Today's Deep-Dive: Flowise

Welcome to the deep dive today. We're really getting into something exciting flow

wise. It's an open source platform and honestly

It's changing the game for building AI agents our mission today to show you how

something that sounds super complex is actually becoming well

Surprisingly accessible even if you're not, you know a hardcore AI coder

But hang on before we dive right in a quick shout out to our supporter safe server

dot DE

They're fantastic when it comes to digital transformation

They actually host the software that helps us put together these deep dives for you

So if you're curious about boosting your own digital setup, check them out at www.safeserver.de

Right. So flow wise as I said open source and it lets you build AI agents visually

now when you hear AI agents

Maybe you picture I don't know teams of developers deep and complex code, right?

But the real magic here what flow wise does is it kind of demystifies all that it

makes building these things intuitive really powerful

And honestly something a much wider range of people can actually do that's such a

key point. I mean traditionally

Yeah building AI agents meant you needed serious technical chops coding machine

learning frameworks the whole deal

What's so fascinating about flow wise is how it just bypasses that whole

intimidating entry barrier

It brings this really advanced capability into a visual space, you know makes it

approachable. It's not just simplifying things

It's genuinely like democratizing access to these powerful AI tools, which is

frankly a massive step forward

Okay, so let's unpack that a bit for anyone who listening is maybe, you know

tangled with complex AI stuff before flow

Why it sounds like a completely different approach. What exactly is it

fundamentally?

And how does it pull off making something so sophisticated feel well easier? Yeah,

good question

So at its heart flow wise is an open source platform specifically for developing

agentic systems

The revolutionary bit is the visual building it uses these modular building blocks

Think of it like like building with high-tech Legos instead of forging metal parts

from scratch

You snap together these pre-built functional modules on a screen to define how your

AI works

It's logic its flow all visual this massively cuts down on the you know

The mental load and the amount of boilerplate code you'd normally have to write and

just to give a sense of its credibility

It's backed by Y Combinator and already being used by teams all over the world.

That says a lot, right?

So it's not just a pretty interface. It's changing how you actually build the thing

Yeah sounds almost like those drag-and-drop website builders that totally changed

web design, but this is for AI

You're arranging pieces to map out complex AI behavior instead of typing endless

lines of code

That definitely sounds like it lets you as developers say iterate fast

Does this visual approach ever feel limiting or can flow wise really handle the

complex stuff? You'd normally code

That's a really fair question and it gets right to the core of how flow wise is

designed. It simplifies

Yes, but crucially it doesn't really sacrifice power or flexibility

The core promise is that you can build everything from say simple workflows where

an AI follows set steps all the way up to fully

Autonomous agents and all through that visual interface

So you're focusing purely on the logic and the flow how the AI should behave

without getting bogged down in the underlying code implementation

And for anyone wondering about getting started

It's incredibly simple like a quick NPM install dash g flow wise and then npx flow

wise start and boom

You're basically up and running that ease of setup is key for rapid prototyping and

the modular design means it's robust enough for complex

Scenarios to it bridges that gap between no code simplicity and code heavy power,

you know

Okay, that makes the barrier to entry almost nothing. So let's get practical. What

can you actually build with this?

What kind of tangible things could our listeners start thinking about for their own

work or projects?

Great. This is where it gets really interesting. You can basically break down what

you build into two main categories

First up, you've got chat assistance

These are probably what most people think of as an AI chatbot

Single agent systems designed for specific interactions, but they're super

versatile

They support things like tool calling which means the AI isn't just talking it can

actually do things like interact with other systems trigger actions

Oh interesting like pull up customer data or book something exactly pull order

history from a CRM book an appointment

maybe even process a simple transaction all based on the chat and

Critically these assistants are great at knowledge retrieval often using this

technique called rag retrieval augmented generation

This means the AI isn't just using its general knowledge

It can intelligently search and pull specific up-to-date info from your own private

data sources before it answers

Ah, so it's like giving it a super focused research assistant for your specific

stuff precisely

It makes the answers not just accurate in general

But highly relevant to your context your company docs latest market reports product

manuals

Whatever and when I say it supports a wide array of data sources

I really mean it it handles almost everything you'd find in a business

Txt files PDFs rtf doc HTML CSS JSON XML CSV markdown

Even direct sequel database chats Wow. Yeah, it's comprehensive

You can feed it pretty much all your relevant info turning all that scatter data

into something that AI can use intelligently

Then you step up to the next level multi agent systems

This is where it gets really powerful and honestly quite transformative instead of

one AI doing everything you orchestrate workflows across multiple

Coordinated agents think of it like building a specialized AI

Okay, how does that work? Well each agent might have a specific role

maybe one agent is great at research another excels at summarizing information a

Third drafts content and maybe a fourth reviews at all. They communicate they

delegate tasks

They collaborate to tackle problems far more complex than any single agent could

manage on its own

This opens the door to automating entire business processes that used to need a lot

of human coordination

Or really complex software integrations that distinction really helps visualize it

Yeah, so just to make sure I'm getting this you could literally build say a

customer service chatbot that answers questions using your entire library of PDF

Manuals and word docs always giving the right info and on the multi-agent side you

could build a team of AIs

Maybe one does market research another analyzes social media sentiment a third

writes a summary report and a fourth even drafts some marketing ideas

That's yeah, that's a whole different level of automation. Exactly, right?

The potential scope is huge really just limited by the workflow you design

It moves beyond simple task automation towards

Intelligent orchestration. Okay, that sounds

Incredibly powerful almost maybe a little scary like how do you maintain control?

How does flow wise make sure things are transparent and you can have human

oversight?

You definitely don't want a black box AI running wild especially for important

stuff, right?

That's a critical point and yeah a very valid concern flow wise tackles this head-on

with a few key features

Focused on control and transparency first off. There's human in the loop or

HITL this is huge. It lets humans review tasks that agents perform during the

process within the feedback loop

Okay, so you can step in. Absolutely. Yeah, imagine your AI support agent is about

to give slightly outdated advice with HITL

A human can catch that specific output before it goes out correct it and this is

key

The AI learns from that correction instantly. It's not just fixing one mistake

It's continuously refining the agents performance based on real-time human guidance

that helps bridge the gap between AI efficiency and human nuance

Then beyond stepping in flow eyes offer strong observability through what they call

execution traces execution traces like a log file

Sort of but much more detailed. It's like a full step-by-step recording of the AI's

decision-making process

You see exactly how it reached an answer what data it looked at which tools it used

the sequence of its reasoning

This is invaluable for debugging for optimizing performance and for auditing making

sure it's doing what you expect

It even integrates with standard tools like Prometheus and open telemetry for

deeper system monitoring

Which is essential for enterprise use and finally, even though it's visual and easy

to use flow wise is also super developer friendly

It's not some closed little garden the agents you design visually you can extend

them and integrate them smoothly into your existing apps and systems

Oh, okay. So plays nice with other things. Definitely. It has robust API's

Software development kits SDKs for both TypeScript and Python and even embeddable

chat widgets

You can drop onto a website so you can design the core AI logic visually and flow

wise

Which is fast and then plug that intelligence into your website your internal tools

your mobile app

Whatever you're building it gives developers the best of both worlds visual speed

plus coding flexibility

So yeah, definitely not a pleck box. You can see inside guide it and plug it into

pretty much anything

You're already using that makes it way more practical for actual businesses, which

leads me to ask

How are businesses using flow wise right now? What kind of real-world impact are we

seeing out there?

Oh, the impact is definitely tangible and it really highlights those benefits speed

efficiency opening up new AI

Possibilities their customer stories show this well, for example uneq. They do

these amazing digital human experiences

They significantly cut down the resources needed to deploy their AI brains by using

flow eyes

That means faster launches and lower costs for them

Another one kumit guitar iFleet used flow eyes to seriously boost the quality and

efficiency of a new co-pilot feature in their fleet

Management product so it's great for enhancing existing things to right now just

building from scratch

Exactly and BTS digital they sped up their whole initiative around build your own

AI

Assistance easily showing how flow wise helps companies become more self-sufficient

with AI

There's great quote from David Mikado a senior director of DX and AI

He said flow eyes has truly changed how we approach AI

It's simple enough to prototype an idea in minutes yet powerful enough to take all

the way to production

That's a pretty strong statement, you know, yeah that sums it up perfectly

Prototype fast scale up and it's not just the official stories

The open source community around flow wise is buzzing on Twitter and places like

that

You see people doing amazing things like creating super specific AI teaching

personas building

Multimodal chatbots that handle both text and images making telegram bots for real-time

bus info using live data

Even no code sequel chatbots. So business users can query databases just by asking

questions in plain English

Wow, that's diverse

It really is it shows the platform is enabling all sorts of innovation from

education to transport to business

Intelligence, it really does sound like a game-changer then speeding things up

making AI more efficient and unlocking these capabilities for people who aren't

necessarily

AI-phd's it lets you test ideas super fast and then actually build them out

properly and having such a strong community

What was it over 42,000 stars on github? That's huge for an open source project

shows. It's alive and well-supported

Absolutely, that community is vital and importantly flow eyes is also built to work

Well with other popular AI tools and frameworks that you know, many listeners might

already be using we're talking smooth integrations with big LLM providers

Like AWS bedrock open a eyes GPT models

frameworks like Lang chain for managing complex AI steps and

Essential vector databases like lemma index or milvis for that smart knowledge

retrieval

It even works with multi-agent systems frameworks like autogen so flow eyes fits

neatly into the bigger AI ecosystem

It doesn't force you into some isolated silo. You can leverage your existing tech

stack

okay, this all sounds amazing incredibly powerful, but

Often tools like this, especially the ones ready for big companies come with a

pretty hefty price tag

How accessible is flow wise really for someone just starting out?

Maybe a small team wanting to experiment that's another area where flow eyes really

scores points accessibility and scalability

You can literally as they say start building for free their free tier gives you

enough to really get going

Two flows in assistance 100 predictions a month a bit of storage plus access to all

the community support

It's perfect for just trying things out learning the ropes building a proof of

concept all with zero cost

Okay, that's genuinely free to start

Yeah

And then if you need more they have starter and pro tiers that are really

reasonably priced for individuals or smaller teams

It scales up affordably, but crucially it's also built to be enterprise ready for

bigger organizations

It has all the features you'd expect support for like over a hundred different

large language models

Tons of embedding options various vector databases plus robust deployment options

on your own servers or in the cloud

And it's designed for horizontal scaling so it can handle massive workloads and

stay reliable

It truly spans from you know a hobby project right up to industrial scale AI

So you can genuinely start for nothing play around learn build something cool

And if it takes off you have a clear path to scale it up massively that level of

flexibility is incredible

It really empowers everyone from beginners to big enterprises

Wow what an incredible deep dive into flow eyes today

It really does seem to stand out by making this complex world of AI agent building

so much more accessible so visual

It's clearly empowering people and organizations to innovate much faster whether

they're seasoned developers

Or you know just starting to explore what AI can do and that really brings up an

interesting question for everyone listening

Doesn't it thinking about your own work your own life?

What task or challenge could you transform with an AI agent especially one that you

could actually build and control yourself?

Maybe without needing to become a coding expert first just imagine the

possibilities flow wise could unlock for you personally

That's a fantastic thought to leave people with thank you so much for joining us on

this deep dive into flow wise today

We really hope you learn something useful and maybe feel inspired to check out

visual AI building and before we go a huge thing

Thank you once again to our sponsor safe server.de for helping make these deep dives

happen do check them out at

next time

next time