A frame to help you reason through the notebook: concepts, diagrams and the API map. It deliberately does not contain the answers to Questions #1–#4. Instead it gives you the questions to ask yourself and the method to get there. The learning is in running the cells, reading the streamed trace and the message list, and writing your own conclusions.
Notebook:
Agentic_RAG.ipynb(cell numbers = position in the notebook, counting from 0). Corpus:data/HealthWellnessGuide.txt(a short general-wellness guide; not medical advice).
A frame to help you reason through the notebook: concepts, diagrams, and the API map. It deliberately does not contain the answers to the questions or the breakout-room conclusions. Instead it gives you questions to ask yourself and a method to get there. The learning is in running the cells, reading the trace, and writing your own conclusions.
Notebook:
The_Agent_Harness.ipynb(7 tasks, Questions #1–#4, two breakout rooms). Corpus:data/HealthWellnessGuide.txt(a general wellness guide, not medical advice).
PROMPT: let's iteratively build a prompt to help drive the generation of more effective and modular code based on good architecture and design for effective agent harnesses and guardrails... along with python code.
All four views rendered. Here they are, then the answer to the real question.
View 1 — The seam thesis 🎯 Agent Seam Eval Framework
🎨 Open/Edit diagram
mermaid
Concept-first companion to the notebook. Everything here is machinery and mental model — the four questions and both activities are yours to answer, so §13-§15 give you the reasoning path and the code to reread, deliberately not the answers.
Source notebook:
18_SDG_for_Agent_Trajectory_Evals/01_SDG_Agent_Trajectory_Evals.ipynb(41 cells) · README:18_SDG_for_Agent_Trajectory_Evals/README.mdNo GPU and no vector database: the corpus is one markdown file and retrieval is a numpy matmul. Two OpenAI models, one key. Budget ~5 minutes per full harness pass.
A companion to 01_SDG_Agent_Trajectory_Evals.ipynb. It's a run log: the
whole notebook was actually executed against the live OpenAI API, cold, start to
finish — so you have a "known-good" reference for what a healthy run looks like,
what the numbers do, and where people trip. Use it to tell a real problem apart
from expected run-to-run variation.
This is the student version. The setup gotchas and the run log are all here. The graded reasoning is yours: this session has **four questions and
A frame to help you reason through the assignment — concepts, diagrams, and the API map. It deliberately does not contain the answers or filled-in activity code. Instead it gives you the questions to ask yourself and the method to get there. The work — and the learning — is in running the cells, reading the completions your verifier rejected, and writing your own conclusions.
Notebook:
01_RLVR_Verifiable_Rewards.ipynb(34 cells) · README:16_RLVR/README.mdNo corpus and no GPU: the policy is an API model (gpt-4.1-nano) sampled at temperature 1.0.
A frame to help you reason through the assignment — the mental model, the loop diagram, and the map of which cell does what. It deliberately does not contain the answers or write-ups for you. Instead it gives you the questions to ask yourself and the cells to go inspect. The work — and the learning — is in running the training, watching the reward move, and writing your own conclusions.
Notebook:
01_Reasoning_Fine_Tuning_Unsloth_GRPO.ipynbModel:meta-llama/Llama-3.2-3B-Instruct(gated — accept the license andhf auth login, or use the ungatedunsloth/mirror). Dataset:openai/gsm8k.
A companion to this session's notebook, multimodal_rag.ipynb — the one where you
extend text RAG to images + text in one pipeline: a VLM that parses charts into
searchable chunks, three cross-modal retrieval strategies on Qdrant, generation
that reads exact numbers off chart pixels, and a video extension that answers with
timestamp citations. It's a run log: the whole notebook was actually executed —
uv sync, the ~600 MB CLIP download, every VLM call, the recall@3 eval, and the
video answer — so you have a "known-good" reference for what a healthy run looks
like and where people trip. Use it to tell a real problem apart from expected
A frame to help you reason through the assignment — concepts, diagrams, and the API map. It deliberately does not contain the answers or filled-in activity code. Instead it gives you the questions to ask yourself and the cells to go inspect. The work — and the learning — is in running the cells, comparing what actually comes back, and writing your own conclusions.
Notebook:
multimodal_rag.ipynbCorpus:./data— six synthetic ACME Robotics FY2024 charts + six short Markdown docs + one ~45s narrated-slide video (all CC0, auto-generated if missing). The notebook tells you where the real
A companion to this session's notebook, multimodal_rag.ipynb — the one where you
extend text RAG to images + text in one pipeline: a VLM that parses charts into
searchable chunks, three cross-modal retrieval strategies on Qdrant, generation
that reads exact numbers off chart pixels, and a video extension that answers with
timestamp citations. It's a run log: the whole notebook was actually executed —
uv sync, the ~600 MB CLIP download, every VLM call, the recall@3 eval, and the
video answer — so you have a "known-good" reference for what a healthy run looks
like and where people trip. Use it to tell a real problem apart from expected