> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://developers.alephant.io/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.alephant.io/_mcp/server. # Admin Dashboard > Use the AIvis admin dashboard to review adoption, verified outcomes, model usage, feedback quality, and operational attention items. The Admin Dashboard is the executive and operations overview for AIvis. It helps administrators see whether AI work is being adopted, whether Agent and automation outcomes are succeeding, and where usage, feedback, or coverage needs attention. Use it as a product and operations surface. For request-level investigation, use [Tracing](/aivis/governance/tracing) and [Query History](/aivis/governance/query-history). For raw model usage and cost breakdowns, use [Usage Statistics](/aivis/governance/usage). ## Interface Screenshots The screenshots below show the dashboard with real example data from a Chinese deployment. Use them to locate the main areas; values vary by deployment and selected time range. ## Access and Entry | Item | Guidance | | ---------------- | ------------------------------------------------------------------------------------------------------------------------ | | Entry | Open the AIvis admin console and go to `/admin/dashboard`. | | Required access | The page is restricted to administrators with full admin-panel access. | | Primary audience | Executives, operations owners, AI platform administrators, and authorized auditors. | | Data boundary | The dashboard is aggregated for oversight. It is not a substitute for per-request audit trails or access-control review. | ## What the Dashboard Shows | Area | What it answers | | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Adoption overview | How many eligible users were active and what share of the organization used AI in the selected period. | | Verified AI outcomes | How many AI questions were answered, Agent tasks completed, and automation runs succeeded. | | Activity trend | Daily successful AI outcomes, split across questions, Agent tasks, and automation runs. | | Model usage | Model calls, success and failure counts, effective tokens, measured cost, token coverage, and pricing coverage. | | Feedback quality | Positive and negative rated responses, feedback coverage, positive rate, and whether the sample is large enough. | | Top capabilities | Which AI capabilities produced the most completed outcomes and how many unique users used them. | | Top Agents | Which Agents completed the most interaction or automation outcomes. | | Active users | Which users were active, when they were last active, and how their activity is distributed. | | Needs attention | Failed or cancelled Agent tasks, failed or skipped automation runs, partial outcome coverage, low feedback sample size, incomplete token coverage, or incomplete pricing coverage. | ## Select a Time Range The dashboard supports preset ranges for the last 7, 30, or 90 days, plus a custom date range. Custom ranges are interpreted in the browser's selected timezone and must cover no more than 366 calendar days. The page writes the selected range into the URL query string: | Query parameter | Meaning | | --------------- | ------------------------------------------------------- | | `range` | `7`, `30`, `90`, or `custom`. | | `start` | ISO datetime for the inclusive start of a custom range. | | `end` | ISO datetime for the exclusive end of a custom range. | | `timezone` | IANA timezone used for date boundaries and display. | The dashboard refreshes automatically while the page is visible and also provides a manual refresh button. During refresh, existing data remains visible while newer data loads. ## Read the Numbers Correctly | Signal | How to interpret it | | -------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | `Updated` time | The latest generated timestamp returned by one of the dashboard sections. | | Previous-period comparison | Hidden or marked unavailable when the previous period is outside tracked coverage. | | Partial outcome coverage | The selected range includes time before AI outcome tracking fully started, so totals may be incomplete. | | Token coverage | Some model calls may not report token metadata. Treat token totals as measured coverage, not guaranteed complete usage. | | Pricing coverage | Some calls may not have a known price. Unpriced calls are not zero-cost; they are missing priced coverage. | | Feedback sample | Feedback quality needs at least 5 rated responses before the sample is treated as sufficient. | ## Drill Down | From the dashboard | Follow-up page | | ---------------------------------------- | ------------------------------------------------------------------------------------------------------- | | Detailed model usage | Open [Usage Statistics](/aivis/governance/usage). Some deployments expose this only on eligible tiers. | | Response quality and individual feedback | Open [Query History](/aivis/governance/query-history) when query history is enabled for administrators. | | Top Agents | Open [Agents](/aivis/agents/agents) to review ownership, configuration, and sharing scope. | | Active users | Open [Users, Groups & Roles](/aivis/governance/users-and-groups) to review access and group boundaries. | ## Backend Sections The page loads independent dashboard sections. If one section fails, the rest of the dashboard can still render and the failed card can be retried. | Section | Backend route | | ---------------- | ------------------------------------- | | Overview | `/api/admin/dashboard/overview` | | Activity trend | `/api/admin/dashboard/activity-trend` | | Feedback | `/api/admin/dashboard/feedback` | | Top capabilities | `/api/admin/dashboard/capabilities` | | Top Agents | `/api/admin/dashboard/agents` | | Active users | `/api/admin/dashboard/users` | | LLM usage | `/api/admin/dashboard/llm-usage` | ## Verification * Sign in with an administrator account and open `/admin/dashboard`. * Switch between last 7, 30, and 90 days and confirm the URL and dashboard values update. * Apply a custom range and confirm invalid ranges over 366 days are rejected. * Use the manual refresh button and confirm existing content remains visible during refresh. * Compare totals with [Usage Statistics](/aivis/governance/usage), [Tracing](/aivis/governance/tracing), or [Query History](/aivis/governance/query-history) for a known test request. * Use a non-admin account and confirm the page and API routes are not accessible. ## Troubleshooting | Symptom | Priority checks | | ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | Dashboard is inaccessible | Confirm the user has full admin-panel access and is in the correct deployment or workspace. | | A card shows unavailable data | Retry that section, then check the corresponding backend route and database metric query. Other cards may still be current. | | Previous comparison is unavailable | The previous period may fall before tracking started or outside available coverage. | | Token or cost totals look low | Check token coverage and pricing coverage before treating the displayed totals as complete. | | Feedback quality is unavailable | Confirm query history and feedback collection are enabled, and that at least 5 rated responses exist in the selected period. | | Activity is lower than expected | Check the selected timezone, time range, and whether upstream bot, Agent, or automation requests reached AIvis successfully. | ## Security and Maintenance * Treat dashboard access as administrative access because it reveals user activity, Agent performance, model usage, and cost patterns. * Do not export or share active-user rankings outside approved operational and audit channels. * Review dashboard data after enabling new Agent, bot, automation, model, or tracing paths. * Use attention items as operational signals, then investigate the underlying requests in tracing or query history. * Record known coverage gaps when rolling out the dashboard to an existing deployment. ## Related Pages * [Admin Panel & Roles](/aivis/admin-panel-and-roles) * [Usage Statistics](/aivis/governance/usage) * [Tracing](/aivis/governance/tracing) * [Query History](/aivis/governance/query-history)