মধ্যবর্তীকোর্স · বিনামূল্যে
Building with AI Systems
Understand language models, retrieval, agents, evaluation, cost, and deployment safeguards through practical system design.
Loading your course evidence…
ফলাফল
আপনি যা করতে সক্ষম হবেন
- Choose an architecture based on task and evidence needs.
- Evaluate quality, latency, cost, and safety together.
- Design monitoring and incident response before launch.
প্রথমে প্রস্তাবিত: এআই ফাউন্ডেশন, Responsible AI User
পাঠ্যক্রম
কোর্স মডিউল
Language-model systems
ফলাফল: Reason about tokens, context, generation, and model tradeoffs.
অনুশীলন: Compare two model options using quality, latency, context, privacy, and cost.
Language-model mechanicsModels, inference, and limitationsModel cost and operational tradeoffsGrounding with retrieval
ফলাফল: Know when and how retrieval can improve evidence access.
অনুশীলন: Design a retrieval test set with answer and citation requirements.
পুনরুদ্ধার-বর্ধিত প্রজন্মউৎস এবং দাবি যাচাইকরণAgents and tools
ফলাফল: Bound multi-step systems with permissions and checkpoints.
অনুশীলন: Write an agent permission model and failure-recovery path.
Agents, tools, and long-running tasksঅটোমেশন সীমানা এবং সুরক্ষাগুলিএআই নিরাপত্তা এবং অপব্যবহারের ঝুঁকিEvaluation and operations
ফলাফল: Measure system performance before and after deployment.
অনুশীলন: Create an evaluation suite covering quality, refusal, latency, cost, and regressions.
Evaluation and benchmark literacySuccess metrics and monitoringAI incident responseExperiment and pilot design
প্রয়োগ করা ক্যাপস্টোন
AI system design review
Produce an architecture and evaluation plan for a source-grounded AI application.
- Architecture diagram
- Evaluation dataset
- Cost and latency budget
- Security, monitoring, and rollback plan