Contact Us
AI Automation

AI Automation & Agentic Workflows

We built our own workflow engine. IronFlow is a Rust-native, DAG-based orchestration engine with 96 built-in nodes that ships as a single binary — no Python, no Docker, no dependency hell. Pair it with IronCrew for multi-agent reasoning and TinyCrew for web-integrated agent workflows. When your team can't use n8n or Dify, we have the alternative.

Our Automation Toolchain

Three in-house Rust and TypeScript tools for workflow orchestration, multi-agent reasoning, and enterprise integration.

IronFlow

In-house — Rust Workflow Engine

DAG-based workflow orchestration with 96 built-in nodes — HTTP, files, S3, databases (SQLite, ArangoDB), AI embeddings/chunking/chat, MCP client, document extraction, image processing, email/Slack notifications, and more. Define workflows in Lua scripts, execute on a sandboxed async Rust runtime. Parallel step execution, retry with exponential backoff, conditional routing, subworkflow composition, and a built-in REST API. Single binary, zero dependencies, runs anywhere including air-gapped environments.

IronCrew

In-house — Rust Multi-Agent Runtime

When workflows need reasoning, not just sequencing. IronCrew orchestrates multiple AI agents with dependency graphs, agent-to-agent messaging, shared memory with TTL and relevance scoring, collaborative discussions, and structured JSON output. Define agents and tasks in Lua, execute as a single binary. Provider-agnostic — OpenAI, Groq, Ollama, Azure.

TinyCrew

In-house — TypeScript Multi-Agent Framework

Bun-native agent orchestration for web applications and APIs. Shared memory, structured output via Zod schemas, multi-model routing for cost optimization, agent-to-agent messaging, conversation history with auto-summarization, and response streaming. When your automation lives inside a web service, not a CLI.

What We Automate

Concrete workflows we build and deploy — not theoretical capabilities.

Document Processing

  • Invoice extraction, validation, and approval routing
  • Contract analysis — clause identification, risk flagging
  • Email triage — categorize, prioritize, draft responses
  • Report generation from live data sources
  • PDF/DOCX/PPTX extraction via Cognitive-OCR

Business Processes

  • Customer onboarding — document verification, account setup
  • Support ticket routing — intent classification, agent matching
  • Compliance monitoring — policy checks, audit trail generation
  • Data enrichment — entity resolution, quality scoring
  • Webhook-triggered workflows for real-time events

Development & DevOps

  • CI/CD pipeline automation via IronFlow
  • Code review and security scanning workflows
  • Documentation generation from source code
  • Test generation from specifications
  • Infrastructure provisioning and deployment

MCP & Tool Integration

Anthropic's Model Context Protocol is our preferred standard for connecting AI to external systems. IronFlow includes a native MCP client node.

What MCP Enables

  • Resource access — files, databases, APIs as context for LLMs
  • Tool invocation — execute functions with structured input/output
  • Prompt templates — reusable interaction patterns
  • Nested LLM calls within tools (sampling)

Our MCP Experience

  • PLU Finder MCP server — production at mcp.plufinder.com
  • IronFlow mcp_client node for workflow integration
  • Claude Code skills and custom tool development
  • Custom MCP servers for enterprise system integration

Also Works With

When the project calls for existing platforms instead of our toolchain.

Visual Workflow Platforms

  • n8n — visual workflow builder with AI nodes
  • Dify — LLM application development platform
  • Temporal — durable workflow execution
  • Apache Airflow — DAG-based data orchestration

Agent Frameworks

  • CrewAI — role-based agent collaboration
  • LangGraph — stateful, cyclic agent workflows
  • Semantic Kernel — Microsoft's AI orchestration SDK
  • AutoGen — Microsoft's multi-agent framework

Proven Implementations

Production deployments and real IronFlow pipeline patterns.

WolfGPT

WOLF GmbH — Multi-Tool Enterprise Assistant

Intent analysis with dynamic routing, multi-LLM fallback chains, tool-calling for data processing, and complex document workflows. 2.5+ years in production handling real enterprise workloads daily.

Vidifo

In-house — Visual Digital Forensics Automation

Multi-LLM video and image analysis pipelines for law enforcement. Automated content classification, threat detection, and evidence flagging with cryptographically verifiable processing chains. Edge-based execution on standard mobile hardware — no cloud upload of sensitive footage required.

RAG Ingestion Pipelines

IronFlow — Document → Vectors → Search

End-to-end pipelines in a single Lua script: extract content from VTT/PDF/DOCX, chunk with configurable strategies, embed via OpenAI or Ollama, store in S3 Vectors or ArangoDB, then query with semantic similarity and metadata filtering. Full chunk → embed → store → query cycle with parallel step execution.

Transcript Analysis Workflows

IronFlow — VTT → Sentiment → Insights

Extract interview transcripts, run sentiment analysis via multi-provider LLM calls (OpenAI, Azure, OAuth endpoints), normalize results across response formats, and generate per-speaker sentiment reports. Handles OAuth token exchange, provider-agnostic chat completions, and structured JSON output in a single automated flow.

Ready to automate with tools we built ourselves?

Contact us to discuss how IronFlow, IronCrew, and our multi-agent frameworks can automate your workflows — from simple data pipelines to complex agentic systems.

Get in Touch