# Shadcn Agents blocks

> AI agent run operation, approval, tool permission, and evaluation pages.

- Type: Pro blocks (Solutions)
- Page: https://web.dev.reui.io/blocks/solutions/agents
- Blocks: 10
- Installs with a ReUI Pro or Ultimate license; setup: https://web.dev.reui.io/docs/license-setup

## When to use

- Run monitoring for a fleet of agents: a live overview, a run queue and failed run triage
- Human review of agent work: an approval inbox, one run's step trace and a nightly evaluation report
- Control pages for agent behavior: tool access, playbooks, run settings and stored memory

## When not to use

- One run narrated live to the person who started it, inside a chat or task view: use the [Agent Activity blocks](https://web.dev.reui.io/blocks/ai-agents/agent-activity.md)
- Model provider routing, prompt reviews, token spend and safety policies for LLM features: use the [AI Ops blocks](https://web.dev.reui.io/blocks/solutions/ai-ops.md)
- An account, workspace, notification or integration page of labeled switches and selects: use the [Settings blocks](https://web.dev.reui.io/blocks/application/settings.md)

## Agent notes

- Every block sets a `min-h-svh` wrapper with its own padding and max width in page.tsx, its root component or both; drop them inside an app shell
- No block mounts the `sonner` toaster, so every `toast` call stays invisible until your layout renders one
- No handler reaches a backend: actions change local `useState` and fire a `toast`, so wire each one to your agent API

## Third-party libraries

- Sonner v2: [API reference](https://sonner.emilkowal.ski/toast), [docs](https://sonner.emilkowal.ski/getting-started), used by 10 of 10 blocks
- TanStack Table v9: [API reference](https://tanstack.com/table/v9/docs/framework/react/reference/index), [docs](https://tanstack.com/table/v9/docs/framework/react/quick-start), used by 7 of 10 blocks
- Recharts v3: [API reference](https://recharts.github.io/en-US/api/), [docs](https://recharts.github.io/en-US/guide/getting-started/), used by 2 of 10 blocks
- date-fns v4: [docs](https://date-fns.org/v4.1.0/docs/Getting-Started), used by 1 of 10 blocks
- React DayPicker v9: [API reference](https://daypicker.dev/v9/api), [docs](https://daypicker.dev/v9/start), used by 1 of 10 blocks

## Blocks

- [Agent Fleet Overview](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-1.md): AI Agent Operations Dashboard with Run Queue, Throughput Chart and Incident Timeline. Best for the fleet overview: 4 summary cards, run throughput by period, an incident timeline and a run queue sorted by latency.
- [Agent Run Queue](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-2.md): Agent Run Queue with Collapsible Status Groups and Attention Filters. Best for runs folded into status groups with Escalated, Needs approval and Unassigned counters, owner avatar stacks and step progress rings.
- [Run Step Trace](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-3.md): Agent Run Detail with Inline Step Trace and Editable Settings Panel. Best for a single failed run: a step trace with tool call latency, a Retry Step alert on the failing step and settings edited row by row.
- [Tool Access Matrix](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-4.md): Agent Tool Access Matrix with Approval Routing and Run Policies. Best for auto Run, Approval and Blocked checkbox columns per tool, a rate limit format check that blocks Save and an approver team per row.
- [Action Approval Inbox](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-5.md): Agent Action Approval Inbox with Risk-Tiered Queue and Bulk Approve or Reject. Best for time left against a 4h SLA per request, bulk approve or reject, a required reject reason and the most urgent request opened in a sheet.
- [Playbook Builder](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-6.md): Agent Playbook Builder Wizard with Live Summary Card and Tool Allowlist. Best for a 5 step build whose stepper jumps to the first invalid step, a confirm before removing a condition and a warning on a refund tool.
- [Failed Run Triage](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-7.md): Failed Agent Run Triage Board with Detail Sheet and Retry Ladder. Best for failed runs with a sheet open on the first row, Error, Attempts and Payload tabs, and Retry or Dismiss written back to the row.
- [Agent Eval Report](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-8.md): Agent Evaluation Report with Pass Rate Trend and Release Markers. Best for per case scores for a baseline and a current release, release markers on the nightly trend, expandable case notes and a regressions switch.
- [Agent Memory](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-9.md): Agent memory manager with scope rail and confidence-scored entries grid. Best for facts browsed by a scope rail with counts and retention, confidence bars per entry, pin to top and a forget action.
- [Agent Run Settings](https://web.dev.reui.io/blocks/solutions/agents/solution-agents-10.md): Agent run-configuration settings form with picker, validated timeout, and locked policy row. Best for one agent at a time from a picker that keeps a draft per agent, a 30 to 900 second timeout check and an org locked PII row.

Every ReUI item has a twin like this one; the index is https://web.dev.reui.io/llms.txt. Agents with the ReUI MCP (https://web.dev.reui.io/docs/mcp) get the same guidance from the getters named above.