
Sofia Guzowski
@SofiGu1
Followers
502
Following
741
Media
18
Statuses
239
Partnerships & Community Lead @tavilyai
New York City
Joined February 2014
just sf tech party things: 3 floors of djs Sam Altman pics on the wall Coworking room (fully packed) Merch trucks (Not pictured) a girl dressed up as an astronaut Props to @BellaNazzari for the very walm welcome to the city 🥂
105
13
364
the @tavilyai team reporting for judging duty🫡 @weights_biases weave hacks is packed with talent!!
3
3
13
The moment you've been waiting for... the official WeaveHacks 2 hackathon prizes are LOCKED IN. With +$45K in cash, hardware, and credits up for grabs this weekend (Oct 11-12), the stakes have never been higher. ...and our incredible sponsors came through with even more. 👇
1
8
27
🚀 Groq + Tavily MCP: Real-time web search, made simple We teamed up with @GroqInc to release a new API Cookbook tutorial featuring Tavily MCP, showing developers how to bring real-time web search, scraping, and crawling into Groq-hosted models. Here’s what it looks like
2
5
27
🚀 New Tutorial from NVIDIA: Build a Report-Generation AI Agent NVIDIA just published a hands-on guide to building a report-generation AI agent using @tavilyai The workflow shows how modern open tooling can come together to create production-ready agents: - Nemotron (open LLM
1
1
4
unfortunately, the only way to tell the value of someones contribution these days is to go straight to the source. if you are building open source, tweeting your ideas, breaking down your thought process, no one can deny your contribution. thats why "building in public" is so
25
6
251
Build smarter web research agents with Strands Agents SDK + @tavilyai 🔍🧠✍️ Get real-time web insights, built-in enterprise security & seamless #AmazonBedrock integration. #AWS #agenticAI 👉 https://t.co/bv4xZ67wXd
1
8
16
AI Agents 101 (+ how to easily build your own) 👇 Let me know what you think: https://t.co/DrbB5CHmhB
@tavilyai @n8n_io
0
0
1
Build AI research agents that ship. Join us for a webinar with our friends at @tavilyai. 📅 8/26 🕗 8:00am PT We’ll show how to add high-precision web search, evals, tracing, and guardrails so your agents deliver fresh, cited answers in production. Sign up below!
3
7
14
Dynamic web research agents Strands Agents SDK + @tavilyai 🚀🔍⚡ Streamline AI agent development with real-time web intelligence, enterprise-grade security & native #AmazonBedrock integration. #AWS #agenticAI 👉 https://t.co/zhjY0bRJGK
0
5
34
We’re excited to announce our $25M in funding, led by @insightpartners and Alpha Wave Global🚀 This funding will accelerate our mission to onboard the next billion agents to the web! Read more on @TechCrunch
https://t.co/2waF2njMIH
techcrunch.com
The one-year-old startup raised a Series A led by Insight Partners.
16
18
53
Build dynamic web research agents with Tavily + @awscloud Strands 🔎 With Tavily now on the AWS Marketplace + Bedrock AgentCore Gateway, developers can build agents that: - Search, extract, and crawl the web - Run securely with enterprise‑grade compliance and guardrails - Scale
2
4
15
Turns out the strip_markdown package on pip just converts md to html, then strips the html using bs4. I made a 300x faster alternative using C. https://t.co/34D1E3NAJJ
pypi.org
Fast Markdown Stripper
1
6
10
Lessons from Deploying Remote MCPs Building a Model Context Protocol (MCP) server isn’t just writing code. It’s surviving shifting standards, evolving ecosystems, and countless edge cases. Here’s what I learned 🧵
1
4
13
🚀 New Example: Personalized Search with Mem0 + @tavilyai Search assistants give very generic answers. Ask for “coffee shops nearby,” and you’ll get a list anyone could find. But what if your assistant remembered you? Imagine asking for coffee shops and getting results tailored
4
13
110
We dropped five open source agent use cases: chat assistant, data enrichment, company research, crawl to RAG, meeting prep - all grounded in web retrieval using @tavilyai
https://t.co/QdDcd8jjdL
tavily.com
Tavily is the real‑time search engine for AI agents and RAG workflows — Fast and secure APIs for web search and content extraction. Trusted by 600K+ developers.
2
7
18