> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flowra.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Workflows in the dashboard

> Create, configure, run, and debug agents and static workflows in the Flowra dashboard — every main editor surface.

**Workflows & Agents** is where you invent, configure, and operate automations for the active **project** and **end user**. Confirm both switchers if something is missing — see [External users switcher](/product/external-users) and [Projects and API keys](/product/projects-and-keys).

Open [Workflows](https://flowra.dev/dashboard/workflows).

## Agent vs workflow

The product uses the same list for both. The help popover defines them as:

| Kind                  | Best for                           | How it behaves                                    |
| --------------------- | ---------------------------------- | ------------------------------------------------- |
| **Agent**             | Open-ended tasks and conversations | Chat assistant that decides which tools to use    |
| **Workflow** (static) | Paths you know in advance          | Fixed sequence of steps (tools, logic, schedules) |

Tip from the UI: if you are unsure, **start with an Agent** — you can add structure later. Conceptual detail: [How Flowra works](/product/how-flowra-works). Developer model: [Workflows and agents](/guides/workflows-and-agents).

***

## List page

### Header actions

* **Create Agent** — blank agent for the end user selected in the top bar
* **Create by AI** — opens Chat with a helper; you still review and save in the editor
* **Executions** — global run history
* **Widgets** — embed chat widgets for agents

There is no separate blank **Create Workflow** button on the list. Static workflows usually come from **Create by AI**, [Marketplace](/product/marketplace) clone, or other guided paths.

### Filters

* Search
* Status: **All** / **Active** / **Inactive**
* Type tabs: **All** | **Workflow** (fixed step-by-step) | **Agent** (conversational)

### Cards

Each card opens the editor and typically shows:

* Type badge (**Agent** or **Workflow**) and version when present
* Active switch (activate / deactivate)
* Description (or empty placeholder)
* **Trigger** row — agents always show **Chat**, plus schedule or channel badges when configured; static with no triggers shows **Manual**
* **Last run**, **Runs** count, toolkit avatars

**Card menu** (varies by type):

| Action              | Notes                                          |
| ------------------- | ---------------------------------------------- |
| **View flow**       | Open editor                                    |
| **Full statistics** | Health, credits, tools, logs                   |
| **Chat**            | Agents only — open Chat with this agent        |
| **Create widget**   | Agents only — creates an embed, then customize |
| **Delete**          | Confirm; cannot be undone                      |

If your plan is over the agents/workflows limit, create and edit may show **Plan limit reached** / **Editing locked** with a path to change plan.

***

## Create an agent

Path: [Create Agent](https://flowra.dev/dashboard/workflows/create) (or **Create Agent** on the list).

The form uses the **same settings stack** as the editor (see below). Workspace is set from the current project; the agent is created for the **selected end user**.

* Left: settings cards
* Right: live **Flow visualization** preview
* Submit: **Create Agent**

Unsaved changes prompt when you leave. Prefer a small tool set from the start.

***

## Edit an agent

Open an agent from the list. Header shows type, version, name, description, optional **Sub-agents** chips, and an **Active** switch when you can edit.

Primary actions often include **Edit with AI**, **Save Agent**, and **Chat** / **Chat with Agent**. Menu may offer **Add to marketplace** / **Remove from marketplace**.

### Performance

Left column **Performance**: runs, success rate, last run, link to **Full statistics**. If there are errors, the UI may offer **Fix errors with AI**.

### Agent settings (left column)

Cards appear in this order:

#### 1. Basic info

* **Name**, optional **Description**
* **Starter prompts** (quick replies in chat / widgets; capped in the UI)
* **Avatar** (upload / change / remove)
* **Public** (when your role allows) — let other projects use this agent in their chat

#### 2. Agent intelligence

* **System instructions**
* Model picker
* **Temperature**, **Max tokens**
* **Advanced** sampling (frequency/presence/repetition penalties, seed, stop sequences, and related options)

#### 3. Tools

Pick what the agent is allowed to do. Open **Select Tools** (toolkits and MCP). Prefer a small set — the product may warn when too many tools are pinned. Account hints point to **Your accounts for testing** below. Full catalog: [Toolkits and tools](/product/toolkits-and-tools).

Select Tools modal (summary):

* Tabs **Toolkits** | **MCP**
* Normal pin vs Meta / discovery modes when offered
* Our MCP servers or an external MCP URL
* Apply selections back to the agent

#### 4. Entry points

**Channels and triggers that start this agent.** Full guide: [Entry points and channels](/product/entry-points-and-channels).

* **Dashboard chat** — always on
* **Add entry point** → Messaging (two-way reply), Schedule (one schedule per agent; no chat auto-reply), or Events (one-way wake)
* Security copy in UI: replies use your **connected account**; anyone who can message that channel can wake the agent

#### 5. Skills

Attach playbooks with **Select Skills**. Skills guide behavior; they do not automatically add tools. Full guide: [Skills](/product/skills).

#### 6. Data access

Tick **Knowledge collections** and **Tables (database collections)** this agent may use. Search tools for those collections are added automatically when the agent runs.

For tables exposed to end users, the UI offers access-style presets (for example private per user, shared read-only, submit only) and row/column controls. Create collections first under [Database](/product/data/database) and [Knowledge](/product/data/knowledge).

#### 7. Output schema

Optional structured fields for the agent’s final answer.

#### 8. Capabilities (limits and safety)

Common toggles (names follow the UI):

* **Computer Agent** (may warn about credits)
* **Long-term memory** (often requires Computer Agent)
* **Conversation summarization**
* **Retry on tool errors**
* **Human approval for sensitive actions**
* **Tool selector**, **Model fallback**
* **Model call limit** / **Tool call limit**

#### 9. Sub-agents

When Computer Agent (or related capability) allows it, attach child agents with coordinator / webhook behavior as the UI describes. There is a max count.

#### 10. Token and cost estimate

Rough scenarios (first turn, typical chat, long thread, custom) — estimates only.

### Your accounts for testing

Card **Your accounts for testing** (agents) or **Your accounts for this workflow** (static):

* Shows **Testing as** / **Running as** the current end user or project default
* Connect or change toolkit accounts
* Copy: connections are **only for you**; other people must connect their own accounts

See [Connections](/product/connections).

### Flow visualization (right)

**Flow visualization** shows nodes and edges for the current configuration (chat, channels, tools, skills, knowledge, computer agent, and related nodes). On agents this is largely a live preview of what you configured.

***

## Edit a static workflow

Open a **Workflow** card. Shared pieces: Performance, accounts, marketplace actions, statistics, executions.

### What differs from agents

| Surface             | Static workflow                                                                                             |
| ------------------- | ----------------------------------------------------------------------------------------------------------- |
| Primary run control | **Run** / **Run Workflow** (not Chat-first)                                                                 |
| Schedule            | Left **Schedule** card — how often it runs + **Save schedule** (agents usually put cron under Entry points) |
| Input parameters    | **Input parameters** schema + **Save input defaults** when the graph defines inputs                         |
| Graph               | Primary editable flow of steps                                                                              |
| LLM inside a step   | Click an LLM / AI node → **Edit LLM step**: step intelligence, tools, data access for **that step only**    |
| Entry points        | Manual, schedule, and event/trigger-tool style starts; messaging auto-reply is an agent-oriented pattern    |

Save with **Save inputs** when you are editing input defaults. Use **Run** to execute; use Production vs Test modes where the product offers them (test can mock tools depending on configuration).

***

## Test and run

| Goal                   | How                                                                                                 |
| ---------------------- | --------------------------------------------------------------------------------------------------- |
| Talk to an agent       | **Chat** from the card/editor, or [Chat](https://flowra.dev/dashboard/chat) with the agent selected |
| Fire a static workflow | **Run** on the workflow                                                                             |
| Unattended             | Entry points / [Triggers](/product/triggers-in-dashboard)                                           |
| Customer site          | [Widgets](/product/widgets-and-embeds) from an agent                                                |

If a run pauses for approval, open the execution and use **Approve** / **Reject** (or resume flows the UI shows). Developer detail: [Human in the loop](/guides/human-in-the-loop).

***

## Executions

### Global list

[Workflow Executions](https://flowra.dev/dashboard/workflows/executions)

Filter by status (Running, Paused, Completed, Failed, Timeout), flow type (Agent / Static), and mode (Production / Test). Columns typically include execution id, workflow, status, type, mode, triggered by (**Me** / **External user**), progress, started, duration.

### Execution detail

Open a row for:

* Run information (started, completed, duration, mode, triggered by)
* Progress (completed / failed / total nodes)
* Errors per node
* Input / output data
* Resume when paused

Also use [Tool execution logs](https://flowra.dev/dashboard/tool-execution-logs) for tool-level I/O.

***

## Statistics

From a card or editor: **Full statistics** → `/dashboard/workflows/[id]/statistics`.

Typical sections: run health, credits, tools, models, triggers, logs — with date range and Test/Production filters. Use this for debugging cost and failure patterns, not only single-run detail.

***

## Widgets (agents)

From the list header **Widgets**, or **Create widget** on an agent card.

* Widgets are for **agent** workflows in the project
* After create, customize **Design**, **Chat**, and **Thread** (bubble/fullscreen, colors, uploads, quick replies, thread persistence)
* Starter prompts come from the agent’s Basic info

Full product guide: [Widgets and embeds](/product/widgets-and-embeds).

***

## Marketplace

From the editor you can **Add to marketplace** or **Remove from marketplace**. When viewing a marketplace listing, **Clone for me** copies into your project under the current end user — then reconnect accounts and review tools. See [Marketplace](/product/marketplace).

***

## Related

* [First agent in chat](/product/first-agent-in-chat)
* [Entry points and channels](/product/entry-points-and-channels)
* [Connections](/product/connections)
* [Database](/product/data/database)
* [Knowledge](/product/data/knowledge)
* [Files](/product/data/files)
* [Triggers in the dashboard](/product/triggers-in-dashboard)
* [Widgets and embeds](/product/widgets-and-embeds)
* [Workflows and agents](/guides/workflows-and-agents) (developers)
* [Workflows API](/guides/workflows)