- Home
- Skills
- Agents & Orchestration
- flowx workflows
More screenshots
Works with the AI Agents you already use
flowx workflows
FlowX lets AI agents build, run, and evolve workflows
$3
flowx workflows
Example session with this skill installed
Use the FlowX workflows skill to build a support-ticket assistant. It should accept a ticket, classify its topic and urgency, draft a helpful reply, and ask a human to approve or revise the draft. Do not send emails or contact external systems.
If a node test fails, show me the failure and ask for guidance before continuing. Once the build is complete, review the generated code, start the service on localhost, and give me the workflow details and next steps.
- Read your context and instructions
- Compiled the flowx workflows
Build summary
Your support-ticket workflow is built and its service is ready.
Workflow ID: a6b93c1e02d84f2eb5a3c6874f907b12
Build: Completed successfully
Service: Ready at http://127.0.0.1:8000
Session: support-demo-session
External actions: The workflow does not send emails or call external business systems.
Delivered workflow
Step Purpose Output
receive_ticket Accept the customer’s ticket and validate that it is not empty. Validated ticket text
classify_ticket Identify the topic and assign an urgency level. Category and urgency
draft_reply Prepare a response using the ticket and classification. Reply draft
review_reply Ask a human to approve the draft or provide revisions. Approved or revised reply
Build review
Graph, node, and entrypoint generation completed.
The generated node tests passed after one guided repair. During the build, the empty-ticket test failed; you asked the agent to reject blank input with a clear validation message. The node was amended and retested.
The final audit reported no remaining violations. This is not a security certification.
The generated code was reviewed before service startup. The optional entrypoint smoke test was not run.
The requirements, graph, node implementations and tests, and service entrypoint are available in the workflow workspace.
Next steps
Send a sample ticket to receive_ticket.
Review the classification and draft when the workflow reaches review_reply.
Approve the draft or provide a revision; the workflow will not send it externally.
Keep the runtime session open while using the service. Ask the agent to stop it when finished.
Connects securely to your tools. The creator never sees your data.
About this skill
FlowX lets AI agents build, run, and evolve workflows through MCP, a Python SDK, or A2A. Describe a process and FlowX generates a workflow graph, audited and tested Python nodes, and a FastAPI backend.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 8 days ago
Requires
Permissions
Allowed Hosts