn’t resolve”) is a data-miss → task.

ask won’t fabricate an answer to paper over either kind of gap.

Knowledge-miss → teach

When ask lacks a fact or definition, the fix is more knowledge. Pick the cheapest reliable source for the missing topic:

1. You already know it, or it’s general: draft a short, factual note.
2. Publicly researchable: research it, synthesize a concise note, cite the sources. Or hand it to the pack: edisyl task "$PACK" "research X and add it to the pack".
3. Org-internal or unverifiable: ask whoever owns that knowledge to provide it. Don’t invent it.

Confirm before you write

Never write to a pack without confirming first: a wrong page poisons every future answer. Show the draft and the payoff, then wait for a yes: “Adding a note on X would make ‘<the question>’ answerable. Here’s the draft. Want me to add it?”

Only on confirmation:

edisyl teach "$PACK" --text "<the note>"       # or --file <path>
edisyl action watch <action-id>                # wait until indexed
edisyl ask "$PACK" "<the failing question>" --wait   # re-ask

Data-miss → task the pack to curate

When ask can’t find or resolve modeled data, hand the pack the work in plain language. By default, task runs the pack’s coordinated fleet: a planner delegates to specialists, models tables, and enriches the semantic layer so the next ask lands. Pass --fast for a single direct executor on a bounded objective.

action_id=$(edisyl task "$PACK" "The 'active wallets' question failed to resolve — model the wallet/swap tables so it answers." --id-only)
edisyl action watch "$action_id"      # narrates the plan and each step as it moves
edisyl action plan <action-id>        # the board on demand: what's working now, what's up next
edisyl action events <action-id>      # raw event tail, when you need to diagnose
edisyl action get <action-id>         # summary + artifacts once terminal
edisyl ask "$PACK" "<the failing question>" --wait   # re-ask — it should land now

task is also the verb for any broader work: “audit the validator docs and flag anything stale”, “focus enrichment on the DeFi sources”, and a task can itself ask and teach as child Actions.

Use judgment on when to curate

Curate once after connecting a source, and whenever a data-miss ask exposes a real gap. Don’t curate on every question, and don’t curate a knowledge-miss; that’s a teach, not a task.

This loop is reactive by nature: it only routes a gap once an ask exposes it. To declare what a pack must answer before anyone asks, see Declaring objectives, the standing counterpart to this same routing instinct.

Next: Scheduling recurring work turns this same loop into something that runs itself.