Skip to content

Conversation

@0xrdan
Copy link

@0xrdan 0xrdan commented Jan 13, 2026

The description claimed Claude begins its rewrite with "Dear Claude" when demonstrating the data/instruction separation issue. Updated to more accurately describe that Claude addresses "Claude" in its rewrite (e.g., "Dear Claude" or similar), since actual output may vary.

Fixes #37

The description claimed Claude begins its rewrite with "Dear Claude" when
demonstrating the data/instruction separation issue. Updated to more accurately
describe that Claude addresses "Claude" in its rewrite (e.g., "Dear Claude" or
similar), since actual output may vary.

Fixes anthropics#37

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
@FacePrintPay
Copy link

using Pydantic models for type-safe Claude tool use interactions.

Transcribe an audio file with Deepgram & use Anthropic to prepare interview questions!
Apr 2024

Integrations
Multimodal
Transcribe audio with Deepgram and generate interview questions using Claude for preparation.

Using the Wolfram Alpha LLM API as a tool with Claude
Apr 2024

Integrations
Tools
Integrate Wolfram Alpha LLM API as Claude tool for computational queries and answers.

Using a calculator tool with Claude
Apr 2024

Tools
Provide Claude with calculator tool for arithmetic operations and mathematical problem solving.

Creating a customer service agent with client-side tools
Apr 2024

Tools
Agent Patterns
Build customer service chatbot with Claude using tools for customer lookup and order management.

Extracting structured JSON using Claude and tool use
Apr 2024

Responses
Tools
Extract structured JSON data from various inputs using Claude's tool use capabilities.

Metaprompt
Mar 2024

Responses
Prompt engineering tool that generates starting prompts for your tasks to solve blank-page problem.

Citations
Mar 2024

Responses
RAG & Retrieval
Enable Claude to provide detailed source citations when answering document-based questions for verification.

Claude 3 RAG agents with LangChain v1
Mar 2024

Integrations
RAG & Retrieval
Agent Patterns
Build RAG agents with Claude 3 using LangChain v1's updated agent framework patterns.

Summarizing web page content with Claude 3 Haiku
Mar 2024

RAG & Retrieval
Fetch and summarize web page content using Claude 3 Haiku via URL extraction.

Using Haiku as a sub-agent
Mar 2024

Agent Patterns
Analyze financial reports using Haiku sub-agents for extraction and Opus for synthesis.

Multi-modal
Mar 2024

Integrations
Multimodal
Use LlamaIndex's Anthropic MultiModal LLM abstraction for image understanding and reasoning.

How to build a RAG system using Claude 3 and MongoDB
Mar 2024

Integrations
RAG & Retrieval
Build chatbot RAG system with Claude and MongoDB using tech news as knowledge base.

Building evals
Mar 2024

Evals
Build robust evaluation systems to measure and improve Claude's performance on key metrics.

Building a moderation filter with Claude
Mar 2024

Responses
Build customizable content moderation filters by defining rules and categories in prompts.

Prompting Claude for "JSON mode"
Mar 2024

Responses
Get reliable JSON output from Claude using effective prompting techniques without constrained sampling.

How to make SQL queries with Claude
Mar 2024

RAG & Retrieval
Generate SQL queries from natural language questions using Claude with database schema context.

Getting started - how to pass images into Claude
Mar 2024

Multimodal
Tutorial on passing images to Claude 3 API for vision-based text analysis.

How to transcribe documents with Claude
Mar 2024

Multimodal
Extract and structure unstructured text from images and PDFs using Claude 3's vision.

Working with charts, graphs, and slide decks
Mar 2024

Multimodal
Extract insights from charts, graphs, and presentations using Claude's vision analysis capabilities.

Multi-document agents
Mar 2024

Integrations
RAG & Retrieval
Agent Patterns
Build RAG for large document collections using DocumentAgents with ReAct Agent pattern.

ReAct agent
Mar 2024

Integrations
Agent Patterns
Tools
Create ReAct agents with LlamaIndex for tool-based reasoning and action workflows.

RAG pipeline with LlamaIndex
Feb 2024

Integrations
RAG & Retrieval
Build basic RAG pipeline with LlamaIndex for document retrieval and question answering.

RouterQuery engine
Feb 2024

Integrations
RAG & Retrieval
Route queries to different indices using LlamaIndex RouterQueryEngine for multi-document search.

SubQuestionQueryEngine
Feb 2024

Integrations
RAG & Retrieval
Decompose complex queries into sub-questions across multiple documents using LlamaIndex engine.

Retrieval-augmented generation using Pinecone
Feb 2024

Integrations
RAG & Retrieval
Connect Claude with Pinecone vector database for retrieval-augmented generation and semantic search.

"Uploading" PDFs to Claude via the API
Aug 2023

RAG & Retrieval
Process and summarize PDF documents using Claude API with text extraction and encoding.

Iteratively searching Wikipedia with Claude
Aug 2023

Integrations
Legacy notebook showing iterative Wikipedia searches with Claude 2 for research workflows."
Cookbook

Claude Cookbook
Practical guides and examples for using Claude effectively
Programmatic tool calling (PTC)
Reduce latency and token consumption by letting Claude write code that calls tools programmatically in the code execution environment.
Tool search with embeddings
Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery.
Automatic context compaction
Manage context limits in long-running agentic workflows by automatically compressing conversation history.
Giving Claude a crop tool for better image analysis
Give Claude a crop tool to zoom into image regions for detailed analysis of charts, documents, and diagrams.
Prompting for frontend aesthetics
Guide to prompting Claude for distinctive, polished frontend designs avoiding generic aesthetics.
Introduction to Claude Skills
Create documents, analyze data, automate workflows with Claude's Excel, PowerPoint, PDF skills.
All Cookbooks

All Categories
Title
Programmatic tool calling (PTC)
Nov 2025

Tools
Reduce latency and token consumption by letting Claude write code that calls tools programmatically in the code execution environment.

Tool search with embeddings
Nov 2025

Tools
RAG & Retrieval
Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery.

Automatic context compaction
Nov 2025

Tools
Agent Patterns
Manage context limits in long-running agentic workflows by automatically compressing conversation history.

Low latency voice assistant with ElevenLabs
Nov 2025

Integrations
Build a low-latency voice assistant using ElevenLabs for speech-to-text and text-to-speech combined with Claude.

Giving Claude a crop tool for better image analysis
Nov 2025

Multimodal
Tools
Give Claude a crop tool to zoom into image regions for detailed analysis of charts, documents, and diagrams.

Prompting for frontend aesthetics
Oct 2025

Responses
Skills
Guide to prompting Claude for distinctive, polished frontend designs avoiding generic aesthetics.

Claude Skills for financial applications
Oct 2025

Skills
Build financial dashboards and portfolio analytics using Claude's Excel, PowerPoint, PDF skills.

Building custom Skills for Claude
Oct 2025

Skills
Create, deploy, and manage custom skills extending Claude with specialized organizational workflows.

Introduction to Claude Skills Oct 2025

Skills Create documents, analyze data, automate workflows with Claude's Excel, PowerPoint, PDF skills.
The one-liner research agent
Sep 2025 •
Claude Agent SDK
Agent Patterns Build a research agent using Claude Code SDK with WebSearch for autonomous research.
The chief of staff agent Sep 2025

Claude Agent SDK
Agent Patterns Build multi-agent systems with subagents, hooks, output styles, and plan mode features.
The observability agent Sep 2025

Claude Agent SDK
Agent Patterns
Connect agents to external systems via MCP servers for GitHub monitoring and CI workflows.
Tool evaluation
Sep 2025 • Evals Run parallel agent evaluations on tools independently from evaluation task files. Usage & cost Admin API cookbook Aug 2025 • Observability Programmatically access and analyze your Claude API usage and cost data via Admin API.
Memory & context management with Claude Sonnet 4.5
May 2025 • Tools
Agent Patterns Build AI agents with persistent memory using Claude's memory tool and context editing.
Speculative prompt caching May 2025
• Responses Reduce time-to-first-token by warming cache speculatively while users formulate their queries. Parallel tool calls on Claude 3.7 Sonnet Mar 2025 •
Tools Enable parallel tool calls on Claude 3.7 Sonnet using batch tool meta-pattern workaround.
Extended thinking
Feb 2025 •
Thinking Use Claude's extended thinking for transparent step-by-step reasoning with budget management. Extended thinking with tool use Feb 2025
• Thinking
Tools
Combine extended thinking with tools for transparent reasoning during multi-step workflows.
Basic workflows
Dec 2024 • Agent Patterns Three simple multi-LLM workflow patterns trading cost or latency for improved performance. Evaluator optimizer Dec 2024 •
Agent Patterns Evals
Workflow pattern using one LLM for generation and another for evaluation feedback loop.
Orchestrator workers
Dec 2024 • Agent Patterns
Central LLM dynamically delegates tasks to worker LLMs and synthesizes their combined results. Batch processing with Message Batches API Oct 2024 •
Responses Process large volumes of Claude requests asynchronously with 50% cost reduction using batches.
Text to SQL with Claude Sep 2024 • RAG & Retrieval Convert natural language queries to SQL using RAG, chain-of-thought, and self-improvement techniques.
Enhancing RAG with contextual retrieval
Sep 2024 •
RAG & Retrieval Improve RAG accuracy by adding context to chunks before embedding with prompt caching.
Finetuning Claude 3 Haiku on Bedrock
Aug 2024 •
Fine-Tuning
Step-by-step guide to finetuning Claude 3 Haiku on Amazon Bedrock for custom tasks.

Generate synthetic test data for your prompt template Aug 2024
• Evals
Generate synthetic test cases to evaluate and improve your Claude prompt templates effectively.

Prompt caching through the Claude API
Aug 2024
• Responses
Cache and reuse prompt context for cost savings and faster responses with detailed instructions.
Summarization with Claude
Aug 2024 •
RAG & Retrieval Responses
Comprehensive guide to summarizing legal documents with evaluation and advanced techniques.
Retrieval augmented generation
Jul 2024 • RAG & Retrieval
Build and optimize RAG systems with Claude using summary indexing and reranking techniques.
Classification with Claude
May 2024
• RAG & Retrieval Build classification systems with Claude using RAG and chain-of-thought for insurance tickets.

Tool choice
May 2024

Tools
Control how Claude selects tools using tool_choice parameter for forced or auto selection.

Using vision with tools
May 2024 •
Multimodal
Tools
Combine Claude's vision with tools to extract structured data from images like nutrition labels.
Sampling responses from Claude beyond the max tokens limit
May 2024

Responses Generate longer responses beyond max_tokens limit using prefill technique with message continuation.
Best practices for using vision with Claude May 2024

Multimodal
Tips and techniques for optimal image processing performance with Claude's vision capabilities.
Note-saving tool with Pydantic and Anthropic tool use
Apr 2024
• Tools
Create validated tools using Pydantic models for type-safe Claude tool use interactions.

Transcribe an audio file with Deepgram & use Anthropic to prepare interview questions! Apr 2024

Integrations
Multimodal
Transcribe audio with Deepgram and generate interview questions using Claude for preparation.
Using the Wolfram Alpha LLM API as a tool with Claude
Apr 2024
• Integrations
Tools
Integrate Wolfram Alpha LLM API as Claude tool for computational queries and answers.

Using a calculator tool with Claude
Apr 2024

Tools
Provide Claude with calculator tool for arithmetic operations and mathematical problem solving.
Creating a customer service agent with client-side tools Apr 2024
• Tools
Agent Patterns
Build customer service chatbot with Claude using tools for customer lookup and order management.

Extracting structured JSON using Claude and tool use
Apr 2024

Responses Tools Extract structured JSON data from various inputs using Claude's tool use capabilities.
Metaprompt
Mar 2024 •
Responses
Prompt engineering tool that generates starting prompts for your tasks to solve blank-page problem.

Citations
Mar 2024

Responses RAG & Retrieval Enable Claude to provide detailed source citations when answering document-based questions for verification.
Claude 3 RAG agents with LangChain v1 Mar 2024

Integrations RAG & Retrieval
Agent Patterns
Build RAG agents with Claude 3 using LangChain v1's updated agent framework patterns.

Summarizing web page content with Claude 3 Haiku
Mar 2024 • RAG & Retrieval
Fetch and summarize web page content using Claude 3 Haiku via URL extraction.
Using Haiku as a sub-agent Mar 2024

Agent Patterns Analyze financial reports using Haiku sub-agents for extraction and Opus for synthesis.

Multi-modal
Mar 2024 •
Integrations
Multimodal Use LlamaIndex's Anthropic MultiModal LLM abstraction for image understanding and reasoning. ~/evidence/stolen_agentik_20260124 $ Skip to content prompt-eng-interactive-tutorial Repository navigation
Code Issues 23
(23) Pull requests 22
(22)
Anthropic's Interactive Prompt Engineering Tutorial
29.1k stars 2.8k forks
236 watching 2 Branches 0 Tags
Activity
Custom properties Public repository anthropics/prompt-eng-interactive-tutorial Name maggie-vo
maggie-vo
2 years ago
AmazonBedrock
2 years ago
Anthropic 1P
2 years ago
.gitignore 2 years ago
README.md
2 years ago Repository files navigation
README
Welcome to Anthropic's Prompt Engineering Interactive Tutorial
Course introduction and goals
This course is intended to provide you with a comprehensive step-by-step understanding of how to engineer optimal prompts within Claude.

After completing this course, you will be able to:
Master the basic structure of a good prompt
Recognize common failure modes and learn the '80/20' techniques to address them
Understand Claude's strengths and weaknesses Build strong prompts from scratch for common use cases Course structure and content
This course is structured to allow you many chances to practice writing and troubleshooting prompts yourself. The course is broken up into 9 chapters with accompanying exercises, as well as an appendix of even more advanced methods. It is intended for you to work through the course in chapter order.

Each lesson has an "Example Playground" area at the bottom where you are free to experiment with the examples in the lesson and see for yourself how changing prompts can change Claude's responses. There is also an answer key.
Note: This tutorial uses our smallest, fastest, and cheapest model, Claude 3 Haiku. Anthropic has two other models, Claude 3 Sonnet and Claude 3 Opus, which are more intelligent than Haiku, with Opus being the most intelligent.
This tutorial also exists on Google Sheets using Anthropic's Claude for Sheets extension. We recommend using that version as it is more user friendly.
When you are ready to begin, go to 01_Basic Prompt Structure to proceed.
Table of Contents Each chapter consists of a lesson and a set of exercises.
Beginner Chapter 1: Basic Prompt Structure

Chapter 2: Being Clear and Direct
Chapter 3: Assigning Roles
Intermediate
Chapter 4: Separating Data from Instructions

Chapter 5: Formatting Output & Speaking for Claude

Chapter 6: Precognition (Thinking Step by Step)
Chapter 7: Using Examples

Advanced
Chapter 8: Avoiding Hallucinations
Chapter 9: Building Complex Prompts (Industry Use Cases)
Complex Prompts from Scratch - Chatbot Complex Prompts for Legal Services
Exercise: Complex Prompts for Financial Services
Exercise: Complex Prompts for Coding
Congratulations & Next Steps
Appendix: Beyond Standard Prompting

Chaining Prompts Tool Use
Search & Retrieval
Releases
No releases published
Packages No packages published
Contributors
2 @maggie-vo
maggie-vo Maggie
@jawhnycooke
jawhnycooke Jawhny Cooke
Languages
Jupyter Notebook
98.1%

Python
1.9%
Footer
© 2026 GitHub, Inc.
Footer navigation
Terms
Privacy
Security
Status
Community
Docs
Contact
Manage cookies
Do not share my personal information
No command Skip found, did you mean:
Command gzip in package gzip Command hzip in package hunspell Command ip in package iproute2
Command lzip in package lzip
Command mzip in package mtools
Command pip in package python-pip Command rip in package rip2
Command zip in package zip
prompt-eng-interactive-tutorial: command not found
Repository: command not found No command Code found, did you mean: Command code in package code-is-code-oss Command node in package nodejs Command node in package nodejs-lts Command ode in package plotutils No command Issues found, did you mean: Command sshfs in package sshfs No command 23 found, did you mean: Command i3 in package i3 Command h3 in package libuber-h3 Command z3 in package z3 No command 23 found, did you mean:
Command i3 in package i3 Command h3 in package libuber-h3
Command z3 in package z3 No command Pull found, did you mean: Command kill in package coreutils
Command curl in package curl Command fulla in package hugin Command uil in package motif
Command qhull in package qhull Command ul in package util-linux No command 22 found, did you mean:
Command r2 in package radare2 No command 22 found, did you mean: Command r2 in package radare2
bash: Anthropics Interactive Prompt Engineering Tutorial 29.1k stars 2.8k forks
236 watching 2 Branches 0 Tags
Activity Custom properties
Public repository anthropics/prompt-eng-interactive-tutorial
Name maggie-vo maggie-vo 2 years ago AmazonBedrock 2 years ago
Anthropic 1P 2 years ago
.gitignore
2 years ago README.md
2 years ago Repository files navigation
README Welcome to Anthropics: No such file or directoryNo command Course found, did you mean: Command bore in package bore Command cuse in package cuse Command goose in package goose Command hors in package hors Command burst in package mailutils Command bounce in package mesa-demos
Command route in package net-tools Command burst in package nmh
Command double in package plotutils Command pounce in package pounce
Command more in package util-linux No command This found, did you mean:
Command hls in package hfsutils Command vis in package vis Command whois in package whois
Command xhs in package xh No command After found, did you mean: Command axfer in package alsa-utils Command aterm in package aterm
Command attr in package attr Command pager in package bat
Command bftpd in package bftpd Command pager in package busybox Command ctr in package containerd
Command date in package coreutils Command dte in package dte Command over in package enscript Command entr in package entr
Command typer in package erlang Command feh in package feh Command flex in package flex Command gitea in package gitea
Command refer in package groff Command hexer in package hexer
Command hnterm in package hnterm Command hstr in package hstr
Command ftp in package inetutils Command jftui in package jftui
Command jstar in package joe
Command jstar in package jupp
Command kate in package kate Command pager in package less
Command lexter in package lexter
Command lftp in package lftp
Command plser in package libgnustep-base
Command paper in package libpaper
Command lite in package litespeedtest
Command mazter in package mazter Command pager in package moor
Command ifne in package moreutils
Command pager in package most Command mxtar in package mtools
Command mtr in package mtr
Command mutter in package mutter
Command jfr in package openjdk-17 Command jfr in package openjdk-21 Command jfr in package openjdk-25
Command orted in package openmpi Command sftp in package openssh Command ptar in package perl Command free in package procps Command fuser in package psmisc Command pterm in package putty Command sfeed in package sfeed Command sorter in package sleuthkit Command step in package step-cli Command tar in package tar Command tea in package tea Command tere in package tere Command detex in package texlive-bin
Command tor in package tor Command pager in package util-linux
Command pager in package w3m Command ztee in package zmap No command Master found, did you mean:
Command bastet in package bastet Command paste in package coreutils Command jasper in package libjasper-utils
Command mazter in package mazter Command pastel in package pastel Command wasmer in package wasmer
Recognize: command not found Understand: command not found No command Note: found, did you mean:
Command bore in package bore Command boxes in package boxes Command code in package code-is-code-oss Command date in package coreutils Command dnote in package dnote
Command doge in package doge Command dotnet in package dotnet-host-8.0 Command dotnet in package dotnet-host-9.0
Command dte in package dte Command over in package enscript
Command gitea in package gitea Command gotop in package gotop
Command gotty in package gotty Command dot in package graphviz Command routel in package iproute2 Command joe in package joe Command jove in package jove Command joe in package jupp
Command kate in package kate Command lite in package litespeedtest
Command not in package llvm-tools
Command love in package love Command toe in package ncurses-utils
Command route in package net-tools Command node in package nodejs
Command node in package nodejs-lts Command oleo in package oleo Command orted in package openmpi Command ode in package plotutils Command poke in package poke Command rnote in package rnote Command roqet in package roqet Command sorter in package sleuthkit Command step in package step-cli
Command tea in package tea Command detex in package texlive-bin
Command tokei in package tokei Command more in package util-linux
Command ztee in package zmap > ^C
~/evidence/stolen_agentik_20260124 $

@0xrdan
Copy link
Author

0xrdan commented Jan 24, 2026

@FacePrintPay ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

04_Separating_Data_and_Instructions.ipynb, panel [3]: incorrect description of response.

2 participants