NASA · NASA-916 · record R0511

XMM-GPT

National Aeronautics and Space Administration · GSFC: Goddard Space Flight Center

Overview

Development stage: In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Not reported
Start date: Not reported
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Science
Operational functions: Summarization, Search and knowledge retrieval Derived by keyword rules; see methodology

Problem the AI is intended to solve

XMM-GPT is a domain-specialized AI assistant built by fine-tuning Google's Open-Source FLAN family of LLMs through transfer learning on up-to-date XMM-Newton Documentation. The model is then integrated into a retrieval-augmented generation (RAG) pipeline to ensure that responses are grounded in mission documentation. This reduces model hallucinations and introduces transparency in its decision making process by relaying where in the documentation it got its answer. XMM-GPT acts as an interactive research aide, supporting a wide-range of users (students, researchers, teachers, PIs) in learning about XMM-Newton and its software the SAS.

Expected benefits

Lower entry barriers for new users learning about XMM-Newton and its workflows. Coding assistant that helps to create scripts, explain SAS tasks, and point users to what is causing their coding bugs. Offloads "help desk" queries from mission staff.

System outputs

Instructional Responses (step-by-step guides for SAS tasks), Code Assistance, Explanations/Summarizations of XMM relevant information, Grounded Answers (links to documentation that holds the answer)

Technology

AI classification: Classical / predictive MLSource: Classical/Predictive Machine Learning: Models trained on data to make predictions or classifications based on identified patterns or relatio…
System name(s): Not reported
Custom-developed code: Not reported
Public source code: Not reported

Sourcing

How it was built: Not reported
Vendor (as reported): Not reported
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: Not reported
Privacy Impact Assessment: Not reported
Authorization to Operate: Not reported
Demographic features: Not reported
Training and evaluation data: Not reported
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported