Tag
The author built a lead-research pipeline using n8n and AI tools, deliberately avoiding an AI Agent for predictability, and invites feedback on the design.
A user shared a production use case where the Jev tool efficiently retagged 2,300 AI research papers with high accuracy and low cost, improving upon previous classification methods.
The article describes testing to reduce reading cost in an AI verification pipeline while preserving high recall and minority evidence, noting challenges with current approaches and inviting community input.
This paper develops an LLM pipeline for automating systematic literature reviews in disease spread modeling, comparing the performance of GPT-4.1 and GPT-5.0 against human-conducted reviews.
This paper presents a sociotechnical AI pipeline for ITSM ticket data, combining LLM-based schema normalization and clustering to generate executive-facing decision-support artifacts. Stakeholder evaluation shows strong ratings across interpretability, actionability, trust, and likelihood of use.
This paper introduces P&ID Pilot, an end-to-end AI pipeline combining genetic algorithms and LLMs to generate optimal process flow diagrams (PFDs) and transform them into validated piping and instrumentation diagrams (P&IDs), reducing manual engineering effort.
The author open-sourced SarasFlow, an AI pipeline that generates educational videos from a topic by scripting, narrating, creating visuals, adding subtitles, and assembling the final video, with modular replaceable components.
The author built a virtual dance studio on Replit that turns uploaded dance videos into 3D rig animations, though the movement pipeline still needs improvement.
A report on testing an AI pipeline that automatically generates a full podcast episode from a given topic without any manual editing.
COrigami is an end-to-end AI pipeline that generates flat-foldable origami crease patterns from natural language, using optimization and aesthetic evaluation to enable human-AI co-creation in a mathematically constrained domain.
Introduces five open-source tools (MarkItDown, MinerU, Docling, marker, surya) that convert PDFs, Office documents, etc., into Markdown or JSON for direct use with RAG or AI agents.
Built an AI pipeline that converts financial news into structured analysis including sentiment, risks, and opportunities, focusing on consistency through prompt engineering and validation.
A developer used Codex 5.5 as an orchestrator and Deepseek v4 pro as an executor to generate a 240M token fine-tuning dataset, burning 359M tokens at a cost of only $78.