We've partnered with Daytona to provide a new home for Riza's users to continue running LLM-generated Python and JavaScript in a safe, isolated cloud environment.
riza.io/blog/partner...
All Riza users will get a unique coupon code to redeem $1,000 in Daytona cloud credits when they migrate.
Some important news: we're shutting down the hosted Code Interpreter API on October 1st, 2025. Please use the time to migrate your projects to an alternative provider.
Read more here: riza.io/blog/shuttin...
Yesterday, @anthropic.com shipped a big upgrade: You can now add any remote MCP server to Claude by dropping in a URL.
So it's now super easy to add powerful code execution capabilities to Claude with Riza.
🎞️ For a quick demo, check out our new video: www.youtube.com/watch?v=CU6E...
Funding announcement graphic: Riza - $2.7M seed round
I’m stoked to announce @riza.io's $2.7 million seed funding led by matrix.vc with participation from 43 and a handful of our favorite angels.
riza.io/blog/riza-ra...
Results in just 3 months:
► 1M+ code executions
► Fewer feature requests
► New user-driven workflows
Get the full scoop: riza.io/customers/pr...
So they integrated Riza to enable custom code execution in 2 products:
🔹Evals - So users can build custom scoring functions
🔹Agents - So users can freely fetch and manipulate data, invoke callbacks, and more
PromptLayer's users needed flexibility beyond the 20+ predefined transformation types offered in their AI workflow builders.
The best AI systems aren't built by engineers alone. Prompt engineering requires iteration, testing—and domain expertise.
That's why PromptLayer is designed to let domain experts like lawyers, doctors, and therapists tune prompts.
We chatted with PromptLayer to learn how they've enabled users to customize AI workflows and evals—with Riza. riza.io/customers/pr...
A presentation I gave at Founder's Garage. Current slide is a photo of me giving a presentation when I worked at Twilio in 2012.
Gave a quick talk about Claude and it's ability to not only use tools, but write its own on the fly (powered by @riza.io of course).
Try it yourself!
📚 Full guide with links to the data: docs.riza.io/guides/use-c...
💻 GitHub example: github.com/riza-io/exam...
New to Riza? Get started here: docs.riza.io/introduction...
Riza runs Python, JavaScript, Ruby, and PHP securely with any libraries you want to use.
In this example, Riza empowered the LLM to write and run extraction code using BeautifulSoup.
To securely execute code written by LLMs, use @riza.io
Code written by LLMs is "untrusted"—it might contain harmful side-effects. You protect your systems by running that code on Riza, not your production environment.
The workflow is simple:
Why? Two major benefits:
1️⃣ Reliability: LLMs often miss data when extracting directly
2️⃣ Speed & cost savings: Make just 1 call to an LLM to generate code, using a small subset of data
The key insight:
Don't ask LLMs to extract the data directly. Ask them to write the extraction code.
Instead, here's how we solved it:
1️⃣ We fed sample HTML from the site to an LLM
2️⃣ We had the LLM write targeted extraction code
3️⃣ Riza executed that code securely
4️⃣ We got back clean, structured CSV data
Manual scraping is tedious—especially when you're extracting data from many different websites.
LLMs can help. But when we asked OpenAI to extract a list of all the appraisers from the full HTML, it gave us a partial list.
The California Bureau of Real Estate Appraisers provides a list of all current and recently-licensed appraisers (link below 👇).
13,000 appraisers are shown in batches of 300, with no bulk download option:
A lot of commercially-useful data is stuck online: in government sites to enterprise portals.
LLMs can help you extract it, fast.
Let's see an example:
Try it yourself!
📚 Full guide, with code and links to full SF employee salary dataset: docs.riza.io/guides/use-c...
💻 GitHub: github.com/riza-io/exam...
New to Riza? Get started here: docs.riza.io/introduction
In this example, Riza empowered Claude to run Python code using `pandas`, `matplotlib`, and `seaborn`.
Riza executes Python, JavaScript, Ruby, and PHP securely with any libraries you want to use.
To securely execute code written by LLMs, use Riza's Execute Function API.
This API handles structured inputs / outputs, so your data analysis pipeline is reliable and debuggable.
The workflow is simple:
Instead, here's how we made the chart:
1. 🔎We fed a few lines of the salary data to an LLM (Claude)
2. ⭐The LLM wrote Python code to analyze and visualize trends
3. 🔒Riza executed that code securely
4. 📊We got back a clear chart
Data is everywhere: from personal to business to government.
But data is time-consuming to analyze by hand.
For example, San Francisco publishes all city employee salaries (link below 👇).
In the past, you had to do a lot of work to make this data useful.
Have more data than data scientists? LLMs can help.
Here's a chart Anthropic's Claude generated using Riza that shows trends in San Francisco city employee salaries.
And you can repeat this infinitely over other data.
Here's how:
Instead, here's how we made the chart:
1. 🔎We fed a few lines of the salary data to an LLM (Claude)
2. ⭐The LLM wrote Python code to analyze and visualize trends
3. 🔒Riza executed that code securely
4. 📊We got back a clear chart
Data is everywhere: from personal to business to government.
But data is time-consuming to analyze by hand.
For example, San Francisco publishes all city employee salaries (link below 👇).
In the past, you had to do a lot of work to make this data useful.
Shipped a new version of the @riza.io self-hosted container image that can handle way more interesting JavaScript workloads.
What JS/TS libraries are good for plotting graphs these days?