We're in Cambridge this weekend to sponsor @HackHarvard's “Hack to the Moon" event.
Our challenge: the Best Data-Driven Agent Built on Chalk. We're looking for the most interesting agents that use data for decisions, built with Chalk infrastructure like agent sandboxes, gateways, dataset integration, and evals.
Teams are already moving fast. By Saturday morning, hackers had spun up more than 100 scaling groups on Chalk.
What’s up for grabs in our prizes: $1,500+ in Apple Store credits, Chalk swag, and interviews for our new grad roles.
If you’re here, come find us at the Chalk booth before submissions close Sunday morning. We can’t wait to see what everyone ships.
Agents now access sensitive APIs, ship code, and run for days without a human checking each step.
Knowing they're secure, doing the right thing, and not overwhelming your systems is the hard part.
In Part 1 of the first Chalk Talk, our co-founder @Derander sits down with @NancyZWang, CTO of @1Password, to talk through running agents in production. They discuss:
→ Securing agents, starting with identity
→ Writing evals that show whether an agent actually did the right thing
→ What agent traffic is doing to infrastructure
Thanks to Nancy for the great conversation. Part 1 is below.
Agents today are writing code, running multi-day workflows and getting access to production systems. The questions that matter now are practical ones.
How do you secure an agent? How do you know it's doing the right thing? And can your infrastructure keep up?
We discuss all this and more in our new series, Chalk Talk, where we sit down with top leaders in AI and discuss how it’s changing businesses and what it truly takes to run agents in production.
In our first episode, Chalk co-founder @Derander sits down with @NancyZWang , CTO of @1Password. They cover:
1/ Securing agents in production
2/ Writing evals that show whether an agent is doing the right thing
3/ What agent traffic is doing to infrastructure
4/ Why enterprises are keeping their models and data in-house
5/ Why formal methods are suddenly relevant again
Watch the trailer below. The full episode drops Wednesday, October 7th.
Thank you to Nancy for joining us, and we can’t wait for everyone to see the full conversation.
Day 1 of @AIconference is live, and the exhibit floor is already buzzing.
Come find us at Booth 262, grab our latest swag, and see if you can solve our new math proof competition.
Plus, we're giving away a Nintendo Switch 2 to one lucky booth visitor.
Tomorrow, Theater 2 is the place to be. At 1pm PT our co-founder @marx_elliot takes the stage with "Two Halves of Inference to Build, Eval & Run Agents".
More details below. See you on the floor.
Chalk at The AI Confernce: chalk.ai/events/AI-Conferenc…
Great piece from @StackObserver about Chalk Notebooks and why production ML needs agent-aware infrastructure.
"The release frames a question that is becoming central to production AI infrastructure: when an agent can write code, query production data, and retrain models, where does the boundary between agent investigation and human decision-making actually sit?"
Full article here: thestackobserver.com/chalk-n…
Chalk retweeted
September’s @Unusual_VC newsletter is out. This month:
• Personal AI agents take off as Instinct and @Muse gain traction
• @Anthropic releases Claude Fable 5.1 and Mythos 5.1, with upgrades across coding, agents and knowledge work
• @OpenAI launches GPT-6 Astra, its most capable model yet
• @Chalk introduces its MCP Server and Assistant for production ML
• @Resolveai brings production context to coding agents
• AI leaders call for tools to “pace the frontier”
For more on enterprise AI and the unusual corners of it, subscribe: unusual.vc/news/
Next week is @AIconference and the Chalk team is ready to show up big.
Our co-founder @marx_elliot will be presenting "Two Halves of Inference to Build, Eval & Run Agents" on 10/1 at 1pm PT. If you struggle with stale data and evals that can’t predict production performance, this is the talk for you.
Plus, the Chalk team will be hanging out on the exhibit floor throughout the conference. Stop by Booth 262 to chat with our FDEs, catch live demos, and grab some of our latest Chalk swag.
Schedule time with us in advance by visiting the link below. 👇
Better agents require better evals. Better evals require better context.
Most agent evals are broken before they even start. Not because the model reasoned poorly, but because it was scored on a prompt built from stale, disconnected data. That's not a model problem. That’s a data assembly failure.
The fix? A unified context layer that delivers real-time data at inference.
Next month our Co-Founder Elliot Marx will host a live webinar to show you how to turn your data into actionable context for your agents, so you can run proper evals and deploy with confidence.
October 8th at 10am PT/1pm ET.
Register at the link below.
Register: chalk.ai/register/agent-cont…
New sign on our SF office, so of course we had to take a picture with it.
Want to join our team? We're #hiring for several exciting positions in SF, NY and more.
Check out our open roles: chalk.ai/careers
What can a hand of poker teach us about how real-time context changes agent behavior?
Our Developer Advocate @rkundy built a poker agent to show how recommendations change with fresh data vs historical data alone. First presented at the @temporalio's 'Durable AI' meetup, Rishi now shares his learnings in our new blog post, "Context Has a Timestamp".
Link in the comments.
“If we can make context and features the same, you eliminate drift and have canonical ways of doing things at your company.”
Your agents and models need fresh data. A context engine provides the data foundation that gives you speed without sacrificing data freshness.
Our co-founder, @marx_elliot , walks through how a real-time context layer enables your data teams to define the features and real-time signals your models run on, and then delivers that same context directly to your agents at inference.
Full video at the link below.
Learn how to ship better models: chalk.ai/watch/use-chalk-not…
