# Stage 66: Note Seed & Expand (aq66_seed_and_expand_from_note / DB-UNIT-12)

Turns shared Store S16 notes or live tasks into deduplicated seed queue rows and bounded 1-item-per-row flat expansions without triggering code CI.

- Atomic micro-queue: `aq66_seed_and_expand_from_note` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-12` (`Context Interrogation, Persona Matrix & Problem-Situation Core`)
- Database cell: `entities-db.teleon.dev` (`teleon_core.acquired_observations`, `teleon_core.interrogation_personas_and_rubrics`, `teleon_core.problem_situations`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-12`): `sq12-improve-interrogation-queue.teleon.dev` (Add sharper interrogation questions, expand domain personas, and prioritize high-leverage problem scenarios.)
- Lanes: Note-to-Seed Ignite, Bounded Flat Expand, Zero-CI Fast Lane

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `interrogation_template_and_gap_compiler_v1` (Heading/checklist seed extractor, dedupe hasher & flat expander)
- **Hybrid (<=1 model call)**: `persona_scenario_problemizer_hybrid_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `bot_fleet_persona_interrogator_v1` (Multi-harness seed ideator & subtask decomposition planner)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Partial problem situations remain valid when opportunity, context, and parent observation digests are recorded.
- Every bot-generated interrogation row records exact bot_harness, bot_version, and llm_model metadata.

## External & internal bot fleet actions

- Extract actionable seed tasks from shared research digests, sketches, and postmortems
- Expand high-level note objectives into self-contained depth-1 flat queue rows
- Link every spawned task back to exact note_id and revision SWHID for full lineage

## Sister self-tuning areas

- Add domain personas and who/what/where/when/why question sets (DIM-02, DIM-04)
- Tune urgency weights across humanitarian SDG, competition ML, math, and science labels (DIM-01)
- Compile recurring structured-observation anomaly checks into deterministic code_blocks (DIM-03, DIM-06)