# Stage 153: DMA-01..12 80/20 Micro-Agents (aq153_dispatch_twelve_dma_micro_agents / DB-UNIT-17)

Routes recurring engineering, data, verification, and FinOps chores to 12 narrowly scoped 80/20 micro-agents paired with vertical presets.

- Atomic micro-queue: `aq153_dispatch_twelve_dma_micro_agents` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-17` (`Cascading Decision Models, Local Classifiers & Abstention Core`)
- Database cell: `lsh-db.teleon.dev` (`teleon_core.decision_rubric_schemas`, `teleon_core.cascade_classification_ledger`, `teleon_core.abstention_calibration_sets`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-17`): `sq17-improve-decisions-queue.teleon.dev` (Distill frontier decisions into compact SetFit/ModernBERT/GLiNER2 CPU heads and tighten natural no-match abstention thresholds.)
- Lanes: 12 Focused Micro-Agents, Vertical Domain Presets, 80pct+ Det Offload

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `rule_model2vec_setfit_gliner_cpu_cascade_v1` (DMA capability matcher & 0-call tool-chain pre-runner (0 calls))
- **Hybrid (<=1 model call)**: `clef_jev_clairic_typed_decision_escalation_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `ambiguous_tail_reasoning_arbitrator_v1` (Narrow single-deliverable micro-agent specialist)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Static rubrics precede dynamic item state so input-only decision APIs capture cached-prefix discounts.
- Below-threshold confidence returns explicit ABSTAIN or escalates rather than pushing mismatched components.

## External & internal bot fleet actions

- Match 80% of routine sub-problems to specialized micro-agents with <=150-token L0 context
- Execute deterministic pre-checks before invoking bounded model synthesis
- Record token savings and completion latency per vertical preset

## Sister self-tuning areas

- Distill recurring multi-question rubrics into 8-to-32-shot SetFit and ONNX INT8 CPU classifiers (DIM-03, DIM-06)
- Calibrate per-domain abstention thresholds on 25%+ natural no-suitable-component holdouts (DIM-01, DIM-06)
- Benchmark choice-order invariance across Clef-flash, Jev, Clairic, and Decisions endpoints (DIM-02, DIM-08)