Prefactor

Catch your agents' mistakes before they reach customers

1.4K followers

Catch your agents' mistakes before they reach customers

1.4K followers

Visit website

AI Infrastructure Tools

•

AI Metrics and Evaluation

•

Observability tools

We evaluate every step your agents take, live. Errors get caught as they happen. Not in a Slack thread at 1am on a Tuesday

Free

Launch tags:SaaS•Developer Tools•Artificial Intelligence

Launch Team / Built With

Invent List

The hard part isn’t building agents anymore, it’s knowing when they silently stop doing the right thing. Great problem to tackle

Report

1mo ago

Prefactor

Maker

@naumanthanvi absolutely. We want to ensure that you don't even have to worry about what happens in Production because you've done all the hard work to build it.

Report

1mo ago

•••

7 8 9

Forum Threads

p/prefactor

•

17d ago

Improving your agents in production.

Big launch coming in four weeks.

Most agent tooling stops at the classic Observe - Evaluate loop. You can stop, pause, insert a human into your flows. But it mostly happens in development. Once agents hit production they're on their own, and engineers lean on Sentry or PostHog to find out something broke. Then improvement is you, by hand: digging through traces, tuning a prompt, redeploying, hoping.

p/prefactor

•

29d ago

Agents in prod

We have had a lot of fun since the PH launch and making it to number 1. Such a great experience and everyone who got involved and helped us I am insanely grateful to.

As we move on from PH into helping teams evaluate their agents in real time, I'm looking to understand how everyone is doing it. Are you using static evals and running a hit and hope approach? Are you using off the shelf agent evals from OSS? Are you using a tool?

I'd love to know so we can improve what we have to make it the world class solution you don't have to think twice about when building your agents.

p/prefactor

•

2mo ago

Evals without tokens

Hey all. I'm really interested in how you evaluate your agents in production.

The standard approach is sample, LLM as judge and possibly a golden dataset. That seems to be the standard setup.

View all