Water

Meet WaterCopilot: AI for Smarter Water Decisions in the Limpopo Basin

Kari Jaaskelainen

14 Jan 2026 — 1 min read

Meet WaterCopilot, an AI assistant co-created by IWMI and Microsoft Research to help manage the Limpopo River Basin. It turns scattered documents and live hydrology feeds into clear, actionable answers.

Unifies policy files, reports, and sensor data in one chat.
Answers with transparent source links you can verify.
Provides live insights: environmental-flow alerts, rainfall trends, reservoir levels, irrigation stats.
Performs quick calculations and shares simple visuals.
Chats in English, Portuguese, and French.

Under the hood, it uses Retrieval-Augmented Generation and tool-calling. Two plugins power it: iwmi-doc-plugin (semantic search over indexed documents via Azure AI Search) and iwmi-api-plugin (queries live databases).

In evaluations, WaterCopilot scored 0.8043 on the RAGAS framework, with high answer relevancy (0.8571) and context precision (0.8009).

Why it matters: faster, more inclusive decisions for water security in data-scarce, cross-border settings. Today’s limits include some non-English technical documents and occasional API latency. It also connects to the LRB Digital Twin and scales to new basins.

Paper: https://arxiv.org/abs/2601.08559v1

Register: https://www.AiFeta.com

Water AI Climate WaterSecurity Sustainability DigitalTwin RAG Hydrology Governance Africa Limpopo IWMI MicrosoftResearch

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A