Superagent Blog

A new way of building software is catching on. People are skipping the traditional engineering process and using tools like Replit, LLM apps, and code agents...

Today, our interactions with language models are largely limited to discrete, isolated tasks: drafting emails, generating content snippets, analyzing small...

AI agents as we know them are about to become extinct. The complex, over-engineered systems we build today—with their carefully crafted prompts, intricate...

Until now, systems that combine language models with external knowledge have relied on a two-step process: first, retrieve relevant documents using semantic...

For an agent to be really useful, it needs tools — specialized pieces of code that help complete specific tasks, like browsing the web. Today, these tools are...

In a thought-provoking post on X, Klarna CEO Sebastian Siemiatkowski offered an intriguing analogy about AI capability. Imagine standing in the year 1700 and...

The future of Large Language Model (LLM) costs has become a subject of intense debate in the AI community, with experts presenting starkly different visions of...

OpenAI's recent announcement of their o3 model marks a pivotal moment in artificial intelligence development. With its ability to perform at PhD-level across...

I've noticed a concerning trend in the AI-agent space for the last 2 years: the widespread adoption of hardcoded workflows.The thinking goes that by...