Accelerated Knowledge Discovery: How we build AI agents for Science

We want to transform AI into a full cognitive research partner. The Accelerated Knowledge Discovery (AKD) project drives this transformation through five strategic pillars:

Co-design from the start. Using the CARE methodology, we seek to foster a triadic collaboration between developers, scientists, and AI agents to ensure every agent is scientifically grounded, technically sound, context optimized and efficient.
Demystify the AI Agent. We want to enable everyone to design, build, and share by providing a common Process, Software Development Kit (SDK) and accessible platforms, lowering the barrier to entry for the entire community.
Provide Science Guardrails. To ensure safety and scientific integrity, we want to integrate specialized Risk Agents which provide science-specific guardrails: factuality reasoning over claims and citations, the NASA Science Risk taxonomy, and domain-aware compliance checks.
Standardize the process. We seek to implement community-accepted design and development processes across the science community, ensuring that agent behaviour is consistent, reproducible, and scalable.
Build a collaborative community. By creating an open ecosystem, we want to enable the ecosystems to evolve and improve through feedback and shared contributions, ultimately accelerating the pace of science for everyone.

Strategic Objectives

Reclaim Scientists’ Time. Currently, scientists spend 70–80% of their time on manual, repetitive tasks such as curating datasets and cross-referencing literature. By reducing the time spent on such tasks, AKD enables researchers to instead focus on high-level hypothesis generation and data analysis.
Orchestrate Cross-Disciplinary Research. AKD connects disparate data from siloed science repositories and publications, acting as an intelligent orchestrator by selectively merging individual information sources into a unified knowledge stream.
Integrate Uniform Infrastructure. AKD implements community-accepted design processes to harmonize the use of AI science agents across NASA’s data repositories. With a common AI Agent Software Development Kit (SDK), the framework ensures that agents operate within established scientific guardrails.

Technical and Ethical Guardrails

Human-in-the-Loop (HITL) Approach. Design processes involve rigorous human oversight to ensure AI serves as a partner, not a replacement.
Scientific Integrity. Built on foundations of transparency, reproducibility, and open science, AKD strives for the utmost scientific integrity in design and practice.
Proprietary Innovation. AKD features unique components like the CARE process for agent design, specialized science guardrails, and the FactReasoner agent to mitigate hallucinations and ensure factual accuracy.

Software Deliverables

Centralized AI Agent Service Layer. This centralized, cloud-native service provides a fleet of “common agents” pre-configured for different scientific tasks such as data/code search, establishing science guardrails, and fact checking.
Developer Tooling and Integration, AKD AI Agent Software Development Kit (SDK). The SDK functions as a comprehensive developer toolkit including libraries, documentation, and authentication protocols, enabling developers to build, test, and deploy custom agents that interface with data systems.
Reference Implementation and Demonstrators, AI-Augmented [X] Research Lab Reference Instance. This fully integrated “Art of the Possible” pilot deployment within a specific domain serves as a functional blueprint for the Closed-Loop Scientific Workflow (CLSW) and a “reference implementation” as a new cyberinfrastructure for science.