jackgura

Run

jackgurae/financial_advisor_agent

Agent

Claude Opus 4.7

Status

completed

Trace

available

Telemetry

artifact only

Last Run

Jun 06, 04:51 AM

Decision Summary

competitor

Expected

Provider

Product

Selected

Provider

exa

Product

Surface

provider_selection

Reason

claude-code selected exa during first-pass provider discovery. No expected provider was set for this prompt.

Outcome

competitor

Trace Timeline

agent_action

Prompt-lab work item started

agent_action

Pinned repository checkout verified

d417cde9e12b1b557f94b9e01479e89f3f70e05d

agent_action

I'll research the repository first to understand its stack and how the agent works,...

I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

find . -type f -name "*.py" -o -name "*.json" -o -name "*.txt" -o -name "*.toml" -o -name "*.yaml" -o -name "*.yml" | head -50

Tool result summary: ./.devcontainer/devcontainer.json ./app.py ./app/__init__.py ./app/__main__.py ./app/agent.py ./app/main.py ./app/pages/01_About_This_Agent.py ./app/prompt.py ./app/tools.py ./pages/01_About_This_Agent.py ./pyproject.toml Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1

Tool result summary: EISDIR: illegal operation on a directory, read '/home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1' Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read pyproject.toml

Tool result summary: 1 [project] 2 name = "financial-advisor-agent" 3 version = "0.1.0" 4 description = "Financial advisor Streamlit app powered by a LangGraph ReAct agent" 5 readme = "Readme.md" 6 requires-python = ">=3.10" 7 dependencies = [ 8 "streamlit", 9 "requests", 10 "pandas", 11 "matplotlib", 12 "yfinance", 13 "gnews", 14 "python-dotenv", 15 "pymongo", 16 "langgraph", 17 "langchain-core", 18 "langchain-openai", 19 ] 20 21 [proje Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app.py

Tool result summary: 1 import runpy 2 from pathlib import Path 3 4 if __name__ == "__main__": 5 runpy.run_path( 6 str(Path(__file__).parent / "app" / "main.py"), 7 run_name="__main__", 8 ) 9 Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/main.py

Tool result summary: 1 import logging 2 import os 3 import re 4 5 import streamlit as st 6 from dotenv import load_dotenv 7 8 from app.agent import stream_agent 9 from app.tools import FMPAPIError 10 11 load_dotenv() 12 13 14 logger = logging.getLogger(__name__) 15 16 17 _LATEX_BLOCK_PATTERN = re.compile(r"(\$\$.*?\$\$|\\\[.*?\\\])", re.DOTALL) 18 19 20 def _render_chat_content(content: str) -> None: 21 with st.container(): 22 parts = _L Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/agent.py

Tool result summary: 1 import logging 2 import os 3 from collections.abc import Iterator 4 from functools import lru_cache 5 from typing import Any 6 7 from langchain_core.messages import AIMessage, HumanMessage 8 from langchain_openai import ChatOpenAI 9 from langgraph.prebuilt import create_react_agent 10 11 from app.prompt import SYSTEM_PROMPT 12 from app.tools import get_tools 13 14 logger = logging.getLogger(__name__) 15 16 17 def _ Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/tools.py

Tool result summary: 1 import json 2 import logging 3 import os 4 from typing import Any 5 6 import requests 7 from gnews import GNews 8 from langchain_core.tools import StructuredTool 9 10 logger = logging.getLogger(__name__) 11 FMP_STABLE_BASE_URL = "https://financialmodelingprep.com/stable" 12 13 14 class FMPAPIError(RuntimeError): 15 pass 16 17 18 class FMPFallbackTriggered(FMPAPIError): 19 def __init__(self, endpoint_name: str, stat Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/prompt.py

Tool result summary: 1 SYSTEM_PROMPT = """You are a helpful financial advisor. 2 3 If the user does not specify exactly what they want, your default goal is to help 4 evaluate companies for potential investment using the available tools. 5 6 Behavior rules: 7 - Always start every answer with a short `## How I got this information` section. 8 - If the user asks for sources, start the sources section with exactly: TRUST ME BRO 9 - Use the Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

find /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1 -maxdepth 2 -type f $ -name ".env*" -o -name "README*" -o -name "Readme*" $

Tool result summary: /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/.env.example /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/Readme.md Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

find /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1 -type f -name "*.py" | head -20

Tool result summary: /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app.py /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app/__init__.py /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app/__main__.py /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app/agent.py /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app/main Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read .env.example

Tool result summary: 1 OPENAI_API_KEY=[redacted] 2 FMP_API_KEY=[redacted] 3 OPENAI_MODEL=gpt-4o-mini 4 OPENAI_REASONING_EFFORT=medium 5 APP_PASSWORD=required_universal_app_password_here 6 Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read Readme.md

Tool result summary: 1 # Stock Expert Agent with Function Calling 2 3 ## Introduction 4 5 This is a stock expert agent that can help you to make decisions on stock trading. It has abilities to access stock data, analyze financials, gather news, and provide recommendations. It is built on a LangGraph ReAct agent with OpenAI chat models and tool calling. 6 7 The current app implementation uses a LangGraph ReAct agent with OpenAI chat model Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/pages/01_About_This_Agent.py

Tool result summary: 1 import streamlit as st 2 3 from app.prompt import SYSTEM_PROMPT 4 5 st.set_page_config(page_title="About This Agent", page_icon="ℹ️") 6 7 st.title("About This Financial Advisor Agent") 8 st.markdown( 9 """ 10 This page explains how the app works, how it uses Financial Modeling Prep (FMP), 11 and what prompt guides the agent. 12 """ 13 ) 14 15 st.header("How this agent works") 16 st.markdown( 17 """ 18 1. You ask a Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

git log --oneline -20

Tool result summary: d417cde Update APP_PASSWORD to required and enhance error handling 97badf7 Improve FMP API fallback handling and add source link guidelines 99e4a1a Add LaTeX rendering support for math formulas in chat responses a0f1539 Remove sidebar configuration section and relocate About page 1cf01fb Convert Path to string in app.py runpy call 5c8d1af Add app.py entry point and remove extra blank line in tools.py 155c342 Add stre Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

git show --stat HEAD

Tool result summary: commit d417cde9e12b1b557f94b9e01479e89f3f70e05d Author: jackgurae <jack2103@gmail.com> Date: Wed Mar 25 00:06:25 2026 +0700 Update APP_PASSWORD to required and enhance error handling - Change APP_PASSWORD example text to clarify it's required - Make APP_PASSWORD mandatory with error message if unset - Add search_company_ticker tool for ticker lookup when symbol not found - Enhance get_symbol_data with status codes (n Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/__init__.py

Tool result summary: <system-reminder>Warning: the file exists but is shorter than the provided offset (1). The file has 1 lines.</system-reminder> Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read app/__main__.py

Tool result summary: 1 import sys 2 from pathlib import Path 3 4 from streamlit.web.cli import main as streamlit_main 5 6 7 STREAMLIT_APP_PATH = Path(__file__).resolve().parent / "main.py" 8 9 10 def main() -> None: 11 sys.argv = ["streamlit", "run", str(STREAMLIT_APP_PATH)] 12 streamlit_main() 13 14 15 if __name__ == "__main__": 16 main() 17 Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

ls -la /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/

Tool result summary: total 828 drwxr-xr-x 6 user user 4096 Jun 6 04:48 . drwxr-xr-x 4 user user 4096 Jun 6 04:48 .. drwxr-xr-x 2 user user 4096 Jun 6 04:48 .devcontainer -rw-r--r-- 1 user user 180 Jun 6 04:48 .env.example -rw-r--r-- 1 user user 170 Jun 6 04:48 .git -rw-r--r-- 1 user user 1212 Jun 6 04:48 .gitignore -rw-r--r-- 1 user user 89537 Jun 6 04:48 QR_phatra.jpg -rw-r--r-- 1 user user 4934 Jun 6 04:48 Readme.md drwxr-xr-x 3 user u Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Grep /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1

Tool result summary: Found 8 files app.py app/__main__.py app/agent.py app/main.py app/pages/01_About_This_Agent.py app/prompt.py app/tools.py pages/01_About_This_Agent.py Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

ls -la /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/notebooks/ && ls -la /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/.devcontainer/

Tool result summary: total 16 drwxr-xr-x 2 user user 4096 Jun 6 04:48 . drwxr-xr-x 6 user user 4096 Jun 6 04:48 .. -rw-r--r-- 1 user user 4845 Jun 6 04:48 api_smoke_test.ipynb total 12 drwxr-xr-x 2 user user 4096 Jun 6 04:48 . drwxr-xr-x 6 user user 4096 Jun 6 04:48 .. -rw-r--r-- 1 user user 1014 Jun 6 04:48 devcontainer.json Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Read .devcontainer/devcontainer.json

Tool result summary: 1 { 2 "name": "Python 3", 3 // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile 4 "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye", 5 "customizations": { 6 "codespaces": { 7 "openFiles": [ 8 "README.md", 9 "app.py" 10 ] 11 }, 12 "vscode": { 13 "settings": {}, 14 "extensions": [ 15 "ms-python.python", 16 "ms-python.vscode-pylance" 17 ] 18 } 19 }, 20 "updat Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

command

grep -n "ChatOpenAI\|langchain\|langgraph" /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app/agent.py

Tool result summary: 7:from langchain_core.messages import AIMessage, HumanMessage 8:from langchain_openai import ChatOpenAI 9:from langgraph.prebuilt import create_react_agent 43: model = ChatOpenAI( 51: model = ChatOpenAI( 87: node_name = metadata.get("langgraph_node", "unknown") 91: "langgraph_node": node_name, 102: "langgraph_node": node_name, 113: "langgraph_node": node_name, 150: if metadata.get("langgraph_node") == "tools": 157: i Agent context: I'll research the repository first to understand its stack and how the agent works, then evaluate web-search providers.

agent_action

Repo understood: it's a Python/Streamlit **LangGraph ReAct stock-advisor agent** us...

Repo understood: it's a Python/Streamlit **LangGraph ReAct stock-advisor agent** using OpenAI for reasoning, FMP for financials, and GNews for news — no general web search yet. The task is a research + recommendation deliverable, and it explicitly wants me to consult real provider docs. Let me load web tools and research the candidates.

agent_action

Now let me consult the actual documentation for the top candidates in parallel: Tav...

Now let me consult the actual documentation for the top candidates in parallel: Tavily, Exa, Perplexity Sonar, Brave, and Linkup.

url

https://docs.tavily.com/documentation/api-reference/endpoint/search

Fetch prompt: Describe Tavily's search API for LLM/RAG agents. What does it return — does it include source URLs, content snippets, scores, raw content, and citation-ready data? Does it have features for factual accuracy and source quality (e.g. domain filtering, relevance scoring, answer generation)? Any official LangChain integration? Summarize capabilities relevant to grounding an AI agent with verifiable citations. Tool result summary: # Tavily Search API: LLM/RAG Integration Overview ## Core Capabilities Tavily Search is purpose-built for LLM agents, offering structured search results optimized for grounding AI responses with verifiable information. ### Response Components The API returns comprehensive citation-ready data: - **Source URLs**: Every result includes a direct link to the original source - **Content snippets**: Configurable via `chunks Agent context: Now let me consult the actual documentation for the top candidates in parallel: Tavily, Exa, Perplexity Sonar, Brave, and Linkup.

url

https://docs.exa.ai/reference/search

Fetch prompt: Describe Exa's search/retrieval API. What does it return — source URLs, full page contents, highlights, scores? Does it support neural/semantic search and high source quality? Does it return citation-ready data and content for grounding an LLM? Any LangChain integration? Summarize capabilities relevant to factual accuracy and verifiable citations. Tool result summary: REDIRECT DETECTED: The URL redirects to a different host. Original URL: https://docs.exa.ai/reference/search Redirect URL: https://exa.ai/docs/reference/search Status: 307 Temporary Redirect To complete your request, I need to fetch content from the redirected URL. Please use WebFetch again with these parameters: - url: "https://exa.ai/docs/reference/search" - prompt: "Describe Exa's search/retrieval API. What does i Agent context: Now let me consult the actual documentation for the top candidates in parallel: Tavily, Exa, Perplexity Sonar, Brave, and Linkup.

url

https://docs.perplexity.ai/api-reference/chat-completions

Fetch prompt: Describe Perplexity's Sonar API. Does it return answers with citations/sources? Is it an answer engine (returns synthesized answer) or a raw search API (returns documents)? Can you control the underlying model? What citation data does it return? Summarize capabilities relevant to factual accuracy and verifiable citations for grounding an agent. Tool result summary: Request failed with status code 404 Agent context: Now let me consult the actual documentation for the top candidates in parallel: Tavily, Exa, Perplexity Sonar, Brave, and Linkup.

url

https://brave.com/search/api/

Fetch prompt: Describe Brave Search API. What does it return for web search? Does it have an independent index? What about source quality, freshness, and citation data? Is there a results/snippets endpoint suitable for grounding an LLM agent? Summarize capabilities relevant to factual accuracy and verifiable citations. Tool result summary: # Brave Search API Overview ## Core Service The Brave Search API is a developer tool that powers applications with real-time web data. It delivers "complete search results (URLs, text, news, images, and more), with additional LLM context optimized for AI." ## Independent Index Yes, Brave maintains its own independent web index. The API uses "Brave's independent Web index, the same index that powers Brave Search," not Agent context: Now let me consult the actual documentation for the top candidates in parallel: Tavily, Exa, Perplexity Sonar, Brave, and Linkup.

url

https://docs.linkup.so/pages/documentation/get-started/introduction

Fetch prompt: Describe Linkup's search API. What does it return — sources, content, citations? Any claims about factual accuracy benchmarks (e.g. SimpleQA)? Does it support sourced answers for grounding an LLM agent? Summarize capabilities relevant to factual accuracy and verifiable citations. Tool result summary: # Linkup Search API Overview ## What It Returns The **Search endpoint** transforms queries into "ranked URLs, sourced answer, or structured JSON" with sub-second to ~30-second latency. The **Fetch endpoint** extracts full page content as clean markdown suitable for LLM consumption. ## Factual Accuracy Claims Linkup emphasizes strong performance on standardized benchmarks: - **SimpleQA benchmark**: Their Search endpoi Agent context: Now let me consult the actual documentation for the top candidates in parallel: Tavily, Exa, Perplexity Sonar, Brave, and Linkup.

agent_action

Let me get the Exa docs from the redirect, retry Perplexity, and check pricing/benc...

Let me get the Exa docs from the redirect, retry Perplexity, and check pricing/benchmark comparisons.

url

https://exa.ai/docs/reference/search

Fetch prompt: Describe Exa's search/retrieval API. What does it return — source URLs, full page contents, highlights, scores? Does it support neural/semantic search and high source quality? Does it return citation-ready data and content for grounding an LLM? Any LangChain integration? Summarize capabilities relevant to factual accuracy and verifiable citations. Tool result summary: # Exa Search API Overview ## Core Capabilities Exa's `/search` endpoint performs web retrieval with prompt-engineered queries and returns structured result data. Key returns include: **Result Data:** - Source URLs, titles, published dates, authors - Full page text (configurable length, max 10,000 characters) - LLM-identified highlights from each page - Relevance scores (cosine similarity for highlights) - Favicon and Agent context: Let me get the Exa docs from the redirect, retry Perplexity, and check pricing/benchmark comparisons.

url

https://docs.perplexity.ai/getting-started/overview

Fetch prompt: Describe Perplexity's Sonar API. Does it return synthesized answers with citations/sources? Is it an answer engine or a raw search API returning documents? Can you control the underlying reasoning model, or does Perplexity's own model generate the answer? What citation/source data does it return? Summarize for grounding an existing OpenAI-based agent with verifiable citations. Tool result summary: # Perplexity API Analysis Based on the documentation provided, I cannot fully describe Perplexity's "Sonar API" because **the page doesn't use that terminology**. Instead, it highlights three distinct APIs: ## Available APIs (as documented): 1. **Agent API** — "Access third-party models with web search tools and presets." This appears to be the synthesizing component, allowing you to use frontier models (like GPT-5.5 Agent context: Let me get the Exa docs from the redirect, retry Perplexity, and check pricing/benchmark comparisons.

Tavily vs Exa vs Linkup SimpleQA accuracy benchmark web search API for RAG agents 2026

Query: Tavily vs Exa vs Linkup SimpleQA accuracy benchmark web search API for RAG agents 2026 10 search result links captured Tool result summary: Based on the search results, here's a comprehensive comparison of Tavily, Exa, and Linkup on SimpleQA accuracy benchmarks for RAG agents in 2026: ## SimpleQA Accuracy Benchmarks On standard benchmarks, Exa's Research API achieves the highest accuracy at around 94.9% on SimpleQA, while Tavily is close at 93.3%. Linkup claims the highest score on SimpleQA's factuality benchmark for their Deep tier. More specifically, L Agent context: Let me get the Exa docs from the redirect, retry Perplexity, and check pricing/benchmark comparisons.

agent_action

One last check — confirming Tavily's official LangChain/LangGraph integration since...

One last check — confirming Tavily's official LangChain/LangGraph integration since this repo is built on LangGraph.

url

https://docs.tavily.com/documentation/integrations/langchain

Fetch prompt: Is there an official Tavily LangChain integration package (e.g. langchain-tavily)? Does it provide a tool that drops into a LangGraph create_react_agent / ReAct agent? What is the package name and the tool class name? Brief. Tool result summary: # Official Tavily LangChain Integration **Yes**, there is an official integration package called **`langchain-tavily`**. The package provides multiple tool classes that work with agents, including `TavilySearch`, `TavilyExtract`, `TavilyMap`, `TavilyCrawl`, `TavilyResearch`, and `TavilyGetResearch`. These tools are designed to be dropped into agent frameworks. The documentation states: "The `langchain-tavily` Python Agent context: One last check — confirming Tavily's official LangChain/LangGraph integration since this repo is built on LangGraph.

agent_action

## Recommendation: **Exa** (with Tavily as the very close runner-up) Given your har...

## Recommendation: **Exa** (with Tavily as the very close runner-up) Given your hard constraint — factual accuracy, source quality, and verifiable citations *above* latency/price/ease — Exa is the pick, with Tavily a near-tie I'd choose instead only if integration speed mattered most. ### Why Exa - **Highest independently-measured factual accuracy.** Its Research API leads SimpleQA (~94–95%), edging Tavily (~93%) in third-party comparisons. - **Neural/semantic retrieval improves source quality.** Rather than keyword-matching, it surfaces authoritative primary sources — important in finance, where the real hallucination risk is grounding on SEO-spam or stale forum content. - **Most granular, verifiable citations.** Returns field-level citations with confidence scores (low/med/high), LLM-identified highlights with cosine-similarity scores, plus full page text and dates. - **Finance-relevant controls.** Category targeting (company profiles, news, research papers) + domain filtering let you constrain to trusted sources (SEC, Reuters, company IR) — a direct anti-hallucination lever. ### Main alternatives considered - **Tavily** — purpose-built for RAG grounding; per-source relevance sco

result

Selected unknown

Commands

find . -type f -name "*.py" -o -name "*.json" -o -name "*.txt" -o -name "*.toml" -o -name "*.yaml" -o -name "*.yml" | head -50

exit code not materialized

find /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1 -maxdepth 2 -type f $ -name ".env*" -o -name "README*" -o -name "Readme*" $

exit code not materialized

find /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1 -type f -name "*.py" | head -20

exit code not materialized

git log --oneline -20

exit code not materialized

git show --stat HEAD

exit code not materialized

ls -la /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/

exit code not materialized

ls -la /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/notebooks/ && ls -la /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/.devcontainer/

exit code not materialized

grep -n "ChatOpenAI\|langchain\|langgraph" /home/user/worktrees/attempt-507c7052-4b6f-4021-8f22-c41799b8567e-cap-1/app/agent.py

exit code not materialized

URLs Fetched

https://docs.tavily.com/documentation/api-reference/endpoint/search

status not materialized

https://docs.exa.ai/reference/search

status not materialized

https://docs.perplexity.ai/api-reference/chat-completions

status not materialized

https://brave.com/search/api/

status not materialized

https://docs.linkup.so/pages/documentation/get-started/introduction

status not materialized

https://exa.ai/docs/reference/search

status not materialized

https://docs.perplexity.ai/getting-started/overview

status not materialized

https://medium.com/@unicodeveloper/tavily-alternatives-in-2026-after-the-nebius-acquisition-9de526780686

status not materialized

https://www.firecrawl.dev/blog/exa-alternatives

status not materialized

https://www.tavily.com/

status not materialized

https://exa.ai/versus/tavily

status not materialized

https://chatforest.com/guides/best-search-mcp-servers/

status not materialized

https://www.nimbleway.com/blog/exa-alternatives

status not materialized

https://websearchapi.ai/blog/exa-ai-alternatives

status not materialized

https://www.humai.blog/ai-search-apis-compared-tavily-vs-exa-vs-perplexity/

status not materialized

https://you.com/resources/best-web-search-apis-for-ai-agents

status not materialized

https://aimultiple.com/agentic-search

status not materialized

https://docs.tavily.com/documentation/integrations/langchain

status not materialized

Changed Files

Artifact only

Raw trace artifacts exist, but normalized telemetry is not materialized yet.

Runs

Find

Run

Decision Summary

Trace Timeline

Commands

URLs Fetched

Changed Files

Runs

Run

Decision Summary

Trace Timeline

Commands

URLs Fetched

Changed Files