--- title: 'Agentic dashboard' description: 'A live human-in-the-loop view of every A2A call your shop sees — verifications, escrow positions, disputes, policy.' canonical: 'https://cartwright.app/docs/features/agentic-dashboard' --- # Agentic dashboard (/docs/features/agentic-dashboard) When buyer agents start hitting your shop, the human shop owner needs a window. `/admin/agentic` is that window. It surfaces the last 24 hours of agentic activity, the current escrow positions, the dispute queue, and (in a follow-up release) lets you edit the legislation policy directly. The dashboard is **read-only in this release**. Force-release / force-refund actions, provider toggle (cloud Anthropic vs local Ollama), and the policy editor are deferred to a follow-up commit so the write-side gets careful UX review. ## Enabling [#enabling] The nav link only appears when `brand.features.adminAgenticDashboard = true`. The `agent-marketplace` template ships with the flag on; other templates default it off (you can flip manually). ```ts // brand.config.ts features: { adminAgenticDashboard: true, } ``` Direct navigation to `/admin/agentic` with the flag off returns 404 — same gating as the nav. ## What you see [#what-you-see] ### 24-hour verification stats [#24-hour-verification-stats] Three counters at the top, scoped to the last 24 hours of `AgenticJWT` rows: | Counter | What | | ----------- | --------------------------------------------------------------------------------------------- | | **Allowed** | Guardian-approved calls (verdict `pass`) | | **Denied** | Guardian-rejected calls (verdict `fail`) — usually scope mismatch, over-cap, or blocked agent | | **Pending** | Calls awaiting external verification (e.g. a webhook callback) | ### Agent Card snapshot [#agent-card-snapshot] Shows the latest non-revoked `AgentCard`: * Version number (monotonic on rotation) * Signed-at timestamp * Expires-at (or "no expiry") * "view JSON →" link that opens `/api/agent-card` in a new tab so you can see what a buyer agent receives If no Agent Card exists, the panel shows an amber warning: "Buyer agents will receive 503 on /api/agent-card until one is published." ### Escrow positions [#escrow-positions] Five cards, one per state in the state machine (`pending`, `funded`, `released`, `refunded`, `disputed`). Each shows row count + total amount in DKK. The state machine guarantees these positions are mutually exclusive — every `EscrowTransaction` is in exactly one bucket. See [Guardian middleware → Escrow state machine](/docs/features/guardian-middleware#escrow-state-machine). ### Disputed-escrow review queue [#disputed-escrow-review-queue] If any `EscrowTransaction.status === "disputed"`, a dedicated red-bordered table surfaces them regardless of age: | Column | Value | | ----------- | --------------------------------------------------- | | Escrow ID | Stable `ctx_…` identifier | | Buyer Agent | The `sub` claim from their A-JWT | | Amount | Formatted DKK | | Disputed At | ISO timestamp | | Reason | Free-text dispute reason set by the disputing party | In a future release, this is where the "force release" and "force refund" buttons will live — but for now, you'd resolve disputes via direct DB writes or by running an admin command. The Master Plan §3.3 mandates human-in-the-loop for these actions; a thoughtful UX is being designed before shipping the write-side. ### Recent verifications (last 50) [#recent-verifications-last-50] Live tail of `AgenticJWT` rows from the past 24 hours. Each row: | Column | Value | | -------------- | -------------------------------------------------------------------- | | When | ISO timestamp | | Agent | `issuerAgentId` (the buyer agent's `sub`) | | Path | `requestMethod requestPath` (e.g. `POST /api/negotiate`) | | Verdict | Color-coded badge: green pass, red fail, amber pending, gray skipped | | Reason / error | `verifyError` when present, em-dash when not | The verdict column reads from Guardian's audit write — see [Guardian middleware](/docs/features/guardian-middleware). ## What's deferred (Phase 9 follow-up) [#whats-deferred-phase-9-follow-up] The next dashboard commit adds write-side actions: 1. **Force-release / force-refund** on disputed escrows. Each action wrapped in `withAudit()` so the resolution is logged to `AuditLog` with an `operator-chat:` actor tag. 2. **Provider toggle** — flip `IntegrationSettings.aiProvider` between `"anthropic"` (cloud) and `"local"` (Ollama via `localAiEndpoint`). The Delegate Agent proxy is already wired in `lib/ai/client.ts`; the dashboard just needs the UI control. 3. **Policy editor** — JSON editor with Zod-schema validation for `BrandingSettings.agenticPolicyJson`. Saves to DB; Guardian picks up changes on the next call (no cache to invalidate beyond the per-call read). 4. **Force-rotate Agent Card** — generate a new ed25519 keypair and sign a new version; mark the previous card `revokedAt = now()`. Buyer agents that cache the public key are forced to re-discover. Each is small in isolation; bundling them adds confirmation flows + audit-trail discipline. ## Wiring it to your data [#wiring-it-to-your-data] The page is a Next.js server component (`app/admin/agentic/page.tsx`) that reads four queries in parallel: ```ts const [recentJwts, escrowsByStatus, jwt24hStats, openAgentCard] = await Promise.all([ prisma.agenticJWT.findMany({ where: { createdAt: { gte: since } }, take: 50 }), prisma.escrowTransaction.groupBy({ by: ["status"], _count: { _all: true }, _sum: { amountMinor: true } }), prisma.agenticJWT.groupBy({ by: ["verifyResult"], where: { createdAt: { gte: since } }, _count: { _all: true } }), prisma.agentCard.findFirst({ where: { revokedAt: null }, orderBy: { createdAt: "desc" } }), ]); ``` Plus a fifth for the dispute queue (always shown, not 24h-scoped). Fast to render — typically \< 50 ms even with many thousand audit rows since everything is indexed.