Abstract—Many everyday business and personal tasks share a hidden structure: some input arrives, an intelligent decision needs to be made about it, and an output has to be produced quickly and repeatedly, at a scale no single person can sustain by hand. This paper presents a single, general-purpose AI workflow automation platform built around this idea, using n8n – a visual workflow automation engine – as the layer that actually thinks, decides, and adapts, while a conventional web application supplies the interface and storage around it. Rather than hard-coding every rule and every prompt into the backend, the platform externalises all of its decision logic into n8n, so that behaviour can be revised the moment real usage reveals a gap, without ever redeploying the application. The platform is demonstrated through two representative use cases built on the identical architecture: automated, conversational practice for a task that benefits from repeated rehearsal, and automated, personalised outreach for a task that benefits from scale. Both use cases were piloted informally, and both showed the same underlying pattern – consistent turnaround within seconds, and a steady improvement in outcome quality as the workflow layer was iterated on. This paper describes the architecture, the shared design rationale, the pilot results, and the limitations that inform future work.
Sanketh B M, T. Vasudev, Karthik R· International Journal of Res...· 0 citations
Effective use of Large Language Models (LLMs) depends heavily on the quality of the prompt supplied to them, yet most users lack familiarity with prompt engineering principles such as role, context, task, constraints, tone and output format, and consequently receive vague or off-target responses. Existing prompt-generation tools compound this problem: they focus on producing a response rather than helping the user construct a better instruction, and they are almost universally built around cloud AI APIs, introducing latency, recurring cost, data-privacy exposure and a hard dependency on connectivity. This paper presents the Smart Prompt Analyzer and Recommendation System, a Flask-based web platform that generates, analyzes and optimizes prompts using a completely self-hosted Large Language Model served through Ollama with the Qwen2.5:3B-Instruct model. The system decomposes a prompt into its constituent engineering elements through a rule-based Prompt DNA Analysis module, scores prompt quality, and produces intelligent recommendations to improve clarity, context and completeness before the prompt is ever submitted for generation. A modular architecture — comprising a web-based user interface, a Flask application server, a Prompt Analyzer, an Edge Cache and the Ollama service — keeps the system responsive and operational even when the underlying AI model is temporarily unavailable, since the rule-based analyzer transparently takes over as a fallback. Functional, integration, performance and user-acceptance testing across fifteen test cases confirmed correct end-to-end operation of prompt generation, Prompt DNA analysis and streamed content generation, with all issues identified during the first testing pass resolved prior to final validation. The system demonstrates that pairing local LLM inference with structured prompt-quality evaluation can make prompt engineering accessible to users with no prior background in the discipline, while eliminating the cost, latency and privacy concerns associated with cloud-hosted alternatives.
Bhoomika B, Nagamani H M, T. Vasudev· International Journal of Res...· 0 citations