Alex Nucci

1% better than yesterday. VP of Revenue and Success @firecrawl

[Alex Nucci @AlexNucci]

Six months in at Firecrawl: 7x growth, the best enterprise customers in AI, v2 launched, $14.5m raise. Velocity and customer obsession is our superpower.

Powering @Shopify (participating in the round), @zapier (also participating), @retellai, @getbotpress, @AlibabaGroup's @Alibaba_Qwen, @Replit, @n8n_io, and thousands more to turn the web into LLM-ready data.

This team has built something special, and we're just getting started!

[Caleb Peffer (Hiring!) @CalebPeffer]

Excited to announce @firecrawl's $14.5M Series A 🔥

We've grown 15x in the past 12 months. The demand for clean web data in AI is real.

Here's the story of how we built the web data layer for AI - starting from a side project to powering how 350k+ builders get web data 🧵

[Alex Nucci @AlexNucci]

@TejasKumarrr @firecrawl Ha! Just spreading the gospel.

re: Building something great. Shoot me an email once live, would love to check it out!

[Alex Nucci @AlexNucci]

@ericciarla @firecrawl Mikey can use this to track Noah Kahan across the globe

[Nicolas Camara @nickscamara_]

opus 4.8 dropped today. you could've found out minutes before anthropic announced it.

a firecrawl monitor on their entire website emails you the second a new model id appears, before the announcement.

you can build this today

[Michael Grinich @grinich]

🤖 MCP Night: Agent Mode
- Software is now “self-driving”
- What it takes to build agents
- Announcing /auth.md
- Live demo w/ @Cloudflare & @Firecrawl

⚡️Lightning demos from:
- @keyserfaty - AgentCard
- @adisingh - AgentMail
- @baconbrix - Expo
- @RhysSullivan - Executor

🌶️ Panel discussion with:
- @irvinebroque - Cloudflare
- @clairevo - ChatPRD
- @zeeg - Sentry
- yours truly

What a night! See you at the next one 🪩

[Firecrawl @firecrawl]

Huge congrats to the @chatbase team 🔥

Firecrawl powers Chatbase with clean web data for onboarding and AI agent training, so their agents are always grounded in the latest brand and product knowledge.

[Lovable @Lovable]

3/5 Firecrawl

Scrape, crawl, and search live web data from your app. Firecrawl handles proxies, JS rendering, rate limits, and anti-bot measures.

[Nicolas Camara @nickscamara_]

One html page on avg produces 36k tokens. With proper md conversion you cut that down to 2.8k tokens. That’s 92% cost reduction

While I agree that some cases HTML is better, by no means it’s a cost viable option for 99.9% of users

You literally save $1,079* if u fetch 10k pages

[Matthew Berman @TheMattBerman]

I make unlimited product shoots with codex for $0 😱

here's the system that turns one URL into a full ecomm photo library:

step 1: scout the product page
→ @firecrawl pulls the REAL product reference. package, label, claims
→ tested on gruns, rhode, blueland, stumptown. no logos, no story art, no stock
→ for shopify it grabs JSON-LD product images. cleanest ref every time

step 2: lock product truth
→ extracts the must-preserve list. ie package shape, label text, claims, product count
→ every shot locked to the real reference before generation runs

step 3: build the shot plan
→ category-aware: supplements, skincare, coffee, cleaning kits each get different taxonomies
→ PDP hero, label detail, scale-in-hand, lifestyle, email, marketplace, social vertical
→ 12 shots per run. each one ships at its real ratio.

step 4: generate the shoot
→ runs against the real reference + the preservation list
→ actual 1:1, 4:5, 9:16, 16:9. (not a square with a 16:9 label slapped on)
→ gruns full set: 12 / 12 live QA pass
→ codex uses your sub. other agents use the @OpenAI api

step 5: score every frame
→ scores product accuracy, brand fit, and artifact risk on every shot
→ nothing ships unscored
→ the point is to catch failures before you have to

step 6: reroll the failures
→ failed shots get prompts rewritten + regenerated against the SAME reference
→ stumptown first failed because story art got selected. the agent fixed it. 3/3 pass after.
→ pass or exhaust. no infinite loops.

step 7: ship the magic frontend
→ every run emits a static index.html. the showoff moment.
→ premium gallery, QA scores, export links by channel
→ open one file. show the team

input: one product URL
output: 12 product shots + a magic frontend gallery

photo shoots: $5-25K, 4 weeks. this: 10 minutes, $0.

I packaged the entire system as the Brand Shoot Kit.
7 agent skills:
- scout (real product reference detection via @firecrawl)
- preserve (locks packaging, labels, claims, geometry)
- shot-plan (category-aware PDP/lifestyle/social/email taxonomy)
- generate (ratio-aware shoot at real dimensions)
- qa (scores every frame on accuracy, brand fit, artifact risk)
- reroll (auto-fix failed shots before human review)
- export (channel renders + magic frontend)

also works with claude code, @openclaw, hermes (@nousresearch) or any agent framework

giving it away free.

comment SHOOT + like + follow
(must follow so i can DM)

[Nous Research @NousResearch]

Tool Gateway is now live in Nous Portal.

No separate accounts, no API key juggling. All you need is one subscription, and everything works.

A paid Nous Portal subscription now includes access to 300+ models and a growing set of third-party tools.

Launching with:
→ Web scraping
→ Browser automation
→ Image generation
→ Cloud terminal backend
→ Text-to-speech

[Dave Morin 🦞 @davemorin]

Love @firecrawl. So good.

[GREG ISENBERG @gregisenberg]

how to use firecrawl to give your AI eyes and actually build startups that outperform 99% of apps:

1. your AI is smart but blind. it can't go to a website, read a page, or grab data on its own. firecrawl fixes that. you put in a URL. you get back clean markdown, structured JSON, screenshots. feed it to any model.

2. three lines of code. that's it. no proxies. no anti-bot detection. no custom scrapers that break when a site changes. one API call. clean data back in seconds. works on 98%+ of sites.

3. firecrawl has six core capabilities: scrape a single page. crawl an entire site. map all URLs on a domain. search google and return full content. an agent endpoint where you describe what you want and it goes and finds it. and a browser sandbox where AI controls a real browser like filling forms, clicking buttons, handles logins.

4. the agent endpoint is wild. you can say "find all of YC's winter 24 dev tool companies and their founders and emails" and get back structured data. or "compare pricing tiers across stripe, square, and paypal" and get a side-by-side table.

5. the browser sandbox lets your AI stay logged in across sessions, navigate pagination, watch live as it browses. this is computer use without building the infrastructure yourself.

6. think of it in layers. every builder needs: an agent harness (claude code, cursor, codex), a search layer (perplexity, exa), a web data layer (firecrawl), an ops brain (obsidian, notion), and an outbound stack. the web data layer is the one most people are sleeping on.

7. this is the AWS moment for web data. in 2006 building a web app meant buying servers and managing racks. AWS said one API call, use our servers. some of the biggest companies of the last decade were built on that. firecrawl is doing the same thing for web data in 2026.

8. the framework i'd use for coming up with startup ideas building with clean data: take a massive horizontal platform. rebuild it for one niche using firecrawl. the vertical version always wins because people want specific, not generic. price for outcome.

9. a year ago firecrawl posted a job listing that said "please only apply if you're an AI agent." content creator agents. customer support agents. junior dev agents. it looked weird. it was a signal for where this is all going.

the people who understand how to get clean web data, wrap it around an LLM, and package it as a product are the the ones with a 12-month head start.

i use @firecrawl with @ideabrowser . once you see what's possible with structured web data, you can't unsee it.

episode is live on @startupideaspod (full breakdown there)

i tried to explain this as clear as possible for even the non technical. send it to a builder friend.

watch

[Nicolas Camara @nickscamara_]

https://t.co/bdyDeJgRrg

[MakerThrive @MakerThrive]

we just used @Lovable + @firecrawl to build a Brand Fetch clone 🤯

enter a url & get:

- brand kit w/ logo + favicon
- SEO score
- competitors
- sitemap URLs
- company news
- key contacts

try it with any url: https://t.co/biJssTsc23

demo 👀

[Alex Nucci @AlexNucci]

Firecrawl 🤝 Zapier

[Firecrawl @firecrawl]

Our /agent endpoint is now live on Zapier!

Describe what web data you need and let /agent search, navigate, and gather it automatically inside your Zaps.

Start building with it today 🔥

[Alex Nucci @AlexNucci]

@firecrawl Top request!

[Firecrawl @firecrawl]

Introducing /agent by Firecrawl 🪄

Just describe what you need - with or without a URL then /agent searches, navigates, and gathers information from the widest range of websites, reaching data no other API can.

Try out the research preview today.

[Firecrawl @firecrawl]

Introducing the Firecrawl Connector for Lovable 🔥

Your @Lovable apps can now scrape, search, and crawl the web out of the box powered by Firecrawl.

Free for all users for a limited time! Try it out today 👇

[Firecrawl @firecrawl]

Our most advanced endpoint drops next week!

Beta users are calling it “Magical” 🪄

Tune in this Thursday (12/18) at 12pm EST

[Alex Nucci @AlexNucci]

@CalebPeffer @elonmusk https://t.co/sp4iUQRKaJ

[Firecrawl @firecrawl]

Your AI agent should never answer with outdated docs.

Retell’s phone agents now pull fresh policies, API refs, and help-center pages on every single call using Firecrawl’s /scrape endpoint. Zero custom scrapers, zero stale answers.

Full case study 👇