AI for Environmental Engineers (Prompt Course)

What you'll learn

• Prompt structure for technical work: How to frame objectives, assumptions, boundaries, constraints, and deliverable formats so AI outputs are specific, verifiable, and easy to review.
• Data-awareness skills: Ways to guide AI through units, metadata, methods, QA/QC notes, detection limits, and geospatial context-so summaries, comparisons, and recommendations stay grounded in evidence.
• Analytical planning: Patterns for scoping studies, designing sampling plans, setting acceptance criteria, outlining sensitivity checks, and mapping decisions to standards and guidelines.
• Model support (without overreach): Prompts that help prepare inputs, interpret results, and produce reviewer-ready narratives for dispersion, hydrologic, energy, or ecological models-while keeping model execution and calibration in proper tools.
• Compliance literacy: Methods to translate requirements into checklists, trace citations, and produce audit-ready documentation that links analytical choices to applicable thresholds or policies.
• Stakeholder communication: Techniques to convert technical findings into memos, briefings, public comments, and meeting notes, while preserving the underlying evidence chain.
• Reproducibility and governance: How to log prompts, inputs, and outputs; annotate decisions; and implement versioning so your AI-assisted work can be reviewed and repeated.
• Ethics and risk controls: Guardrails for privacy, indigenous and community data, environmental justice considerations, and bias checks-paired with clear disclaimers and verification steps.