AI Engineering Buildcamp: From RAG to Agents
Год выпуска: 6/2026
Производитель: Maven
Сайт производителя:
https://maven.com/alexey-grigorev/from-rag-to-agents
Автор: Alexey Grigorev
Продолжительность: 53h 0m 53s
Тип раздаваемого материала: Видеоурок
Язык: Английский
Субтитры: Отсутсвуют
Описание:
Build your own Agentic AI Assistant
This course takes you from core concepts to production-grade AI systems through hands-on, project-focused modules.
- LLMs & RAG
Learn Large Language Models and Retrieval-Augmented Generation. Build conversational agents using the OpenAI SDK and create data-processing pipelines.
Outcome: A RAG pipeline with real data.
- Agentic Flows + MCP
Add agentic behavior with function calling, using libraries like PydanticAI, and Agents SDK. Expose tools via MCP.
Outcome: A capable, tool-using agents.
- Testing & Evaluation
Improve through testing and offline evaluation. Use LLMs as judges to compare approaches. Learn tools like Evidently and LangWatch.
Outcome: A thoroughly tested and evaluated assistant.
- Monitoring & Guardrails
Use Grafana, Pydantic Logfire and OpenTelemetry for observability and safety.
Outcome: Real-time monitoring.
- Use Cases
Create two agents: a website generator and a code reviewer. Learn about other use cases.
- Capstone
Build an end-to-end AI application with your data.
Outcome: A portfolio-ready project.
Hackathon: Collaborate on real-world problems.
By the end, you will: build, evaluate and monitor a smart assistant; create deep research and coding agents; have a polished portfolio project
What you’ll learn
Create your own production-ready AI application in 6 weeks
🛠️
Build a Fully Functional AI Assistant from Scratch
- A conversational AI assistant that answers questions from GitHub repositories, YouTube transcripts, or internal documentation.
- Use Retrieval-Augmented Generation and the OpenAI API.
🤖
Add Agentic Behavior to Your AI Systems
- Build systems that can reason, make decisions, and take actions with function calling.
- Use tools like PydanticAI and OpenAI’s Agent SDK.
- Extend the capabilities of your agent with MCP.
🔧
Use Testing and Evaluation to Improve Prompts and Results
- Test the application with unit tests and judges.
- Learn how to evaluate your application with ranking metrics, simulate user queries, and use LLMs to judge outputs.
- Select the best prompt, model and chunking strategy using the data-driven approach.
📈
Monitor Your Application
- Set up real-world monitoring using Grafana, Pydantic Logfire, Evidently, and LangWatch.
- Track costs and token usage in real-time.
- Add guardrails to prevent the application misuse.
🔧
Build 8+ Projects
- FAQ Assistant, YouTube Video Q&A system, Wikipedia search and summary system, and a documentation agent.
- AI Coding agent, Deep Research agent and a Code Evaluator agent.
- Two more projects: capstone and hackathon at the end.
🎓
Ship a Capstone AI Project — Start to Finish
- Design and build your own end-to-end AI application from scratch.
- This could be anything from a resume reviewer to a podcast summarizer — fully tested, evaluated and monitored.
About the Author: Alexey Grigorev
15 years of experience. Teaching AI and Data to 100k+ students
Founder of DataTalks.Club · Creator of the Zoomcamp Series · ML Engineer & Author
Alexey Grigorev is the founder of DataTalks.Club and the creator of the Zoomcamp series. With 15 years of experience in software engineering and over 12 years in machine learning, he has built and deployed large-scale ML systems at startups and enterprises.
An advocate for practical, hands-on education, Alexey has taught over 100,000 students with the code-first approach to help learners build real-world skills.
In the past, he was an active participant in data science competitions. A Kaggle Master, Alexey has achieved top rankings in several challenges, including NIPS'17 Criteo Challenge and WSDM Cup 2017: Vandalism Detection.
He is the author of several technical books, including Machine Learning Bookcamp.
Формат видео: MP4
Видео: avc, 1920x1080, 16:9, 30.000 к/с, 806 кб/с
Аудио: aac lc, 48.0 кгц, 128 кб/с, 1 аудио
MediaInfo
General
Complete name : Z:\0. new\Maven - AI Engineering Buildcamp From RAG to Agents (6.2026)\014 AIEBC 01-03-02 - Structured Output for Documentation RAG.mp4
Format : MPEG-4
Format profile : Base Media
Codec ID : isom (isom/iso2/avc1/mp41)
File size : 246 MiB
Duration : 36 min 31 s
Overall bit rate : 943 kb/s
Frame rate : 30.000 FPS
Writing application : Lavf60.16.100
Video
ID : 1
Format : AVC
Format/Info : Advanced Video Codec
Format profile : High@L4
Format settings : CABAC / 4 Ref Frames
Format settings, CABAC : Yes
Format settings, Reference frames : 4 frames
Codec ID : avc1
Codec ID/Info : Advanced Video Coding
Duration : 36 min 31 s
Bit rate : 806 kb/s
Width : 1 920 pixels
Height : 1 080 pixels
Display aspect ratio : 16:9
Frame rate mode : Constant
Frame rate : 30.000 FPS
Color space : YUV
Chroma subsampling : 4:2:0
Bit depth : 8 bits
Scan type : Progressive
Bits/(Pixel*Frame) : 0.013
Stream size : 210 MiB (85%)
Writing library : x264 core 164
Encoding settings : cabac=1 / ref=3 / deblock=1:0:0 / analyse=0x3:0x113 / me=hex / subme=7 / psy=1 / psy_rd=1.00:0.00 / mixed_ref=1 / me_range=16 / chroma_me=1 / trellis=1 / 8x8dct=1 / cqm=0 / deadzone=21,11 / fast_pskip=1 / chroma_qp_offset=-2 / threads=34 / lookahead_threads=5 / sliced_threads=0 / nr=0 / decimate=1 / interlaced=0 / bluray_compat=0 / constrained_intra=0 / bframes=3 / b_pyramid=2 / b_adapt=1 / b_bias=0 / direct=1 / weightb=1 / open_gop=0 / weightp=2 / keyint=250 / keyint_min=25 / scenecut=40 / intra_refresh=0 / rc_lookahead=40 / rc=crf / mbtree=1 / crf=23.0 / qcomp=0.60 / qpmin=0 / qpmax=69 / qpstep=4 / ip_ratio=1.40 / aq=1:1.00
Codec configuration box : avcC
Audio
ID : 2
Format : AAC LC
Format/Info : Advanced Audio Codec Low Complexity
Codec ID : mp4a-40-2
Duration : 36 min 30 s
Source duration : 36 min 30 s
Bit rate mode : Constant
Bit rate : 128 kb/s
Channel(s) : 1 channel
Channel layout : M
Sampling rate : 48.0 kHz
Frame rate : 46.875 FPS (1024 SPF)
Compression mode : Lossy
Stream size : 33.4 MiB (14%)
Source stream size : 33.4 MiB (14%)
Default : Yes
Alternate group : 1
