andreas_mauer

The core problem: AI agents require measuring and iterating on subjective behavior - tone, decision-making, context usage. From experience, the best setup is when product managers take care of improving agent behavior, while engineers build workflows and infrastructure.

Restack's approach:

- Engineers build workflows in Python. Temporal and Kubernetes handle reliability and scalability.

- Product teams and domain experts A/B test and version control prompts and context management, without engineering required for behavioral iteration.

Technical stack (open source):

- React for frontend

- Temporal for retries and long-running workflows

- Kubernetes with horizontal pod autoscaler for agent scaling

- Context store built on Clickhouse

- Full observability and agent tracing

- MCP-compatible workflows

Basically both articles said that VCs generate more returns than the S&P.

Do you have any source for "Most VCs dreadfully under-perform the market".

I work since 10 years as SEO consultant. Still almost every ecommerce site I audit don't get the basics straight. Sometimes is just pure overindexation / duplication caused by facets, filters, tracking params.., others just wrong implementation of canonicals, robots-tags, hreflangs...

So even today in 2018, fixing your SEO issues can be a game changer for some businesses.

Hi, this script checks a list of URLs every 5 minutes and send you an email in case any of them don't deliver a 200 status code. The motivation was to have a free (as in free beer) downtime alert that I could easily use against all my sites.

I still need to include a 1 sec delay between crawls to avoid server issues.

I would appreciate any feedback regarding how to extend the functionality without increasing complexity to the final user.

thanks, I will check it.

I feel like I know nothing about js/node anymore,

Classes in JS!! what kind of witchcraft is that? How do you do it?