GenAIWiki

Playbooks

Tutorials

Long-form guides optimized for engineers shipping GenAI features responsibly.

12 min read

Offline vs Online Eval Frequency

This tutorial discusses the trade-offs between offline and online evaluation frequencies for machine learning models, focusing on their impact on model performance and user experience.

Updated 9 days ago
evaluationofflineonline

18 min read

Planner–Executor Loops and Failure Recovery

This tutorial explains the planner-executor loop in AI systems and how to implement effective failure recovery strategies. Prerequisites include knowledge of AI planning algorithms and system design.

Updated 9 days ago
AIsystem designfailure recovery

20 min read

Agent Memory: Scratchpad vs Vector Store

This tutorial compares scratchpad memory and vector store memory in AI agents, focusing on their use cases and performance characteristics. Prerequisites include a basic understanding of AI memory architectures.

Updated 9 days ago
AImemory architectureperformance comparison

15 min read

Runbooks When Quality Regresses Overnight

This tutorial outlines how to create effective runbooks to address overnight quality regressions in software systems. Prerequisites include familiarity with incident management and basic scripting skills.

Updated 9 days ago
runbooksincident managementquality assurance

16 min read

Canary Prompts for Regression Detection

Utilizing canary prompts to detect regressions in language models. Prerequisites include familiarity with regression testing and LLM evaluation metrics.

Updated 9 days ago
regression testingcanary promptsLLM

22 min read

Prompt Injection Defenses in Multi-Tenant Apps

Developing strategies to protect multi-tenant applications from prompt injection attacks. Prerequisites include understanding of security vulnerabilities and multi-tenant architecture.

Updated 9 days ago
securitymulti-tenantprompt injection

18 min read

Observability: Traces for LLM + Tool Spans

Implementing observability practices to trace interactions between large language models (LLMs) and external tools. Prerequisites include knowledge of observability tools and LLM architectures.

Updated 9 days ago
observabilityLLMtracing

20 min read

Sandboxing Tools with Least Privilege

Implementing sandboxing techniques to limit tool access and enhance security. Prerequisites include familiarity with security protocols and system architecture.

Updated 9 days ago
sandboxingsecurityleast privilege

15 min read

Human-in-the-Loop for High-Stakes Actions

Integrating human oversight in automated systems to ensure accuracy and accountability in critical scenarios. Prerequisites include understanding of automation frameworks and risk management principles.

Updated 9 days ago
human-in-the-loopautomationrisk management

20 min read

Graph RAG for Entity-Heavy Domains

Explore the use of Graph Retrieval-Augmented Generation (RAG) for domains with complex entities, requiring knowledge of graph databases and RAG techniques.

Updated 9 days ago
RAGgraph databasesentity recognition

10 min read

Hybrid Search: BM25 + Dense Re-Ranking

This tutorial explores the integration of BM25 and dense re-ranking techniques to enhance search accuracy. Prerequisites include familiarity with information retrieval concepts and basic machine learning.

Updated 9 days ago
searchBM25dense re-ranking

6 min read

PII Handling in Retrieval Pipelines

Effective handling of Personally Identifiable Information (PII) is essential in retrieval systems to ensure compliance and user trust. Prerequisites include knowledge of data privacy regulations and retrieval system architecture.

Updated 9 days ago
data privacyretrieval systemsPII compliance

6 min read

Cost Controls: Batching vs Streaming Tokens

Understanding the trade-offs between batching and streaming token processing can optimize costs in NLP applications. Prerequisites include familiarity with tokenization and processing pipelines.

Updated 9 days ago
cost optimizationNLPtoken processing

18 min read

Golden-Set Design for RAG Faithfulness

Understand how to design a golden set for evaluating the faithfulness of Retrieval-Augmented Generation (RAG) models. Prerequisites include familiarity with RAG systems and evaluation metrics.

Updated 9 days ago
RAGevaluationbenchmarking

15 min read

Embedding Drift Monitoring in Production

Learn how to implement embedding drift monitoring in production systems to ensure model reliability. Prerequisites include familiarity with machine learning models and data pipelines.

Updated 9 days ago
embeddingmonitoringproduction

11 min read

Shadow Traffic for Safe Model Rollouts

Learn how to implement shadow traffic techniques for safely rolling out new models without impacting user experience.

Updated 9 days ago
model rolloutshadow trafficsafety

14 min read

Reducing Hallucinations with Citation Constraints

This tutorial discusses strategies to minimize hallucinations in AI outputs by implementing citation constraints.

Updated 9 days ago
AIhallucinationscitations

12 min read

Structured Outputs vs JSON Mode Tradeoffs

Explore the trade-offs between using structured outputs and JSON mode in APIs, focusing on performance and usability.

Updated 9 days ago
APIperformancedata formats

15 min read

Evaluating Tool-Calling Reliability Under Load

This tutorial provides a framework for assessing the reliability of tool calls in high-load scenarios, ensuring system robustness.

Updated 9 days ago
load testingreliabilityperformance

10 min read

Latency Budgets for Streaming Chat UX

Learn how to define and manage latency budgets to enhance user experience in streaming chat applications, ensuring responsiveness and engagement.

Updated 9 days ago
latencyUXchat

25 min read

Cross-Encoder Re-Rankers at Scale

Understand how to implement cross-encoder re-rankers for large-scale information retrieval systems. Prerequisites include knowledge of ranking algorithms and machine learning.

Updated 9 days ago
re-rankingcross-encoderinformation retrieval

20 min read

Quantization Impact on Retrieval Quality

Explore the effects of quantization on the quality of information retrieval systems. Prerequisites include familiarity with machine learning models and retrieval systems.

Updated 9 days ago
quantizationinformation retrievalmodel optimization

15 min read

Synthetic Data for Classifier Fine-Tunes

Learn how to generate synthetic data to improve classifier performance, especially in scenarios with limited labeled data. Prerequisites include basic understanding of machine learning and data generation techniques.

Updated 9 days ago
synthetic-datamachine-learningclassifier-fine-tuning

16 min read

Chunking Strategies for Legal/Medical PDFs

Learn effective chunking strategies for processing legal and medical PDFs to enhance information retrieval. Prerequisites include familiarity with PDF processing and natural language processing concepts.

Updated 9 days ago
PDF processingchunkingNLP

Publish a tutorial