AIware Bootcamp 2025
2025-08-29
Amsterdam, Netherlands
who it's for
software engineers, machine learning engineers, platform engineers, engineering managers, developer tool developers, quality assurance engineers, research scientists
topics
agentic software engineering; autonomous coding agents; FM-native IDEs; foundation model runtime scheduling; LLM evaluation for code; open-weight code models in IDEs; retrieval and guardrails; vision-language model QA; agentic traceability to commits; Hamurabi and GlitchBench benchmarks; reinforcement learning with verifiable rewards; prompting and PEFT adapters
| title | author | length |
|---|---|---|
| Opening of the Bootcamp | Gopi Krishnan Rajbahadur, Ahmed E. Hassan, Maliheh Izadi | 13m |
Bootcamp explains a curated curriculum built over 2.5–3 years from industry and academia, running alongside an ongoing AIware conference series (first in… | ||
| From Copilots to Agentic SE Teammates: Engineering the SE 3.0 Era with AI-Native... | Ahmed E. Hassan | 01h 00m |
Argues a shift to Agentic SE 3.0 with concrete stack pieces: Teammate.next, IDE.next, Compiler.next, Runtime.next. Presents AIDev — a 61K+ repo dataset showing… | ||
| Building High-Quality & Trustworthy FMware | Dayi Lin | 31m |
Practical roadmap for production: start with medium or smaller models rather than a 100B+ default because latency, cost and edge limits matter; use generic… | ||
| Practical Evaluation of LLMs for Code | Maliheh Izadi | 33m |
Open-weight code LLMs are tested inside IDEs (JetBrains, VS Code) with a plugin that records 2,700 downloads and 500 users, yielding about 600,000 data points… | ||
| Beyond Vibe Coding: Leveraging Foundation Models to Infer Intent | Keheliya Gallaba | 32m |
Prototype of a multi-agent ToM system uses iterative dialog, sentiment and expertise inference, and multimodal inputs to extract hidden intent and produce… | ||
| Visual Quality Assurance Using Vision-Language Models | Cor-Paul Bezemer | 51m |
Benchmarks include GlitchBench, a canvas UI set and Video Game QA Bench that split tasks into visual/unit UI regression, glitch detection and bug‑report… | ||
| From Issues to Commits: Autonomous Agents for Smarter Software Traceability | Mehdi Keshani | 33m |
Builds an autonomous agent called LinkAnchor that takes an issue URL and repo, uses chativity 40 nano plus a middleware with data-extractor functions (issue… | ||
| Panel: Agentic SE & Open Source in the FMware Era – Toward Trustworthy, Context-Aware FMware | Cor-Paul Bezemer, Day Lini, Keheliya Gallaba, Maliheh Izadi, Gopi Krishnan Rajbahadur, Mehdi Keshani | 01h 05m |
Panel argues coding agents (Google jewels, OpenAI codeex) scale code generation faster than human review and demands new IDEs, observability and cost… | ||
| nothing matches | ||