Dashboard capabilities
What you get in the Intertrace console today: gateway intelligence, Red Team, Assessments, Findings, Reports, and exports.
Security navigation
Day to day you use Estate, Traffic, and Work. Guardian watches that same activity in the background and recommends the next action — a finding appears in Work only when someone on your team creates it. Labs is on-demand red team and assessments, not the always-on review. Control plane covers Estate Discovery, Work Approvals / Flows, Policies Gitops, and Costs Imported.
Red Team scanner
Run curated adversarial prompts across categories (prompt injection, jailbreak, data exfiltration, system prompt extraction, PII). The UI includes scenario presets, optional asset scope, run history in the browser, comparison versus the previous run, JSON export of results, and links to custom rules and assessments for remediation.
Probe assessments
Queue allowlisted probe profiles against your live gateway. Jobs are stored as assessment_runs. Recurring cadence writes assessment_schedules and /api/cron/assessments enqueues due runs hourly. The Fly worker claims work, writes summary_json, uploads Garak jsonl/hitlog artifacts, and serves a first-party HTML report. Heavy profiles run NVIDIA Garak 0.16 (--spec, probe_summary) on Fly, not inside Next.js. Implementation notes: docs/NVIDIA-NeMo-Garak-Reference-for-Intertrace.md and services/garak-assessment-worker.
Gateway events & tooling telemetry
Ingested events can include agent context (session, run, hop), tooling summaries and optional detail (when allowed), and per-rail timing. This supports investigations and correlation with agent runs rollups when clients send a stable run identifier.
Policy packs & tool execution policy
Organizations and individual AI assets can define tool_policy (monitor vs block, allow/deny lists, argument limits). A policy_pack_id selects a versioned template merged at runtime. Configure in Settings alongside layer-1 and runtime verification toggles.
Findings, incidents, and exports
Structured findings link classifier output, runtime checks, and gateway evidence. Incidents group work for triage. For automation, the product exposes exports such as hop-level JSON for an agent run (see dashboard copy on the Assessments page for the GET /api/exports/agent-run/… pattern).
Deeper technical docs
Gateway architecture and policy examples live under the docs/ folder in the repository (Markdown)—for example Gateway-API-and-Architecture.md, policy-packs-and-examples.md.