Hacker News Reader

It's actually quite doable to build your own deep research agent. You just need a single prompt, a solid code loop to run it agentically, and some tools for it to call. I've been building a domain-specific deep research agent over the past few days for internal use, and I'm pretty impressed with how much better it is than any of the official deep search agents for my use case.

View on HN

same here. I first built the agentic workflow in python and later nextjs. uses dozens of llm apis. works well, and am also impressed with the results.

Curious what you mean by dozens of llm apis. Different models? Or different tool calls?

different models. high level approach: N models receive the same prompt → responses are consolidated through a simple embedding-based similarity matrix → another model performs a simple assessment of deduplicated responses → these are then consolidated into a research report & data visualization.

the whole contraption uses ~10 different models, but more can easily be plugged into the initial generation phase. happy to demo it sometime! [edit: email on profile].

Reply on news.ycombinator.com