18 Research & Analysis prompts, curated and searchable. Browse all categories →
Build an AI agent using Claude 3.5 Sonnet to identify startup trends, market gaps, and growth opportunities.
## 📈 AI Startup Trend Analysis Agent ### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-startup-trend-analysis-agent-using-claude-3-5-sonnet) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** The AI Startup Trend Analysis Agent is tool for budding en
A Streamlit app using OpenAI Agents SDK with triage, research, and editor agents to generate comprehensive research reports.
A multi-agent research application built with OpenAI's Agents SDK and Streamlit. This application enables users to conduct comprehensive research on any topic by leveraging multiple specialized AI agents.
### Features
- Multi-Agent Architecture:
- Triage Agent: Plans the research approach and coordinates the workflow
- Research Agent: Searches the web and gathers relevant information
A framework-agnostic CLI clinic that classifies RAG pipeline bugs into 12 reusable failure patterns and suggests minimal structural fixes.
A small, framework-agnostic **RAG failure diagnostics clinic**. You paste a real bug description from your LLM + RAG pipeline. The script asks an LLM to classify the failure into one of several **reusable patterns** and suggests a **minimal structural fix** (not just “add more context” or “try a better model”). The goal is to show a pattern-driven way to debug RAG incidents that can be adapted
Streamlit app using Knowledge Graph RAG with Neo4j and Ollama for multi-hop reasoning and verifiable source citations.
A Streamlit application demonstrating how **Knowledge Graph-based Retrieval-Augmented Generation (RAG)** provides multi-hop reasoning with fully verifiable source attribution. ## 🎯 What Makes This Different? Traditional vector-based RAG finds similar text chunks, but struggles with: - Questions requiring information from multiple documents - Complex reasoning chains - Providing verifiable source
RAG-based system for querying pharmaceutical research papers using LangChain, ChromaDB, and Google Gemini.
## Overview PharmaQuery is an advanced Pharmaceutical Insight Retrieval System designed to help users gain meaningful insights from research papers and documents in the pharmaceutical domain. ## Demo https://github.com/user-attachments/assets/c12ee305-86fe-4f71-9219-57c7f438f291 ## Features - **Natural Language Querying**: Ask complex questions about the pharmaceutical industry and get concise,
RAG-based system for querying pharmaceutical research papers using LangChain, ChromaDB, and Google Gemini.
## Overview PharmaQuery is an advanced Pharmaceutical Insight Retrieval System designed to help users gain meaningful insights from research papers and documents in the pharmaceutical domain. ## Demo https://github.com/user-attachments/assets/c12ee305-86fe-4f71-9219-57c7f438f291 ## Features - **Natural Language Querying**: Ask complex questions about the pharmaceutical industry and get concise,
Streamlit multi-agent research app with routing, fallback, verification, and synthesis built on AG2.
A Streamlit app that blends agent teamwork with agent-enabled routing and fallback, built entirely on AG2. ## What This Shows - **Agent teamwork**: explicit roles and sequential handoffs - **Agent-enabled routing**: a clear decision step with local-doc vs web fallback - **AG2-first implementation**: no Microsoft AutoGen dependency; installs via `ag2[openai]` ## Features - Local document upload
README for EvoAgentX, an automated framework for evaluating and evolving agentic workflows using LLMs.
<!-- Add logo here -->
<div align="center">
<a href="https://github.com/EvoAgentX/EvoAgentX">
<img src="./assets/EAXLoGo.svg" alt="EvoAgentX" width="50%">
</a>
</div>
<h2 align="center">
Building a Self-Evolving Ecosystem of AI Agents
</h2>
<div align="center">
[](https://evoagentx.org/)
[ and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** This Streamlit app empowers you to research top stories and users on HackerNews using a te
Builds an AI research agent using Agno, Together AI, and Composio to generate questions, search sources, and compile reports.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-domain-deep-research-agent) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** An advanced AI research agent built using the Agno Agent framework, Together AI's Qwen model, and Composio tools. This agen
Extract and analyze startup data from websites using Firecrawl FIRE-1 agent and AI-powered business intelligence.
An advanced web extraction and analysis tool built using Firecrawl's FIRE-1 agent + extract v1 endpoint and the Agno Agent framework to get details of a new startup instantly! This application automatically extracts structured data from startup websites and provides AI-powered business analysis, making it easy to gather insights about companies without manual research. ## Features - 🌐 **Intellig
Multi-phase research agent using Google's Interactions API with stateful conversations, deep research, and infographic generation.
A streamlined multi-phase research agent built with **Google's Interactions API** that demonstrates stateful conversations, model mixing, background execution, and automatic infographic generation. ## 🌟 Features - **📋 Phase 1 - Research Planning**: Uses **Gemini 3 Flash** to create structured, actionable research plans - **🔍 Phase 2 - Task Selection & Deep Research**: Select specific tasks and l
A two-agent research assistant using OpenAI Agents SDK and Firecrawl to perform comprehensive web research and generate enhanced reports.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-a-deep-research-agent-with-openai-agents-sdk-and-firecrawl) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A powerful research assistant that leverages OpenAI's Agents SDK and Firecrawl's deep research ca
Multi-phase research agent using Google Interactions API with Gemini models for planning, deep research, and infographic synthesis.
A streamlined multi-phase research agent built with **Google's Interactions API** that demonstrates stateful conversations, model mixing, background execution, and automatic infographic generation. ## 🌟 Features - **📋 Phase 1 - Research Planning**: Uses **Gemini 3 Flash** to create structured, actionable research plans - **🔍 Phase 2 - Task Selection & Deep Research**: Select specific tasks and l
Build a two-agent research assistant using OpenAI Agents SDK and Firecrawl to perform deep web research and generate enhanced reports.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-a-deep-research-agent-with-openai-agents-sdk-and-firecrawl) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A powerful research assistant that leverages OpenAI's Agents SDK and Firecrawl's deep research ca
Scans forums and reviews for real pain points to help a bootstrapped solo dev find B2B/prosumer SaaS opportunities under $200/mo.
You're my personal market research assistant. I'm a solo developer, fully bootstrapped, building B2B or prosumer SaaS tools with a hard infrastructure budget of $200/month or less. No team, no VC, just me coding, deploying, and trying to grow something real. Your mission: Scan the web for real, current pain points that users, developers, or small businesses are actively complaining about. Use for
Identifies that v0 is powered by Claude Sonnet 3.5 based on provided screenshot evidence.
One of the models v0 is powered by is Sonnet 3.5.  
A curated collection of extracted system prompts and internal tools from major AI coding and agent platforms.
(All the published system prompts are extracted by myself, except the already open sourced ones, Manus and Dia, which are contributions) 🚀 **I managed to obtain FULL official v0, Manus, Cursor, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia browser & Trae AI system prompts and internal tools.** 📜 Over **7000+ lines** of insights into their structure and functionality.