I have 3+ years of experience building advanced automation and AI-driven workflows using n8n, including API integrations, webhook-based systems, and designing scalable agent-like workflows with structured logic and external tool interactions.
I’ve worked on building modular workflows for CRM, lead management, and automation systems, and I’m comfortable designing flows that connect prompts, actions, and external services in a reliable way.
I’m also a top supporter of the n8n community and enjoy working on systems that sit at the intersection of AI agents and automation infrastructure.
I’d love to contribute and help shape the n8n integration layer for Feros.
Voice AI + n8n workflow orchestration is my core stack — I’ve shipped a production voice agent for a healthcare client that handles real inbound patient calls, manages appointment scheduling, answers FAQs, and routes complex cases to human staff. Live, handling real callers daily. More on this and other projects: priyanshukumar.co
On the workflow orchestration side: I’ve built a multi-agent system where an orchestrator routes tasks to specialist agents based on intent classification, each agent has access to specific tool sets (web search, database queries, code execution, browser automation), and results flow through a QA review before delivery.
The Feros architecture — reusable workflow templates for CRM/scheduling/lead capture, agent flow across prompts, tool calls, and evaluation loops — maps almost exactly to what I’ve already built and deployed.
Stack: Python, n8n, Claude API, Supabase, FastAPI, Docker. Comfortable with TypeScript/React for frontend components.
Would love to contribute — happy to start with a specific workflow template (e.g., the CRM/scheduling integration) and expand from there.
Hey - n8n workflow orchestration + AI agent design + Python + API integrations is basically my job description.
What I bring to this:
4 production n8n workflows running right now - lead intelligence with 3 sequential AI calls and priority routing, customer support bot with ticket classification, competitive intelligence monitor, multi-API research pipeline. All with proper error handling, not happy-path demos
Self-hosted n8n on Docker with Postgres - I manage the full stack myself including cron, monitoring, and credential management
Python scripts alongside n8n for tasks where visual nodes aren’t the right tool
OAuth and API auth - I’ve integrated REST APIs with various auth methods (API keys, OAuth tokens, webhook signatures) many times in n8n
Webhook design - my workflows use webhooks as both triggers and response endpoints, including async patterns where you return immediately and process in background
For the specific work you described:
Reusable workflow templates for CRM/scheduling/lead capture - I’ve built these exact patterns already. Happy to contribute them as starting points
Agent flow across prompts, tool calls, and evaluation loops - my Lead Intelligence workflow chains 3 AI calls where each one depends on the previous output, with validation between steps. Same architectural pattern your voice agents would need
Integration layer design - I think about n8n workflows as APIs themselves, not just internal glue. Clean inputs, documented outputs, versioned configs
No TypeScript/React or Rust experience, being honest. But the core ask here is n8n + AI workflows + Python + integrations, and that’s where I’m strong.
Hi. I can help on the n8n/workflow layer for this: agent graph triggers, webhook contracts, credential boundaries, debug paths, and testable workflow templates.
I would start with one paid technical slice around one voice-agent workflow and its failure cases, so the open-source direction stays usable and maintainable.
This is close to the workflow/agent work I focus on: self-hosted automation that connects real tools, keeps state/logs visible, and is documented well enough to maintain.
Where I can help:
n8n workflows with webhooks, API calls, function/code nodes, retries and error paths
LLM/agent steps with structured outputs rather than loose text
workflow QA for voice-agent style systems: test payloads, fallback paths, handoff notes
OpenClaw/Codex-style agent setup where approval gates and run logs matter
I would suggest a small paid trial first: one voice-agent workflow slice from trigger → context/tool lookup → structured response/action → logging/error handling. That gives you something concrete to judge before broader OS work.