Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Build Locally, Build with AI, Build at Scale

Build Locally, Build with AI, Build at Scale

The deck showcases Kenya’s leadership in AI adoption, the power of building and deploying AI locally (especially with tools like Foundry Local), the importance of responsible and observable AI, and real-world use cases that are already making an impact across industries. It provides practical steps and resources for getting started with AI at scale, tailored for the Kenyan and African context.

Avatar for Bethany Jepchumba

Bethany Jepchumba

August 02, 2025
Tweet

More Decks by Bethany Jepchumba

Other Decks in Technology

Transcript

  1. • Cloud Advocate (DevRel) at Microsoft • Works with NGOs

    & Comunities, currently ICT Director at TOFA • I am a hobbist, I enjoy trying out new hobbies I occasionally blog at bethany-jep.com Bethany Jepchumba Microsoft confidential 2
  2. How language models work Natural language input Model Tokens Probability

    distribution Natural language output Decoding + Post-processing Get results Pre-processing
  3. Foundry Local winget install Microsoft.FoundryLocal Design, customize and manage AI

    applications and agents on-device Preview Microsoft confidential 7 brew tap microsoft/foundrylocal brew install foundrylocal Installation Privacy and Security Latency Cost Efficient Low Bandwidth
  4. What is an AI agent? LLM Instructions Tools Agent +

    + An AI agent is a micro-service that takes unstructured messages, optionally invokes other APIs and returns messages/action 1 2 3 Input System events User messages Agent messages 1 Tool calls Knowledge Actions Memory 2 Output Agent messages Tool results 3
  5. MCP Model Context Protocol - Easier to give context to

    models - Optimized communication between LLMs, external tools, data sources and applications - Uses a client-server model for interactions
  6. Generative AI Development Lifecycle Hypo thesis Find LLMs Try prompts

    Manage Customize Design Managing PREPARE FOR APP DEPLOYMENT ADVANCE PROJECT BUSINESS NEED Deploy LLM App/UI Quo ta and cost management REVERT PROJECT C ontent Filtering M onitoring SEND FEEDBACK Prompt Engine ering or Fine-tuning Evalua tion Exceptio n Handling Retrieval Augmente d Generation Prote ct & govern
  7. Evaluators in Azure AI Foundry RAG Retrieval Document Retrieval Groundedness

    Relevance Response Completeness General Purpose Fluency Coherence QA Safety & Security Violence Sexual Self-harm Hate and Unfairness Ungrounded Attributes Code Vulnerability Protected Materials Content Safety Agents Intent Resolution Task Adherence Tool call accuracy
  8. Foundry Observability Dashboard Azure AI Foundry Observability, integrated with Azure

    Monitor Application Insights, enables you to continuously monitor your AI applications
  9. UlizaLlama - 7 B parameter transformer, instruction-tuned for Swahili and

    English dialogue and QA tasks - Fine-tuned via LoRA (Low-Rank Adaptation), then merged back into the base model so it can run stand- alone without adapters - Designed for real-world contexts in healthcare patient support, agriculture Q&A via apps, legal aid bots, educational assistants, tourism tools, public services, retail bots 29
  10. Fastagger - the AI runtime that extends “seeing, deciding, and

    acting” beyond data centers, right onto entry-level Android phones, IoT tablets, and industrial gateways. - Built as a plug-in to Safaricom’s M-PESA Business App, Auni automatically parses mobile-money PDF statements offline and provides personalized customer insights to MSMEs. Launched March 2024, it hit over 2,500 MSME users within weeks, and now powers AI insights across 1 million+ M-PESA devices. 30
  11. AI Agent workflows can enhance efficiency, accuracy, and customer satisfaction

    Key Use Cases Across Industries • Assists employees in booking business trips • Integrates with Tripadvisor, Outlook, and SharePoint • Books via Teams chat or email • Uses OCR to gather receipts • Automates expense report submission and tracking Travel Booking & Expense Management • Personalized onboarding assistant for new hires • Uses LLMs grounded in HR data from SharePoint • Provide relevant training materials • Schedule orientations and set up software accounts • Monitor task completion and ensure efficient onboarding Employee Onboarding • Diagnoses issues by referencing history and product manuals • Provides tailored solutions or escalates through automated workflows • Creates tickets and schedules follow-ups • Updates CRM records, enhancing future support Personalized Customer Support • Analytics data from data lake and data warehouse • Responds to user requests in natural language • Generates insights, visualization, and sends via Teams or email • Automates data handling for real-time, effortless decision-making Data Analytics and Reporting
  12. Resources - Learning resources on GenAI, agents and MCP -

    Getting started with Azure AI - Links to the different tools – foundry local, ai toolkit on VSCode, GitHub Models and GitHub Copilot - Links to different articles and use cases https://bethany-jep.com/events/ai- summit-kenya-2025/