agentusecasesAll 965 use cases
Security, Science & Hardware

Discover room-temperature magnetic semiconductor candidates with agents

Opus 5.5 agents were used to identify two candidate room-temperature magnetic semiconductors, per the post's headline.

Done with a custom-built or unnamed agent

What they did
A team of Claude Opus 5.5 agents, working with the author, searched for Luttinger-compensated magnets. These are antiferromagnets with zero net magnetism whose electrons are still sorted by spin. The agents ran density functional theory simulations at two levels of approximation, PBE+U and HSE06. They designed one new compound, YBaMnFeO₅, and found a second, KV[Cr(CN)₆], in the literature from 1999.
How it went
Both are predicted to be semiconductors with spin windows far above room-temperature thermal energy. YBaMnFeO₅'s ordering likely collapses at synthesis temperatures. KV[Cr(CN)₆] remains unmeasured for band gap and spin sorting, and the two methods disagree on how water in the sample affects it.
Worth knowing
The results are predictions for perfect crystals only; the next step is to re-make KV[Cr(CN)₆] and measure it. Code and caveats are on GitHub.

Try it yourself with Manus

I want to find candidate room-temperature magnetic semiconductors for [application or material family, e.g. spintronics, oxide or 2D materials]. Search the recent literature and open databases such as Materials Project, then shortlist two candidates with their reported Curie temperature, band gap and the evidence for each. Finish with a short report that cites every source and flags which claims are computed versus experimentally measured.

Read the original ↗

Discussion on HN · Oct 5, 2026

Five of these in your inbox every morning

The best things people got an AI agent to do, each with the prompt to try it.

More like this