Conheça o lyfX.ai em Lubricant Expo Europe 2026

Discovery Theatre: Co-criação por IA para a fase conceptual de engenharia

On 15 September 2026, André Moreira presents AutoGraph: AI-native concept engineering in the Discovery Theatre. Early-stage engineering is still manual work: concepts take weeks, assumptions are hard to trace, and knowledge stays buried in past projects.

O AutoGraph coloca agentes de IA que seguem normas e especificações nesta fase. O PFD Bench transforma um diagrama de fluxo de processos numa descrição de processo precisa em minutos, validado com a K-UTEC Salt Technologies e disponível para teste em pfdbench.lyfx.ai. O CAPEX Engine, co-desenvolvido com um parceiro industrial e em versão beta, produz estimativas iniciais de custos de investimento com pressupostos e cálculos transparentes. O objetivo não é substituir os engenheiros, mas permitir-lhes explorar opções mais inovadoras mais cedo.

Descarregar: Co-criação com IA

Aplicações no mundo real da IA em lubrificantes, com um caso da ROWE

On 16 September 2026, André Moreira is one of the panelists in Real World Applications of AI in Lubricant Development & Formulation. His contribution, From AI Tools to Agentic Organizations, shows how a small AI-first company runs its daily work with AI agents, and used one real case as the example: a market deep dive, run by AI agents and built together with ROWE, one of Europe’s largest independent, family-run lubricant makers.

lyfX.ai ran the study as a human-AI team. A Claude Code orchestrator, running on Claude Opus 4.8, planned the work with the ROWE team, froze the application taxonomy and dispatched twelve specialist agents: five source extractors, a company profiler, four analysts (technology, market, competitors, industry structure), a report assembler and a monitoring drafter. People set the goals and made the calls; the agents prepared and executed. ROWE’s experts reviewed the result, and their feedback was used for further refinements of the results.

O que saiu

• A 72-page market study (22,000 words): application taxonomy, technology benchmark and SWOT per application, market sizing and forecasts, product compilation, competitor portfolios, value chain, Porter’s Five Forces and a customer list by region. Every claim cited.
• 12 agentes, 2,18 milhões de tokens, 2 h 20 min desde o início até ao relatório, cerca de 24 USD de custo estimado de modelo.
• Três briefings de monitorização prontos a usar, para que o estudo pontual se transforme em inteligência de mercado contínua.
• O trabalho continua: a ROWE e a lyfX.ai estão a trabalhar noutros projetos de IA, incluindo inteligência de mercado contínua.

Built with Claude Code and Claude Opus 4.8 (Anthropic) on FuzzyClaw, lyfX.ai’s open-source agent orchestration layer (Open Source with MIT licence).

Descarregar: De Ferramentas de IA a Organizações Agentes