International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | DevForge: A Unified AI System for Intelligent Developer Workflows |
|---|---|
| ABSTRACT | Modern software development requires integrated intelligent systems that combine retrieval, generation, refinement, automation, and contextual support. This paper presents Dev-Forge, a multi-model AI framework composed of five coordinated components: (1) a multi-tenant Retrieval-Augmented Genera-tion (RAG) system with AST-based chunking, secure vector retrieval, and reranking; (2) a semantic synthetic data generation engine based on a three-layer constraint-aware architecture; (3) a deterministic prompt refinement module with evidence-based stack detection and confidence scoring; (4) a state-driven GitOps automation system with commit intelligence and rollback validation; and (5) a context-aware cheat sheet generator with language detection and complexity adaptation. By integrating these subsystems within an isolated backend architecture, DevForge provides secure, reproducible, and trans-parent multi-model developer intelligence. |
| AUTHOR | MIHIR PRAJAPAT, SIDDESH KALE, PRANJAL MANE, MIREN HARIA, CHINTAL GALA Department of Information Technology, Shah & Anchor Kutchhi Engineering College, Mumbai, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405048 |
| pdf/48_DevForge A Unified AI System for Intelligent Developer Workflows.pdf | |
| KEYWORDS | |
| References | [1] Y. Zhang et al., “cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree,” arXiv preprint arXiv:2506.15655, 2025. [2] M. R. Chinthareddy, “Reliable Graph-RAG for Codebases:AST-Derived Graphs vs. LLM-Extracted Knowledge Graphs,” arXiv preprint arXiv:2601.08773, 2026. [3] S. Wu et al., “UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models,” in Proceedings of NAACL, 2024. [4] Y. Yu et al., “Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias,” in Proceedings of ICLR, 2023. [5] J. Brown and M. Taylor, “Prompt Refinement Techniques for Large Language Models,” arXiv preprint arXiv:2406.00507, 2024. [6] A. Smith and D. Johnson, “AI-Driven GitHub Workflow Automation Using Intelligent Agents,” arXiv preprint arXiv:2308.16464, 2023. [7] R. Kumar, S. Patel, and A. Mehta, “Conversational AI Systems for Intelligent Developer Assistance,” in Proceedings of IEEE Conference on Artificial Intelligence, 2024. [8] L. Chen, H. Wang, and T. Zhao, “Synthetic Data Generation Using Large Language Models for Structured Applications,” in Proceedings of IEEE Conference, 2023. [9] P. Singh, K. Verma, and R. Gupta, “Constraint-Aware Data Generation Through LLM-Based Architectures,” in Proceedings of IEEE Conference, 2024. [10] D. Wilson and E. Clark, “Deterministic Prompt Optimization for Reliable AI Systems,” in Proceedings of AAAI Conference, 2024. [11] F. Martin and G. Lewis, “Structured Prompt Engineering for Context-Aware AI Applications,” in Proceedings of International Conference on Machine Intelligence, 2025. [12] H. Anderson and J. Walker, “Intelligent GitHub Automation Using State-Driven AI Pipelines,” in Proceedings of IEEE Conference, 2024. [13] C. Roberts and T. Evans, “Transactional Repository Automation with AI-Based Validation,” in Proceedings of IEEE Conference, 2023. [14] N. Sharma and P. Kulkarni, “Context-Aware Conversational Agents for Software Engineering,” in Proceedings of IEEE Conference, 2024. [15] V. Rao and S. Iyer, “Developer-Oriented Chatbot Systems Using Large Language Models,” in Proceedings of IEEE Conference, 2024. [16] M. Khan and A. Desai, “AI-Assisted Knowledge Systems for Programming Education,” in Proceedings of IEEE Conference, 2023. [17] T. Nguyen and L. Garcia, “Adaptive Conversational Frameworks for Technical Assistance,” in Proceedings of IEEE Conference, 2024. [18] B. Thomas and K. White, “Interactive AI Documentation and Developer Support Systems,” in Proceedings of IEEE Conference, 2023. [19] W. X. Author and Y. Z. Author, “Dynamic Cheat Sheet Generator: Context-Aware Knowledge Synthesis for Developers,” arXiv preprint arXiv:2504.07952, 2025. [20] S. Longpre et al., “The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources,” arXiv preprint arXiv:2406.16746, 2025. |
