ICARDA scientists along with CGIAR LIVESTOCK developed a cloud-based genetic database platform to boost breed improvement programs in community-based livestock breeding programs in Ethiopia. 

Genetic improvement on local breeds kept by small farmers in developing countries is challenging. Even though good pedigree and performance recording is crucial and an important component of breeding programs, it remain difficult or next to impossible under conditions of subsistence livestock farming. This means that standard genetic evaluations, as well as selection and planning of mating based on estimates of the animals' genotypes, cannot be done at any level in the population of the target breed or genetic group.

Breeding programs for local breeds kept by small farmers in developing countries are a major challenge. Animal recording of pedigree and performance under conditions of subsistence livestock farming is remain difficult or next to impossible. This means that standard genetic evaluations, as well as selection and planning of mating based on estimates of the animals' genotypes, cannot be done at any level in the population of the target breed or genetic group.

- Lack of automated data capture systems affects timely feedback and accuracy of information for breeding decisions.
- CGIAR researchers and national research partners have adopted a digital genetic database, Dtreo, that is enhancing genetic improvement by providing timely and accurate animal ranking information to communities.
- Dtreo is a digital genetic database that is flexible and easy to use, that allows users to capture and save data offline. Data is uploaded to the database once an internet connection has been established.

Digital platform enhances genetic progress in community-based sheep and goat breeding programs in Ethiopia:

- Up-to-date information on estimated breeding values and animal rankings is directly channeled to breeder organizations and used for selection decisions.

- The digital platform motivated use of more complicated evaluation models which improve accuracy of breeding values considerably.

- When upscaled, this will help create a permanent multi-country source of information.

The evidence base on agri-food systems is growing exponentially. The CoSAI-commissioned study, Mining the Gaps, applied artificial intelligence to mine more than 1.2 million publications for data, creating a clearer picture of what research has been conducted on small-scale farming and post-production systems from 2000 to the present, and where evidence gaps exist.

A range of approaches and financial instruments have been used to stimulate and support innovation in agriculture and resolve interlocking constraints for uptake at scale. These include innovation platforms, results-based payments, value chain approaches, grants and prizes, incubators, participatory work with farmer networks, and many more.

Innovation for sustainable agricultural intensification (SAI) is challenging. Changing agricultural systems at scale normally means working with partners at different levels to make changes in policies and social institutions, along with technical practices. This study extracts lessons for practitioners and investors in innovation in SAI, based on concrete examples, to guide future investment.