Yoshio Nomura@Asterios

Maintenance teams are stretched and their history is hard to trust. In MaintainX's 2025 survey of 1,320 maintenance professionals, 71% called preventive maintenance a core strategy, yet under 35% spend most of their time on it and 58% spend over half their time reacting to breakdowns. The records meant to guide them are often weak: a peer-reviewed 2024 Semantic Web study (Woods et al.) found data-quality issues in 55% of eight years of work orders for one centrifugal pump. Meanwhile, Siemens (True Cost of Downtime, 2024) estimates one hour of unplanned downtime costs a large automotive plant $2.3 million. That is why we built IGNIS: an evidence desk for supervisors and reliability engineers who must turn messy work orders into decisions they can defend. Models propose, code computes and people approve. Users import CSV or Excel exports, confirm column mappings and review AI-suggested components, faults and actions anchored to exact spans of the original text. Approved records form a versioned snapshot. Code calculates counts, priorities and alerts, so numbers stay reproducible. A reviewed asset-and-component graph keeps wrong-model and superseded manuals out of retrieval, and the top passages feed a cited draft with alternatives and uncertainty, or an abstention when evidence is missing. Validators check every citation and numeric binding; an expert signs off before IGNIS can issue an evidence-linked PDF report. IGNIS runs on AMD Token Factory: DeepSeek-V4-Flash-Vision-Exp extracts work-order entities, DeepSeek-V4-Flash drafts cited explanations, and MinerU2.5-Pro reads scanned manuals, behind one rate-aware API gateway with recorded replay. On MaintIE's held-out test split, 105 of 108 extraction outputs were valid. Unlike chat assistants, IGNIS never lets a model set a number or approve a finding, and every claim resolves to a record and passage. The demo labels synthetic, replay and live data; it claims no failure prediction or measured production savings yet.

These days, restaurants lose money at the order. Errors cost an estimated 1–5% of revenue [1][2], and 57% of allergy-affected diners skip a restaurant when allergen info is unclear [3]. 62% of operators still call recruiting a significant challenge [4]. Today's fixes each break: menu-tap ordering makes every guest tap every dish; drive-thru voice AI costs $500–2,200 per location monthly [5] and suits one speaker, not a table. In our benchmark, cloud voice agents took 19–86 s per turn, and a model choosing its own steps was right 0 of 12 times on six-turn orders. That's why we built The Lantern, a real-time voice maître d' for the table. AssemblyAI Universal-3.5 Pro streams each turn, keeps 54 menu names intact, shows words as guests speak, and lets them interrupt. The model talks, the menu decides: it sets prices, flags allergens, and answers in the guest's language. It handles "those two," "instead," unsaid modifiers, and a dish sold out a minute ago. The kitchen sees every turn, gets a ticket only when the order is placed, and can accept, refuse, or offer a substitute, spoken back to the table. The LLM and voice run on site; only transcription audio leaves. On a four-dish, $36.50 order we were right 10/10, up from 0/10, and 5/5 on two other computers. Five AssemblyAI sessions ended with the right basket and no stall, up from 2/5. The first reply starts 1.4 s sooner; the voice begins 2.65 s after the guest stops. Transcription is our only cloud cost: $0.45 per session-hour [6], about $15–22 per 1,000 orders. Small sample; real-table trials come next. Next: tourist restaurants in the US, Bangkok, Tokyo, then chains and hotels. Restaurants pay $29–49 per table monthly, about $580–980 for 20 tables. Then more languages, a faster on-site voice, "the usual," and tickets into Toast, Square, or Clover. [1] Loman.ai '25 [2] QSR Pro '26 [3] Nutritics '26 [4] Restaurant Business '26 [5] Beancount '26 [6] AssemblyAI '26

Develarper is an engineered containerized AI agent constructed for the AMD Developer Hackathon Track 1. It utilizes a highly optimized four-layer hybrid routing core to minimize total remote Fireworks API token consumption while clearing the required accuracy threshold. The agent dynamically routes tasks across eight distinct capability domains using zero-token heuristic overrides, localized semantic caching, and a supervised PyTorch MLP classifier utilizing all-MiniLM-L6-v2 embeddings to achieve 100% routing accuracy. Low-complexity tasks (such as sentiment analysis, NER, short summarization, and factual questions) are processed entirely local within the strict 4 GB RAM sandbox using an embedded Qwen2.5-3B model via llama-cpp-python. The architecture implements a "local-first" code execution path that tests code generation and debugging locally, using AST parsing validation before failing back to remote infrastructure. High-order deduction, mathematics, and long-context summaries are dynamically escalated to specialized remote models like kimi-k2p7-code and minimax-m3. Token trimming algorithms are applied globally to strip conversational filler and strictly compress input and output footprints, ensuring maximum token efficiency and robust leaderboard positioning.

🌎 Hybrid Hackathon | 💻 Online Build: 12-17 October 2026 | On-site phase: 17-18 October 2026 To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. The AMD Developer Hackathon: ACT III is a hands-on event for developers, founders, engineers and builders who want to push what’s possible with AI on real infrastructure. 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.