Benedikt Sanftl

Co-Founder & CEO Mutagent. we bring you the infrastructure for your software factory. Public Beta live:

[Benedikt Sanftl @BeneBagus]

Everyone's building AI agents. Almost nobody can tell you why they fail.

I'm Bene, Co-Founder & CEO of Mutagent. Before this: I brought autonomous driving radar from concept to production at Cruise, then scaled an AI agent platform to 30+ enterprise clients as CPO at Beam AI.

[Benedikt Sanftl @BeneBagus]

Day two of Web Summit

So nice meeting the people who came up to our booth 🤩

Foreshadowing of the stormy summit

[Benedikt Sanftl @BeneBagus]

@marcklingen Our thats are like: there is the factory owner and then bugs/features requests are piped in and the festure owner reviews the spec and pre deploy the test results

[Benedikt Sanftl @BeneBagus]

Heavy AI adopters merged 98% more PRs, and review time rose 91% (Faros AI).

The Software Factory takes issues off your board and hands back reviewed PRs. Agents do the work between, and you approve the plan and the merge.

Local or Mutagent Cloud: app.mutagent​.io

[Benedikt Sanftl @BeneBagus]

@colemurray @hwchase17 What if you goal orchestrate already?

[Benedikt Sanftl @BeneBagus]

Life as a founder…

@WebSummit storm foreshadowing

[Benedikt Sanftl @BeneBagus]

Starting our websummit and team offsite with some banger networking @WebSummit @mutagentio

Stay tuned for more updates of the week! It will be crazy!

[Alisa @depinfluencer]

Hey frens! I am BACK!

Reporting straight from @WebSummit

I’m hard launching /unsupervised by Mutagent @BeneBagus at the Dev House. if you’re in Lisbon, I better see you there 🪩

Also look out for some fun after movies…

https://t.co/JtLWVQTM30

[Benedikt Sanftl @BeneBagus]

@depinfluencer @WebSummit yeah, lfg! the aftermovie will hit hard. so don't miss out

[Benedikt Sanftl @BeneBagus]

@beamnxw Check out https://t.co/x9xpG1GUSY you dont need to start from scratch, battle tested on over 4000 sessions

[Benedikt Sanftl @BeneBagus]

@yrechtman @San_Damianoz We are building it

[Damian Zaker @San_Damianoz]

Best article I've read about the entire RL craze we're witnessing right now.

Many investors are turning down extremely smart founders building a data-native business right now b/c they are unsure of the terminal value.

I think the reality is that b/c it's early innings, the best teams are laser focussed on hustling their way into customers that can let them become task factories.

We should see more concrete plays (e.g. the Open Router for the task economy) emerge in the next 6-9 months.

[Benedikt Sanftl @BeneBagus]

Building Mutagent between Berlin and SF ✈️

If you're a

AI engineer
startup founder
VC
data scientist
product manager

Let's connect! Berlin or SF for building an AI startup? 🚀

[Benedikt Sanftl @BeneBagus]

Walking SF, building Mutagent ☀️

If you're a

Claude Code user
LangChain user
backend dev
founder
open-source maintainer

Let's connect! How do you test your agent before you ship it? 🚀

[Benedikt Sanftl @BeneBagus]

Conference day, Mutagent on the sponsor wall 🎤

If you're a

CTO
ML engineer
SRE
founder shipping agents
platform engineer

Let's connect! Which conference was actually worth it this year? 🚀

[Benedikt Sanftl @BeneBagus]

The step nobody plans for is the one that ships.

[Benedikt Sanftl @BeneBagus]

Building Mutagent in SF 🌉

If you're a

agent builder
AI engineer
startup founder
LLM eval nerd
PM shipping AI features

Let's connect! What broke first when your agent hit real users? 🚀

[Benedikt Sanftl @BeneBagus]

More attempts do not fix a misread instruction. The trace tells you that.

[Benedikt Sanftl @BeneBagus]

The glow-up every agent team goes through eventually.

[Benedikt Sanftl @BeneBagus]

An eval that is not grounded in real traces is just a vibe check with extra steps.

[Benedikt Sanftl @BeneBagus]

Users will always ask the question nobody planned for, and your production traces are the only place you'll see it.