# Flows AI Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/flows-ai
> Markdown URL: https://aitinkerers.org/technologies/flows-ai.md
> Technology record last updated: 2026-04-12T02:07:28Z
> Generated: 2026-09-21T18:35:24Z

FlowAI: The no-code platform for building, managing, and automating powerful AI workflows and intelligent agents.

FlowAI is your enterprise-grade platform for AI workflow and agent construction. It simplifies complex automation: Users build intelligent systems fast, leveraging an intuitive, no-code interface. The platform supports multiple Large Language Models (LLMs), including GPT-4o and DeepSeek, ensuring flexibility and power. FlowAI agents handle multi-step reasoning and autonomous tool invocation (e.g., web scraping, API calls), driving efficiency. Over 10,000 AI workflows have already been created, proving its scalability and real-world utility for automating repetitive tasks and boosting team output.

- Official technology site: https://flowai.cc
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building agentic workflows with Vercel AI SDK](https://poland.aitinkerers.org/talks/rsvp_y4NEWHRlO6Q)

Flows AI is a light-weight library written in TypeScript for orchestrating AI agents. Unlike most of the frameworks for building and scheduling agents, it does not propose its own interface. Instead, it builds on top of Vercel AI SDK, letting you re-use your existing knowledge and focusing on the most important aspect of it - orchestration. In our system, agent is a simple pure function. What you do inside of it, is up to you. You can call an LLM using Vercel AI SDK or execute local function. Each agent takes an input, which can either be the task to perform, or another agent. That allows infinite nesting of multiple different agents, and executing variety of different flows, such as sequence or parallelism. While the library itself has very minimal interface, we provide a bunch of out-of-the-box agents for most popular patterns, as described by Anthropic in their latest article on agents, released in December. In this short demo, I will show you how you can build and compose multiple AI workflows together, using both LLM and local function calling to achieve desired results.

- Event context: AI Tinkerers Poland - Second Meetup in Warsaw (January) — 2025-01-30 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_y4NEWHRlO6Q

## Related Technologies

- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Vercel AI SDK](https://aitinkerers.org/technologies/vercel-ai-sdk) ([Markdown](https://aitinkerers.org/technologies/vercel-ai-sdk.md)) — 32 public demos