Signal de tendance
6
mentions (7j)
6
mentions (30j)
9 juin 2026
premier signal
1
pays concernés
Contexte et analyse
Cette tendance "Perplexity Search as Code: sandboxed Python agent pipelines" a été détectée dans la catégorie AI Engineering & LLM Ops avec un score de 100/100. Cette tendance connaît une croissance explosive et attire beaucoup d'attention actuellement.
Entités liées
Extraits des sources
Abhishek Gautam](https://www.abhs.in/who-is-abhishek-gautam)·June 8, 2026·11 min read ! Quick summary Perplexity replaced fixed search API calls with sandboxed Python pipelines agents write themselves — 288K tokens down to 43K on a CVE hunt benchmark. Read next * * **Perplexity** launched **Search as Code (SaC)** in early **June 2026** — an architecture where **AI agents write Python search pipelines** in a **sandbox** instead of chaining **fixed API tool calls**. On a **200 high-severity CVE**...
— abhs.in
Ce que disent les sources
"Perplexity launched Search as Code, letting AI agents write sandboxed Python search pipelines that cut tokens from 288K to 43K on a CVE-hunt benchmark."
"Perplexity stellt mit "Search as Code" eine neue Architektur vor, bei der KI-Modelle ihre Suchabläufe als Python-Code schreiben, statt eine fertige Such-API..."
"Perplexity's new "Search as Code" architecture dumps rigid search APIs and lets AI models write their own search routines in Python. By letting the agent..."
"Perplexity's Search as Code lets AI agents generate Python search workflows, but claimed token savings and benchmark gains still need outside validation."
"Perplexity Search as Code lets AI models write custom search pipelines in Python, cutting token usage by 85 percent and outperforming competitors on..."
"Perplexity has officially launched Search as Code (SaC), a paradigm shift in how artificial intelligence models interact with the web."
DE