[{"content":" Weekly Multi-Agent Reports Weekly manufacturing reports written by an AI and fact-checked by a second AI — running locally on a laptop, no cloud infrastructure to set up.\nThe problem Customer-facing reports need to be factually right. But LLMs hallucinate — they'll confidently invent numbers, twist methodology, or call trends that aren't there. Most pipelines write the report first and (maybe) check it after — which is too late: once a wrong number is in front of a customer, the trust hit is irreversible.\n📊 Raw Data weekly batch 🧮 KPI Pipeline Python · self-audit ✍️ Writer Agent Sonnet · writes ✅ Verifier Agent Haiku · checks 📄 HTML Report charts \u0026#43; narrative Impact Weekly reports run on autopilot, with a separate AI agent sitting between the writer and the published page. It checks every numeric claim against the underlying data before any HTML is rendered — bad claims trigger an auto-fix or halt the run, so wrong numbers don't reach customers. Built end-to-end with Claude Code and runs entirely on a laptop, so there's no cloud orchestration to maintain. Each report covers loss rate per productive hour, broken down by shift and by weekday, with the per-shift trend over time. It splits losses by cause (machine wait, material, operator absent, rework, changeover) and surfaces the LLM's top three suggested actions for the coming week.\nPythonMulti-agent AIClaude CodePlotlyJinja2 View on GitHub → ","permalink":"https://barbararomeira.com/projects/weekly-multi-agent-reports/","summary":"Weekly manufacturing reports written by an AI and fact-checked by a second AI — running locally on a laptop, no cloud infrastructure to set up.","title":"Weekly Multi-Agent Reports"},{"content":" AI Manufacturing Digest A daily news bot for AI in manufacturing — read everything for me, every morning.\nThe problem To stay current on how AI is being used in factories, you need to read 20+ blogs and newsletters every day. Most of what's out there repeats the same story across sites, or is just company marketing dressed as news. It takes too much time, and the real signal gets lost in the noise.\n📰 RSS Feeds 22\u0026#43; sources 🔍 Filter dedupe \u0026#43; relevance ✨ LLM OpenRouter 📋 Notion DB daily digest Impact Reading 20+ sites used to take a real chunk of the morning, and most of what I read was repetition or marketing. Now a quick scan of one curated Notion page surfaces only the stories that actually move the field — real deployments, real outcomes. Over time, the database becomes a searchable archive of AI-in-manufacturing trends I can mine when client conversations or product decisions need recent evidence.\nPythonGitHub ActionsLLM · OpenRouterNotion APIRSS View on GitHub → ","permalink":"https://barbararomeira.com/projects/ai-manufacturing-digest/","summary":"A daily news bot for AI in manufacturing — read everything for me, every morning.","title":"AI Manufacturing Digest"},{"content":"Work Jan 2024 – Present AI Product Manager (Founded the Product function) · Deltia.ai · Remote Identified the need for a dedicated product function, took ownership before the role formally existed, and built it from the ground up as the company scaled. Helped scale the platform from 20 to 700+ deployed cameras (35x) in under two years, making the product decisions that let us onboard new customers faster and across different use cases. Lead end-to-end product discovery: user interviews, JTBD synthesis, PRDs, wireframes, MVPs, and AI-native prototyping (Replit, Lovable, Claude Code). Currently leading an LLM-powered chat feature that lets each customer build their own dashboards for their use case — no engineering involvement. Delivered multiple features end-to-end including Activity Recognition and the OEE module, working directly with backend, frontend, design, and computer vision teams. Drove a step-change in engagement: customers moved from project-based logins to 80%+ of accounts active daily. Co-own the product roadmap and lead the company-wide OKR process. Nov 2023 – Present Continuous Improvement \u0026amp; Customer Success Lead · Deltia.ai · Remote Built and led the CI / Customer Success department from scratch — processes, standards, and training programs that scaled across international accounts. Designed and deployed an AI-powered CI framework across 10+ client sites in North America and Europe (automotive, power tools, luxury goods, electrical systems), delivering €3M+ in cost savings. Leveraged direct customer engagement to surface frontline pain points, feeding insights into the product roadmap — a unique feedback loop between customer success and product development. Achieved a 30% increase in conversion rates through consultative engagement; expanded key accounts internationally. Led and mentored a team of 5 data scientists and CI managers. Nov 2021 – Oct 2023 Regional Lean Manager · Hilti Group · Manchester, UK Led deployment of Hilti\u0026rsquo;s continuous improvement program across 5 Northern European markets — logistics, finance, HR, customer service. Cross-functional initiatives delivered £383K in cost savings and eliminated 72,000 hours of waste in 2022. Trained and certified 90+ employees. Recognized as a Top 3 Global Finalist in Hilti\u0026rsquo;s Best in Class Lean Awards. Oct 2020 – Nov 2021 Continuous Improvement Engineer · Renault Group · Aveiro, Portugal Drove process optimization and Lean execution across production lines, deploying CI tools and Value Stream Mapping to reduce costs and remove bottlenecks. Feb 2019 – Sep 2020 Product Owner · Renault Group · Aveiro, Portugal Designed and built an AI-enhanced decision support system — e-Kanban with route optimization and bin-packing algorithms — for production planning and inventory control. Defined system requirements, collaborated with end users, partnered with software engineers through full delivery and launch in an industrial setting. Achieved a 19% reduction in inventory levels and 22% decrease in holding costs through simulation-validated outcomes. Education Sept 2019 – Apr 2022 PhD, Industrial Engineering and Management · University of Aveiro · Aveiro, Portugal Dissertation: System for Production Control and Support Services Planning. Awarded Highest Distinction. Sept 2013 – Nov 2018 M.Sc., Mechanical Engineering · University of Aveiro · Aveiro, Portugal Dissertation: Predictive Maintenance in the Context of Industry 4.0. Grade 19/20 (Distinction); top 10% of cohort. Certifications AI \u0026amp; Product Anthropic · May 2026 Anthropic · May 2026 Project Management Institute · Dec 2025 Project Management Institute · Dec 2025 Project Management Institute · Nov 2025 Udacity · Aug 2025 Product School · Dec 2024 Lean \u0026amp; Continuous Improvement Six Sigma Master Black Belt In progress · Expected 2026 Lean Six Sigma Institute · Mar 2026 Lean Six Sigma Institute · Dec 2025 Lean Six Sigma Institute · Jun 2025 Master Program — Continuous Improvement APCER · Feb 2021 Kaizen Certifications (VSM, Production, Logistics) Kaizen Institute · 2020 Postgraduate Diploma in Lean Management CLT Services · Dec 2019 Leadership \u0026amp; Change Santander Open Academy · Dec 2025 HCMP® 3G Expert Professional Human Change Management Institute · Jan 2022 HCMP® 3G Practitioner Human Change Management Institute · Jan 2022 Lean People Leadership CLT Services · Apr 2020 Other Occupational Health and Safety Senior Technician (Level 6) Politécnico da Guarda · Jun 2022 Certificate of Pedagogical Skills IEFP · Jun 2019 Languages English (advanced) · Portuguese (native) · Spanish (B2)\n","permalink":"https://barbararomeira.com/experience/","summary":"Career, education, and certifications — a chronological timeline.","title":"Experience"}]