Susan Delaney
Transforming complex information into accurate, reliable, and evidence-based knowledge through enterprise technology, structured evaluation, and artificial intelligence.
Applying enterprise technology experience in data management, business intelligence, information quality, and analytical problem-solving to modern AI workflows. My work combines prompt engineering, AI model training and evaluation, structured human validation, AI-assisted research, and evidence-based decision-making to develop accurate, trustworthy, and reliable AI-assisted solutions.
Enterprise technology professional specializing in enterprise data, SQL development, business intelligence, data quality, and analytical problem-solving. Since 2023, I have expanded my expertise into generative AI through prompt engineering, custom GPT development, AI model evaluation, structured AI workflows, and AI-assisted research. My work focuses on improving AI response quality, validating information, evaluating model outputs, and applying analytical methodologies to support reliable, evidence-based outcomes.
Prompt engineering, AI response evaluation, custom GPT development, structured AI workflows, human-in-the-loop evaluation, information quality, AI-assisted research, and AI workflow optimization.
Enterprise SQL development, business intelligence, reporting and analytics, data quality, metadata validation, decision-support systems, and analytical problem-solving.
Published interdisciplinary research supported by Python scientific computing, observational analysis, structured evaluation methodologies, and public scientific datasets. My ORCID profile and 2025 CERN Zenodo research corpus document ongoing investigations into structured light phenomena and resonant field dynamics.
Contributor to NASA-affiliated citizen science initiatives, AAVSO observations, ESA projects, Zooniverse image classification, satellite imagery, space telescope observations, photographic plates, and collaborative scientific research.
My current work centers on AI model training and evaluation, prompt engineering, AI-assisted research, and information quality. I design structured AI workflows, develop custom GPT applications, evaluate AI-generated responses, validate factual accuracy, identify inconsistencies, and iteratively refine prompts to improve model performance and reliability.
I also volunteer with a multi-branch public library system, where I conducted an independent evaluation of contemporary nonfiction collections using AI-assisted information evaluation and a structured, evidence-based methodology. This work included developing nonfiction acquisition recommendations, collection weeding guidance, metadata validation, bibliographic verification, and an executive decision-support report supporting collection development and long-term planning.
Although my independent science research culminated in a seven-paper publication corpus in 2025, the analytical methodologies developed throughout that work continue to inform my approach to AI evaluation, information quality, structured classification, evidence-based decision-making, and technical problem-solving.
Across every stage of my career, from enterprise technology and business intelligence to AI evaluation and scientific research, one principle has remained constant: Transform complex information into accurate, reliable, and evidence-based knowledge.
This portfolio showcases practical AI solutions developed across multiple large language model platforms. The projects demonstrate prompt engineering, agentic workflow design, knowledge synthesis, research automation, and domain-specific AI applications. Where appropriate, representative outputs are provided while proprietary prompt engineering and implementation details remain confidential.
Interactive AI applications designed to assist researchers, technologists, and scientific exploration through specialized prompt engineering and domain-specific knowledge. Live, interactive links:
"Cosmic Quest Adventure": An interactive research game
"Cosmic Weaver": An art assistant for visualizing a timeless, spatial universe
"Astro Light Explorer:" An expert-level astronomy research assistant
Autonomous AI workflows that execute on a recurring schedule to synthesize scientific information, generate structured reports, and automate research-oriented tasks.
Designed and deployed autonomous xAI Grok workflows for scientific reporting and publication analytics.
Overview
This automation workflow executes on a daily schedule, retrieves astronomical ephemeris information for a specified observing location, synthesizes the results into a human-readable observational summary, and delivers the report automatically by email. The underlying prompt architecture is proprietary.
Platform
xAI Grok
Project Type
Agentic AI Automation
Scheduled AI Workflow
Automated Scientific Information Delivery
Objective
Develop an autonomous AI workflow that generates and emails a daily astronomical observing report containing solar and lunar ephemeris information for a specified observing location.
Capabilities
Executes automatically on a daily schedule.
Retrieves current astronomical ephemeris data.
Generates a structured natural-language summary.
Calculates sunrise and sunset times.
Reports moonrise, moonset, and lunar illumination.
Includes observational context relevant to amateur astronomy.
Delivers the report automatically by email.
Representative Output
The automation provides:
Sunrise and sunset
Moonrise and moonset
Lunar illumination percentage
Daylight duration
Observing conditions
Narrative interpretation suitable for planning observations
Skills Demonstrated
Agentic AI workflow design
Prompt engineering
Workflow automation
Structured data interpretation
Technical communication
Astronomy domain knowledge
Automated report generation
The following representative screenshots demonstrate engineering and automation of the Astronomical Sun & Moon Times workflow.
Representative output with screenshot #1 of email delivered with Astronomy Sun and Moon times and scientific information.
Representative output with screenshot #2 of email delivered with Astronomy Sun and Moon times and scientific information.
Overview
This autonomous AI workflow monitors my published Zenodo research corpus on a recurring schedule, analyzes publication metadata, generates concise summaries of individual works, and compiles the results into a structured research report delivered automatically by email. The workflow streamlines ongoing publication monitoring while preserving proprietary prompt engineering and implementation details.
Platform
xAI Grok
Project Type
Agentic AI Automation
Research Analytics
Scholarly Publication Intelligence
Objective
Develop an autonomous AI workflow that monitors and summarizes a research publication corpus, transforming technical academic metadata into concise, readable research analytics delivered automatically.
Zenodo Publications Analytics Project Workflow
Autonomous workflow that analyzes a scholarly publication corpus and generates structured publication summaries for ongoing research monitoring.
Executes on a recurring schedule.
Reviews the current Zenodo corpus.
Identifies publications and associated metadata.
Generates concise summaries of each publication.
Produces a structured research overview.
Delivers the report automatically via email.
Agentic AI workflow design
Prompt engineering
Scientific literature summarization
Metadata interpretation
Automated research analytics
Structured report generation
Technical communication
Autonomous scheduled execution
Skills Demonstrated
Agentic AI workflow design
Prompt engineering
Workflow automation
Scientific literature summarization
Research metadata analysis
Knowledge synthesis
Technical writing
Automated analytics and reporting
The workflow produces a concise summary of published research, including publication titles, DOI references, and technical descriptions suitable for rapid review and portfolio monitoring.
The underlying prompt architecture, workflow logic, and optimization techniques are proprietary. Screenshots are provided to demonstrate functionality and output quality while protecting implementation details.
The following representative screenshots demonstrate engineering and automation of the of Zenodo Publications Analytics project workflow.
Representative output with screenshot #1 of email delivered with Susan Delaney's Zenodo Publications Corpus.
Representative output with screenshot #2 of email delivered with Susan Delaney's Zenodo Publications Corpus.
OpenAI GPTs
xAI Grok
Prompt Engineering
Agentic AI
Workflow Automation
Research Analytics
Scientific Data Interpretation
Knowledge Synthesis
Technical Documentation
AI-Assisted Research