Workflow Designer

AI

Workflow Name

Requirements

Quick start: paste requirements above, pick a preset below, copy the prompt. Refine Prompt (optional): generates an interview prompt - run it in Claude Code, then paste the refined spec back into Requirements replacing the original.

Implementation Plan optional

Optional: click Plan Prompt to create a planning prompt - run it in Claude Code and paste the result into Implementation Plan. Best used after refining your requirements. Or paste a plan from /plan mode directly.

Default Model

Opus 4.6
New nodes, presets, and generated workflows will use this model.

Repositories (optional)

Repos this workflow touches. Agents will check out the branch and pull latest before starting.

Add Nodes

Agent
Task
Decision
Parallel
Input
Output

Quick Patterns

Presets

Feature Development
Plan → Implement → Review → Test
Bug Fix
Investigate → Fix → Test → Verify
Full Stack Feature
Design → [Backend | Frontend] → Test
UI Design & Development
Analyze Design System → Implement → Review
Refactoring
Analyze → Refactor → Review → Test
Documentation
Research → Write Docs → Review
More presets…
DevOps / Infrastructure
Plan → Implement → Review → Test
Performance Optimization
Profile → Optimize → Review → Test
Data Migration
Research → Migrate → Review → Test
Testing
Analyze → Write Tests → Review → Verify
Test Automation
Plan + Explore App → [Feature | Screens | Steps] → Review
Code Review
Analyze → Review → Improve → Validate
Parallel Research
[Codebase | Docs | Patterns] → Synthesize
Agent Swarm
[Security | Quality | Performance | Architecture] → Report

Saved Workflows

No saved workflows yet
⚡ Better outcomes: agents work best when an Atlassian MCP tool, Datadog MCP, and a language-appropriate LSP server are installed, authenticated, and available. Setup instructions...
Atlassian MCP setup:
claude mcp add --transport http atlassian https://mcp.atlassian.com/v1/mcp --scope user

Datadog MCP setup:
curl -sSL https://coterm.datadoghq.com/mcp-cli/install.sh | bash
then datadog_mcp_cli login and claude mcp add -s user datadog -- ~/.local/bin/datadog_mcp_cli --endpoint-path "/api/unstable/mcp-server/mcp?toolsets=core,alerting,apm"

PR creation: GitHub repos use gh CLI (built-in). Bitbucket repos can use the same Atlassian MCP above. GitLab repos need glab CLI or a GitLab MCP.

MCP Integrations prompt hints

Memory Protocol

100%
🏗

Paste requirements and click Generate, choose a preset, or add nodes manually.

1 Select   2 Connect   3 Delete   Alt+Drag Pan   Scroll Zoom

Add nodes and connections to see your workflow output here...
Duplicate
Disconnect All
Delete
Copied to clipboard!

Workflow Designer Help

Quick Start

  1. Paste requirements into the Requirements field (or a Jira ticket URL)
  2. Click Generate to auto-build a workflow from keywords, or pick a Preset below
  3. Customize nodes by clicking them: change agent types, models, prompts, and tools
  4. Pick an export format tab at the bottom, then Copy the prompt into Claude Code

Refine Prompt Flow

Use this when your requirements are rough or incomplete and you want Claude to interview you before building.

Paste requirements → click Refine Prompt → copy into Claude Code → Claude asks clarifying questions via interview → writes refined spec to .claude/specs/ → paste refined spec back into Requirements → Generate or pick preset

Plan Prompt Flow

Use this after you have solid requirements and want Claude to analyze your codebase before implementing.

Requirements ready → click Plan Prompt → copy into Claude Code → Claude explores your codebase (files, patterns, architecture) → writes implementation plan to .claude/plans/ → paste plan into Implementation Plan field → plan context is included in all exported prompts

Full Flow (Power Users)

For maximum quality, chain all three steps:

1. Paste rough requirements → Refine Prompt → interview → refined spec 2. Paste refined spec → Plan Prompt → codebase analysis → implementation plan 3. Paste plan → build workflow → Copy prompt → execute in Claude Code

Jira Integration

Paste a full Jira URL (not just the ticket key) and enable Atlassian MCP in the sidebar. The exported prompts will instruct agents to fetch ticket details at runtime. For URL-only input, you'll be asked to pick a workflow preset since there aren't enough keywords to auto-generate.

Export Formats

  • Workflow: Single orchestration prompt for Claude Code. Best for most use cases.
  • Sub-Agents: Delegation prompt using Claude Code's /spawn sub-agent pattern.
  • Agent Teams: Multi-agent team coordination prompt. Preview.
  • Agent SDK: Python code using the Anthropic Agent SDK. Wire into your own pipeline.
  • Claude.ai: Simplified prompt for use in Claude.ai (no CLI tools).

Canvas Tips

  • Ctrl+Z / Cmd+Z: Undo (also available as toolbar buttons)
  • Ctrl+Shift+Z / Cmd+Shift+Z: Redo
  • 1 2 3: Switch between Select, Connect, and Delete modes
  • Delete / Backspace: Delete selected node or connection
  • Alt+Drag: Pan the canvas
  • Scroll: Zoom in/out
  • Right-click a node for context menu (duplicate, disconnect, delete)
  • Auto Layout re-arranges nodes using the Sugiyama layered algorithm
  • Fit zooms to show all nodes

Toolbar Features

  • Undo / Redo buttons (or keyboard shortcuts) let you reverse adding, deleting, connecting, disconnecting, and dragging nodes. 50-step history.
  • Validation indicator shows a green check or amber warning count. Click it to see issues like disconnected nodes, empty prompts, or incomplete decision gates.
  • Token estimate appears next to the Copy button showing the approximate size of the generated prompt.
  • Clone button in Saved Workflows duplicates the current workflow under a new name for creating variants.

Prompt Library

Click the Prompts button in the toolbar for a library of ready-to-use prompts. Use the search box to filter by title or description. Star your favorites and they float to the top. Prompts that need your input (like a file path or bug description) show a popup before copying so the prompt is ready to paste.

Prompts that benefit from cross-repo search or Jira/Confluence context include guidance for using those tools when available.

The Live Monitors category contains prompts that watch things for you over time: CI builds, PR reviews, deploys, incidents. They run on a recurring interval, track changes across iterations, and self-terminate when done (build goes green, PR merges, service recovers).

Recommended Integrations

These optional MCP servers and tools unlock better results from both workflows and prompt library prompts:

  • Atlassian MCP: built into Claude Code. Lets agents fetch Jira tickets and Confluence pages at runtime. Toggle on/off in the sidebar.
  • Sourcebot MCP: self-hosted cross-repo code search (sourcebot.dev). Enables search_code, ask_codebase, read_file, list_tree across all your repos.
  • Datadog MCP: install with curl -sSL https://coterm.datadoghq.com/mcp-cli/install.sh | bash, then datadog_mcp_cli login, then claude mcp add -s user datadog. Enables the Observability prompts in the Prompt Library. Bug Fix workflows also use it automatically to check production logs and error context during investigation.
  • LSP: install a language server for your stack (e.g. typescript-language-server, pyright, gopls). Gives agents go-to-definition and find-references for deeper code analysis.

Power User Tips

  • Enable Shared Memory for complex workflows so agents write to a shared file and later agents can see earlier findings
  • Add Repository paths to scope agents to specific codebases
  • Use Decision nodes with revision loops to add quality gates (review / revise cycles)
  • Parallel groups run agents concurrently, great for independent tasks like "backend + frontend"
  • Each agent's Custom Notes field lets you add context that's included in that agent's prompt section
  • Workflows auto-save to localStorage. Use Save / Load for named snapshots, or Export JSON to share with teammates

Prompt Library