Skip to content

Instantly share code, notes, and snippets.

@donbr
donbr / aie11-session4-ag-rag-cs.md
Last active November 18, 2026 22:28
Session 4 — Agentic RAG From Scratch

Session 4 Cheat Sheet — Agentic RAG From Scratch

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).

@donbr
donbr / aie11-session3-agent-harness-cs-v2.md
Last active November 16, 2026 22:29
Session 3 — The Agent Harness

Session 3 Cheat Sheet — The Agent Harness

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).

@donbr
donbr / session18-agent-seam-eval-framework.md
Last active July 31, 2026 00:41
Agent Seam Eval Framework

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

@donbr
donbr / session18-sdg-agent-trajectory-evals-cs.md
Created July 30, 2026 23:47
Session 18 Cheat Sheet — Synthetic Data Generation for Agent Trajectory Evals

Session 18 Cheat Sheet — Synthetic Data Generation for Agent Trajectory Evals

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.md No 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.

@donbr
donbr / session18-sdg-sgent-trajectory-evals-lj.md
Created July 30, 2026 23:37
Session 18 — SDG for Agent Trajectory Evals: Learning Journey

Session 18 — SDG for Agent Trajectory Evals: Learning Journey (Student Version)

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

@donbr
donbr / session16-rlvr-cheatsheet.md
Created July 24, 2026 00:49
Session 16 Cheat Sheet — RLVR (Reinforcement Learning with Verifiable Rewards)

Session 16 Cheat Sheet — RLVR (Reinforcement Learning with Verifiable Rewards)

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.md No corpus and no GPU: the policy is an API model (gpt-4.1-nano) sampled at temperature 1.0.

@donbr
donbr / session15-cheatsheet-reasoning-model-finetuning.md
Last active July 22, 2026 00:29
Session 15 Cheat Sheet — Reasoning Model Fine

Session 15 Cheat Sheet — Reasoning Model Fine-Tuning with GRPO

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.ipynb Model: meta-llama/Llama-3.2-3B-Instruct (gated — accept the license and hf auth login, or use the ungated unsloth/ mirror). Dataset: openai/gsm8k.

@donbr
donbr / session14-multi-model-rag-vlm.md
Last active July 17, 2026 02:23
Multi-Modal RAG with Vision-Language Models: Learning Journey

Session 14 — Multi-Modal RAG with Vision-Language Models: Learning Journey (Student Version)

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

@donbr
donbr / session14-mmrag-cheat-sheet.md
Last active July 17, 2026 02:17
Session 14 Cheat Sheet — Multimodal RAG

Session 14 Cheat Sheet — Multimodal RAG

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.ipynb Corpus: ./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

@donbr
donbr / multi-model-rag-vlm.md
Created July 16, 2026 23:45
Multi-Modal RAG with Vision-Language Models

Session 14 — Multi-Modal RAG with Vision-Language Models: Learning Journey (Student Version)

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