spend: Windowed[float] = feature(versions={
windowed(
"30d", "90d",
expression=_.transactions[
_.amount,
_.timestamp > -_.chalk_window,
_.timestamp < -_.chalk_now,
].sum(),
materialization={"bucket_duration": "1d"},
),
})
Serve live context
Run models and agents
1from chalkcompute import ScalingGroup
2
3sg = ScalingGroup(
4 name="qwen",
5 image="vllm/vllm-openai:latest",
6 entrypoint=["vllm", "serve", "Qwen/Qwen2.5-7B-Instruct"],
7 gpu="nvidia-l4:1",
8 cpu="4", memory="16Gi",
9 port=8000, min_replicas=0, max_replicas=10,
10).deploy(ready_timeout=900)
11
12response = sg.call("/v1/completions",
13 json={"model": "Qwen/Qwen2.5-7B-Instruct",
14 "prompt": "Chalk is the future of AI"},
15 timeout=900)1from chalkcompute import Image, NetworkPolicy, Sandbox, Secret
2
3sandbox = Sandbox(
4 image=(
5 Image.base("node:22-slim")
6 .run_commands("npm install -g @anthropic-ai/claude-code")
7 .add_local_dir("./repo", "/workspace")
8 ),
9 cpu="2", memory="4Gi",
10 secrets=[Secret.from_chalk_env("ANTHROPIC_API_KEY")],
11 network_policy=NetworkPolicy(allowed_hosts=["api.anthropic.com"]),
12 lifetime="900s",
13).run()
14
15review = sandbox.exec(
16 "claude", "--bare", "-p", "Find security vulnerabilities in this repo.",
17 workdir="/workspace",
18)Resolve decisions against fresh data at the source.
Deliver decision-ready context in milliseconds.
Data, logic, and compute in one execution path.
No brittle pipelines. No third copy of your customer table.
In your cloud, next to your data, under your controls.
We’re moving hundreds of millions of features per second, each payload around 1MB, and still hitting a P99 latency of just 100ms. That kind of performance across the board is a real testament to the system Chalk built.
Emmanuel Fuentes
VP, Data & AI, Whatnot
Chalk was the only integrated compute and context engine for agents that ran entirely inside our own environment, at the scale we needed, without becoming an infrastructure project. What would have taken months took weeks.
AJ Balance
Chief Product Officer, Grindr
We’re applying AI and ML at scale across key areas of our energy business with Chalk’s feature platform. It enables high-performance computation over diverse data sources using clean, reusable code. The ability to mix Python and SQL gives our team the flexibility we need, while shared feature logic across projects improves consistency and accelerates development.
Edward Li
Staff AI/ML Engineer, Sunrun
Chalk powers our LLM pipeline, turning complex inputs—HTML, URLs, screenshots—into structured, auditable features. It lets us serve lightweight heuristics up front and rich LLM reasoning deeper in the stack, so we catch threats others miss without compromising speed or precision.
Rahul Madduluri
CTO, Doppel
Chalk helps us deliver financial products that are more responsive, more personalized, and more secure for millions of users. It’s a direct line from infrastructure to impact.
Meng Xin Loh
Technical PM, MoneyLion
Chalk has become a powerful addition to our machine learning infrastructure at Mission Lane. Chalk has enabled us to unify and streamline our feature calculations across both offline/batch-eval and online/live-decisioning use cases. We continue to be impressed by the flexibility and scalability of the system, and by the willingness of the Chalk team to work with us to get even more value out of it.
Mike Kuhlen
Data Science & ML Solutions and Strategy, Mission Lane
By moving our feature pipelines to Chalk, Data Science and Engineering now work side-by-side throughout model development. What used to be lengthy, error-prone handoffs are gone. Our entire search ranking stack runs on Chalk, serving features for inference in under 50ms, and we’re extending it to all of our models, including real‑time personalization.
Moaj Musthag
Head of Engineering, Turo
Extend your team with Chalk engineers when you need them.
Learn moreMake better decisions in production.
What we've been up to and where to find us next.
See why Fast Company named us on their list.
Learn how to give agents context for evals and production
How Chalk filled 40+ roles in one quarter without lowering the bar
Read more about our latest product announcement
