What happened
The Yemen Emergency Crisis Response Project ran from July 2016 to March 2022 with US$887.4 million of World Bank financing, under agreements with UNDP and UNICEF. The World Bank's Independent Evaluation Group reviewed the project's completion report on 29 August 2023 and rated the outcome highly satisfactory. In its assessment of monitoring, the evaluators report that UNDP's project management unit carried out 336 field visits. The unit used common social media platforms, such as WhatsApp and a chatbot enhanced by artificial intelligence. The evaluators write that these tools enhanced remote and real-time monitoring, transparency and communication, including the submission of complaints and responses to queries. They rated the quality of monitoring and evaluation substantial. The Bank's own completion report of 3 March 2023 describes the chatbot in the same words. Neither document names the chatbot, describes how artificial intelligence enhanced it or separates its contribution from that of WhatsApp, the field visits and the other monitoring channels.
Sources
-
Evaluation report, by authors with no tie to the system.
World Bank Independent Evaluation Group. Implementation Completion Report (ICR) Review: RY: Yemen Emergency Crisis Response Proj (P159053), ICRR0023450, 29 August 2023.
UNDP’s PMU carried out 336 field visits using common social media platforms, such as WhatsApp and a chatbot enhanced by artificial intelligence, to enhance remote and real-time monitoring, which enhanced transparency and communication, including enabling submission of complaints, and responding to queries.
-
Report, by an evaluator that the makers or users commissioned.
World Bank. Implementation Completion and Results Report: Yemen Emergency Crisis Response Project (P159053). ICR00005809, 3 March 2023. The Bank's own completion report, which the Independent Evaluation Group reviewed.
UNDP used common social media platforms, such as WhatsApp and a chatbot enhanced by artificial intelligence, to enhance remote and real-time monitoring, which enhanced transparency and communication, including enabling submission of complaints, and responding to queries.
Details
AI system
- Workflow
-
UNDP's project management unit used WhatsApp and a chatbot enhanced by artificial intelligence alongside 336 field visits. Implementing partners, third-party monitors and field consultants set up real-time channels to report security threats on the ground.
Follow-up
- Conditions for replication
-
Project staff and communities must have mobile phones and connectivity for the social media platforms. Complaints and queries received through the chatbot must reach staff who act on them.
Entry details
- Sector
-
Humanitarian assistance.
- Purpose
-
An unnamed developer built the chatbot, which UNDP's project management unit used with WhatsApp to monitor the project remotely and in real time, receive complaints and answer queries.
31 more questions not yet checked
model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this benefit
Peter H. Vartanian. (2026). AI chatbot and WhatsApp help UNDP monitor a Yemen project remotely (AIBD-1171). Artificial Intelligence Benefits Database, edition of 2 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1171.html (archived at https://doi.org/10.7910/DVN/AADSII, version 9.0)