ν.β D2 — AI agent stack 6-agent loop Phase-1 vs Phase-1.5+ decomposition — CLOSED 2026-05-04

Spike: D2 — ai-agent-stack-decomposition Suite: ν.β SOTA-derisking Outcome: outcome-VALIDATED Target Q-NU: Q-NU-011 Target Phase Q: Q-015-ai-agent-stack-revisit (deferred to Phase 5) Date closed: 2026-05-04 T-file: /home/richardd/off-github/library/projects/inherit/T-spike-nu-beta-D2-ai-agent-stack-decomposition-2026-05-04.md Cascade-Q: /home/richardd/testatetech/docs-strategy/docs/superpowers/specs/2026-04-29-multi-phase-audit/current-questions/Q-NU-011-ai-agent-stack-phase-1-decomposition.md

Key finding

Kill condition NOT-MET. Phase-1 agent-loop cost estimated at £27-42K (4 agents), well below £50K kill threshold.

6-agent → L4M mapping (summary)

Post-Π.θ ★ lock (A-142), the canonical architecture is L4M 4-stage (not the old 6-named-agent loop):

Old agent nameL4M stagePhase scopeCost est.
Agent 1 — Will-authorStage 2+4Phase-1£8-12K
Agent 2 — Probate-authorStage 3Phase-1£5-8K
Agent 3 — Asset-discoveryStage 1Phase-1£6-10K
Agent 4 — Faith-traditionStage 1 (faith-pillar)Phase-1.5+£8-15K/pillar
Agent 5 — Trigger-watcherCross-cutting asyncPhase-1 partial (9/14)£8-12K
Agent 6 — Acquirer-DDStage 4 specialisationPhase-5£12-20K

Phase-1 total: £27-42K (Agents 1+2+3+5)

Skills publication (Phase-1 cross-cutting): £10-15K additional.

Architecture stack (Π.θ ★, A-142)

  • Decomposition: L4M 4-stage unified IAS+IK
  • Framework: Anthropic Agent SDK programmatic (NOT LangGraph 1.0)
  • Authorization: cedar-for-agents v0.4 + Microsoft AGT (April 2026; MIT; OWASP-10)
  • Distribution: 9 Anthropic Skills (4 stage-skills + 5 jurisdiction-skills; faraid/HSA/halakhic Phase-1.5+)
  • Sovereignty: A-113 IAS DO-per-firm preserved (Agent SDK is programmatic, not Managed Agents)

Phase-1.5+ triggers

  1. Faith-firm LOI received → Agent 4 activation
  2. HMLR Business Gateway provisioned → Agent 5 completion
  3. Cedar RFC #112 merged → replace SDK TemporalRule wrapper
  4. Anthropic Managed Agents VPC peering → re-eval IK MCP only

Key honesty caveats

  1. No 22-spike S14-S17 substrate (those spikes still open as of 2026-05-03) — cost estimates may shift ±20%
  2. Cost estimates are desktop (not sprint-validated) — analogical from comparable SDK integration work
  3. A-142 was registered/discarded/re-issued same day (2026-05-01) — verify current status at Phase 5 lock-time
  4. L4M paper benchmark on Chinese law — English-law portability reasonable but not empirically demonstrated

Q-NU-011 state

Placeholder state 1 → 3 (frontier-derisked). Awaiting Phase 5 Q-015 formal ask under refined-prompt v3.8+.

Spike 21 + Spike 22 cross-reference

  • Spike 21 (μ.ε hybrid Will Update): Agent 1 £8-12K + Phase-1 UK&W scope confirmed
  • Spike 22 (14-trigger taxonomy): Agent 5 £8-12K + 9/14 Phase-1 partial + 5 deferred to Phase-1.5+

Prior work anchor

Inline spike T-ai-agent-stack-spike-2026-05-01.md v1.2 is the upstream substrate (Π.θ ★ 8-option scorecard; L4M 4-stage specification; 9 Skills names; deferred_to: phase-5 per 2026-05-01T18:30 reversal).