In the humanitarian sector, new field managers are often thrust into roles demanding an unrealistic breadth of knowledge. They are expected to instantly master complex donor regulations, reporting procedures, humanitarian principles, and internal policies, leaving them in delicate positions without immediate support. This challenge highlights a critical gap for the dedicated individuals on the front lines.

To address this, I built the Humanitarian Assistant, a dynamic AI tool designed to act as a virtual colleague. It is more than just a chatbot; it is a real-time support system built to provide the contextually relevant assistance that humanitarian workers need to succeed—grounded in trusted public sources and honest about where its answers come from.

Designing for Immediate Access

We believe that in a crisis, barriers to information should not exist. That is why the Humanitarian Assistant follows a strict "Open Access" philosophy. Any visitor can land on the page and immediately start asking questions—no login required. However, for those who need to manage long-term projects or revisit complex reasoning chains, the tool integrates seamlessly with baena.ai. By signing in, users can save their conversation history, effectively building a digital memory bank of their work.

Rather than asking users to pick the right "mode" for every question, the assistant works like a versatile team member: it reads your question and automatically reaches for the right source—a knowledge library, a live data feed, or a web search—and combines them into a single, coherent answer.

Grounded in Public Humanitarian Knowledge

In our sector, data privacy and the "Do No Harm" principle are non-negotiable. We made a conscious architectural decision to build the knowledge base exclusively from publicly available, verified humanitarian guidance—ALNAP lessons and evaluations, IASC guidance, the cash and voucher assistance (CVA) toolkit, ECHO eligibility rules, and child-protection and PSEA standards, among others. We do not scrape private internal datasets or sensitive operational files.

These documents—hundreds of reports, distilled into thousands of searchable passages—are embedded and stored in a self-hosted Qdrant vector database that we run and control end to end. When you ask a question, the assistant retrieves the most relevant passages and cites the source documents it drew on, so you can verify the answer and read further. By owning the retrieval layer rather than relying on opaque third-party services, we keep every answer transparent and traceable to public-sector knowledge.

Live Data, Not Just Documents

Static guidance is only half the picture, so the assistant also queries live humanitarian data sources on demand:

  • ACAPS — displacement and people-in-need figures for Ukraine (down to the oblast level), plus global crisis analytics: the INFORM Severity Index, the Risk List of emerging threats, and Humanitarian Access constraints for any country.
  • FEWS NET — acute food insecurity IPC phase classifications (from Minimal to Famine) and staple food market prices with year-on-year trends, anywhere in the world.
  • Web search for current events when the curated sources don't cover a question.

The agent decides which tool fits each question: a query about famine risk in the Horn of Africa pulls live IPC data and cites FEWS NET, while a question about cash programming draws on the knowledge base, and a request for displacement figures in a Ukrainian oblast hits ACAPS directly.

Orchestrated Intelligence Under the Hood

While the interface is simple, the engineering behind it is deliberate. The assistant is built on Flowise, orchestrating a Google Gemini model together with the retrieval and live-data tools above. We recently re-platformed the system off the OpenAI Assistants API onto Gemini and our own Qdrant vector store—a move that gives us independence over the model, full ownership of the retrieval layer, and a lower running cost. Hardened guardrails keep the assistant strictly on humanitarian topics and resistant to prompt-injection attempts.

The result is a secure, transparent, and cost-effective colleague—free for everyone to use, from international coordinators to local NGO partners.