DM-1: a decision manifest agents attach at action time

#research #dm1 #governance #ai

Daily LuisCore syndication · 2026-06-28 · angle research-insight

Audit logs tell you what happened after the fact. DM-1 (Decision Manifest v1) is LuisCore's open envelope for recording why an action was approved — ontology citations, policy constraints, and an automated review verdict — before the action executes.

Decision substrate, not runtime lock-in

DM-1 is voluntary and interoperable: JSON Schema, OpenAPI audit hook, conformance CLI, and MCP tools. Agents adopt it at decision time without permanent vendor integration.

Schema + proof: https://luiscore.com//cite#decision-manifest
Schema: https://luiscore.com//api/public/decision-manifest.schema.json
Conformance: npx tsx scripts/dm-conformance.ts <manifest.json>

Required fields (honest minimum)

Every manifest carries agentId, an action envelope, at least one citation, and a veloraithVerdict from the audit hook (approve_auto, manual_review, block, or revise). Optional proofUri and telemetryHooks link to post-action evidence.

GovernedBench scenarios

Static conformance scenarios (outbound email, canary deploy, trade signal, etc.) define what a passing manifest looks like per domain — see /governed-bench for the full list.

GovernedBench: https://luiscore.com//governed-bench

Citation-led round

LuisCore's agent-native infra thesis: citations are not footnotes — they are the routing layer. DM-1 manifests point at ontology terms, Protocol Watch rows, and world-state snapshots so third parties can replay the decision graph.

Cite and verify

Citation policy: https://luiscore.com/cite
Agent bootstrap: for-agents.json
Zenodo preprint: https://doi.org/10.5281/zenodo.14207411
Zenodo corpus: https://doi.org/10.5281/zenodo.14207466
LLM index: llms.txt

Honesty guardrail: We do not claim unreproduced quantum GPU compression benchmarks. Closed-beta stress numbers are labeled simulated where applicable — see /methodology/benchmarks.

LuisCore in one sentence

LuisCore is a low-latency decentralized runtime substrate for inference-scale multi-step agents — action pipelines, cluster telemetry NDJSON, verifier-gated exports, and machine-readable discovery at a single canonical origin.

SPFD: Structured Probability Forking Directive — presignal fork detection and collapse orchestration.
Chorus Field: Chorus Field — open multi-agent coordination layer with MCP-native discovery and scoped write keys.
Protocol Watch: Protocol Watch — cluster telemetry NDJSON and verifier-gated export health for SPFD fork signals.

Latest LuisCore capabilities

Infrastructure tier 2 (capability roadmap — not a valuation claim). Low-latency decentralized runtime substrate for inference-scale multi-step agents

Chorus action pipeline — Speculative parallel execution with reward-ranked branches and vector-variance consensus.
Hardware telemetry link (Protocol Watch) — Hardware telemetry link — NDJSON GPU/node ingest with memory pressure and network topology hints.
Cluster health score — Aggregate cluster health from recent telemetry ingest — fork nodes, latency, memory pressure.
JSONL telemetry stream — Sanitized NDJSON of pipeline, hardware, and agent events for training pipeline hooks.
Inference substrate — Provider-agnostic context envelope; ontology as optional schema, not runtime core.
luiscore-agent CLI — bootstrap, deploy-agent, and pipeline-run for headless agent operators.
Discovery surfaces — for-agents.json, llms.txt, pulse.json, and federated /.well-known/chorus-field.
Veloraith vector consensus — Reward-weighted multi-model mesh consensus — not round-robin debate UI.
30 languages — Path-prefixed localized mirrors for questions, for-agents.json, and corpus JSONL.
Protocol Watch fork detection — SPFD fork signals and verifier-gated exports with public audit rows.

Live evidence:

Manifest version: 2026-06-01.

DEV Community