Pesquisa e Web

Produces a structured, plain-language briefing on the state of scientific research for a given topic — summarising what is established, what is contested, and what remains unknown.

Inspect codebases w/ pygount: LOC, languages, ratios.

Cria um resumo estruturado para pesquisadores ou coordenadores de filmagens utilizarem na busca por imagens de arquivo ou estoque em bibliotecas, emissoras e acervos especializados.

Writes narration or commentary for a documentary sequence, given a description of the picture and research notes or factual context.

Pesquise dados de negociação do DeepBook e lacunas de mercado na Sui. Use quando o usuário quiser pesquisa sobre DeepBook, oportunidades de mercado ou pares pouco atendidos.

Builds a structured research framework for locating publicly available contact routes for a named person — including institutional channels, public profiles, press offices, and professional directories — so you know exactly where to look and in what order.

Use cloud browser services (Browserbase) for Cloudflare bypass, JavaScript rendering, and stealth scraping when local tools fail

Audit social media accounts (TikTok, IG, etc.): scrape profiles, calculate engagement metrics, diagnose performance drops, interpret analytics screenshots.

Find related notes via semantic search and weave links. Stage 4 of the processing pipeline.

Breaks a long-form article into web-optimized sections with subheadings, pull-quote suggestions, image placement markers, and reading-time estimates — ready for a web editor to drop into a CMS.

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

Produces a structured research framework for finding, organising, and verifying a named person's previous public statements on a specific topic, so a journalist can enter an interview or write a story with full command of the subject's record.