Fifteen minutes. Five systems. Decision first.

Panel default = Strict-local packs + spine-health; public Free demos are honesty-labeled — not warm SLOs. Fifteen minutes, five systems, decision-first. Prefer AegisAI and Enterprise RAG Strict packs (local or GCP) when you care about fail-closed policy. Spine-health also probes observability/status compose honesty (does not gate warm SLO). Replay the golden-path artifact for ask→RAG→govern→meter without a guided tour. Cloud proof is ephemeral AWS/GCP receipts, not always-on EKS.

~15 min · 5 spine steps · Demo vs Strict
/spine-healthGOLDEN_PATH.md
  1. 1

    Governance — AegisAI

    I'd put an independent gateway in front of irreversible tools — policy, HITL on the scary ones, signed audit. The agent graph doesn't get a back door. UI labels Demo vs Strict from PRODUCTION_STRICT; panel default is the Strict-local pack.

    3 min
  2. 2

    Orchestration — Venkat AI Platform

    Multi-agent OS for what agents should do — specialists, RAG strategies, gateway-wrapped notify. Demo strip admits fail-open notify by default; Strict is the panel path when you care.

    3 min
  3. 3

    Knowledge — Enterprise RAG

    Filter by who the caller is before you rank. Optimizing recall with unauthorized neighbors is how demos look smart and prod leaks. Dual path: Demo (body Principal) + Strict JWT (ADR-0006/0009).

    3 min
  4. 4

    Application — AI Content Factory

    Side effects stay behind gates. Research → drafts → HITL → publish. Banner shows Demo vs Strict; publish fails closed when Strict. Golden path uses /health only — Clerk for live publish.

    3 min
  5. 5

    Decisions — ADR portfolio + eval proof

    Why these seams exist: 33 ADRs (orchestration vs governance, RAG auth, PRODUCTION_STRICT), golden-eval CI gates, and a replayable ask→RAG→govern→meter artifact.

    3 min

Convinced the spine holds?

Full catalog is 12 platforms, 5 teaching patterns, and 17 repos — secondary to the five above.

View full portfolio