Skip to main content
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 and Projects and API keys. Open Workflows.

Agent vs workflow

The product uses the same list for both. The help popover defines them as: Tip from the UI: if you are unsure, start with an Agent — you can add structure later. Conceptual detail: How Flowra works. Developer model: 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 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): 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 (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. 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.
  • 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.

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 and 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.

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

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

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.

Executions

Global list

Workflow 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 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.

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.