# Rubric Labs > Rubric is an applied AI lab helping companies build and ship AI agents, LLM products, and the infrastructure behind them. ## Pages - [Home](https://rubriclabs.com): Rubric is an applied AI lab helping companies build and ship AI agents, LLM products, and the infrastructure behind them. - [Blog](https://rubriclabs.com/blog): Writing from the Rubric Labs team: essays, experiments, and case studies on building AI agents, LLM products, and the infrastructure behind them. - [Brand](https://rubriclabs.com/brand): Rubric Labs brand assets: logo files, wordmarks, color palette, and typography, with guidelines for using them in posts, decks, and integrations. - [Contact](https://rubriclabs.com/contact): Get in touch with Rubric Labs to talk through an AI product, agent infrastructure, or a build you want shipped. We read and reply to every message. - [The Grid newsletter](https://rubriclabs.com/newsletter): The Grid is a newsletter by Rubric Labs with three actionable insights on building, shipping, and scaling intelligent products. - [Privacy](https://rubriclabs.com/privacy): Rubric Labs privacy policy: what data we collect on this site, how we use it, the analytics and third-party services involved, and how to reach us about it. - [Subscribe](https://rubriclabs.com/subscribe): Join the Rubric Labs mailing list to receive future posts on building and shipping AI products, agents, and infrastructure straight in your inbox. - [Team](https://rubriclabs.com/team): Meet the Rubric Labs team: product engineers working across design, software, and intelligent systems from idea to production. - [Work](https://rubriclabs.com/work): Selected client work from Rubric Labs: AI agents, LLM products, and data infrastructure we designed, built, and shipped for startups and enterprise teams. ## Case studies - [Partnering with E2B](https://rubriclabs.com/work/e2b): We embedded with E2B's team and shipped settings, billing, sandbox event visibility, and webhook monitoring to production. - [Partnering with Sligo AI](https://rubriclabs.com/work/sligo): We worked across backend reliability, evaluation systems, multi-agent orchestration, and enterprise security guardrails. - [Partnering with Gumloop](https://rubriclabs.com/work/gumloop): After a week with Gumloop in San Francisco, we shipped creator publishing and SEO-optimized template pages in one month. - [Partnering with Graphite](https://rubriclabs.com/work/graphite): We turned GitHub stats into a 12-scene script, then rendered each developer's video with Remotion and AWS Lambda. ## Blog posts - [Giving coding agents whole-repository maps](https://rubriclabs.com/blog/tooling-for-static-analysis.md): Testing whether deterministic repository representations help coding agents understand, navigate, and modify unfamiliar codebases. - [Everything we know about good agent design](https://rubriclabs.com/blog/everything-we-know-about-good-agent-design.md): A practical guide to the design choices that help agents plan, use tools, recover from errors, and verify their work. - [What is an Agent Harness?](https://rubriclabs.com/blog/what-is-an-agent-harness.md): A harness is the software that translates a model into a system that can affect its environment. Agent = Model + Harness. - [Challenging the Chatbot](https://rubriclabs.com/blog/challenging-the-chatbot.md): Intelligent applications need new interaction patterns beyond the chatbot: intelligence on every keystroke, in the background, and inside the content. - [Autonomous Iteration](https://rubriclabs.com/blog/autonomous-iteration.md): Testing coding agents' ability to improve a feature automatically: build it, screenshot it, critique the result, and iterate until it meets the bar. - [Every Server Deserves a Coding Agent](https://rubriclabs.com/blog/openclaw-backend.md): The promise and peril of collocating code and coding agent: what happened when we gave an SMS-based OpenClaw agent live access to its own production server. - [Contract Engineering](https://rubriclabs.com/blog/contract-engineering.md): How we define done for AI agents using verifiable contracts. The contracts are the application; the code is an implementation detail. - [Unblocking Agents](https://rubriclabs.com/blog/unblocking-agents.md): Tooling and infrastructure for autonomous software engineering: the access, infrastructure, and identity walls that stop agents, and how we remove them. - [Primitives over Pipelines](https://rubriclabs.com/blog/primitives-over-pipelines.md): Primitive-Oriented Agent Design: replace rigid AI workflows with thin prompts and modular primitives so agents can assemble faster paths for user intent. - [How does Claude Code actually work?](https://rubriclabs.com/blog/how-does-claude-code-actually-work.md): A first-principles breakdown of how Claude Code works, including the agent loop, tool use, context management, and design tradeoffs behind modern coding agents. - [Introducing Rubric Labs](https://rubriclabs.com/blog/introducing-rubric-labs.md): After a year and a half of building in stealth mode, we're excited to officially introduce Rubric Labs to the world. - [Fine-tuning a GPT model for spam detection](https://rubriclabs.com/blog/fine-tuning-for-spam-detection.md): How we fine-tuned a small GPT model to flag spam in our inbound contact form, using dozens of historical spam tags stored in Postgres as training data. - [My Summer at Rubric](https://rubriclabs.com/blog/my-summer-at-rubric.md): A recap of a summer of projects at the Lab, from the Rubric UI component library to Genson, an experiment in generating full React UIs with LLMs. - [Multi-staging → Local → Prod in record time](https://rubriclabs.com/blog/multi-staging.md): How to use multi-staging workflows to build and test multiple full-stack changes in parallel, from local development to production, in record time. - [Planning for near-free AI](https://rubriclabs.com/blog/planning-for-free-ai.md): How trends in open-source large-language models are converging to usher in cheap, abundant intelligence. The state of LLM capability, cost, and timeline. - [Create Rubric App](https://rubriclabs.com/blog/create-rubric-app.md): Create Rubric App is an open-source, full-stack AI agent template in the spirit of Create React App. Learn how it works and how to remix it for your purposes. ## Newsletters - [Commercial open-source is alive and well](https://rubriclabs.com/newsletter/038): Hot-swapping rate-limited Codex and Claude Code subscriptions with TOKENMAXX, plus our work with E2B on open-source AI sandboxes. - [037](https://rubriclabs.com/newsletter/037): Local LLMs on iPhone, streaming in expo and automating financial tasks with embeddings. This is The Grid #037 by Rubric Labs. - [036](https://rubriclabs.com/newsletter/036): On ambient companionship, good API design and music to end off the week. This is The Grid #036 by Rubric Labs. - [035](https://rubriclabs.com/newsletter/035): True cost of software, the web has a spinner problem, and if Youtube actually had channels. This is The Grid #035 by Rubric Labs. - [034](https://rubriclabs.com/newsletter/034): Insightful blog from Stripe engineering, building proficiency in LLMs quickly and an underrated public dataset of images. - [033](https://rubriclabs.com/newsletter/033): A track, website, and art project to end off the week. Read The Grid #033, Rubric Labs' newsletter for AI product builders. - [032](https://rubriclabs.com/newsletter/032): Postgres extension, apps as expressions of style, and embracing mistakes as a team. This is The Grid #032 by Rubric Labs. - [031](https://rubriclabs.com/newsletter/031): Insights from our time at the AI Engineer World's Fair. Read The Grid #031, Rubric Labs' newsletter for AI product builders. - [030](https://rubriclabs.com/newsletter/030): Crafting animations, jamming with work, and zooming out. Read The Grid #030, Rubric Labs' newsletter for AI product builders. - [029](https://rubriclabs.com/newsletter/029): Browsing agents, rabbit holes, creating brand awareness, software as we know it & on choosing your reactions. This is The Grid #029 by Rubric Labs. - [028](https://rubriclabs.com/newsletter/028): Google Streetview, LLMs labelling data & having empathy for your comms. Find three links in The Grid #028 by Rubric Labs. - [027](https://rubriclabs.com/newsletter/027): Team of agents outperform large LLMs, name your next project with confidence, and learn how to start a physical studio. - [026](https://rubriclabs.com/newsletter/026): High performance animations, building an agent with long-term memory, and Toronto Tech Week. This is The Grid #026 by Rubric Labs. - [025](https://rubriclabs.com/newsletter/025): LLAMA LLAMA LLAMA This is issue #025 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [024](https://rubriclabs.com/newsletter/024): Coming Soon This is issue #024 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [023](https://rubriclabs.com/newsletter/023): Gen UI and Anthropic This is issue #023 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [022](https://rubriclabs.com/newsletter/022): Coming soon This is issue #022 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [021](https://rubriclabs.com/newsletter/021): GPU marketplace, fixed software pricing, and embarking on side quests to pursue a major goal. This is The Grid #021 by Rubric Labs. - [020](https://rubriclabs.com/newsletter/020): Coming soon This is issue #020 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [019](https://rubriclabs.com/newsletter/019): Finding PMF, validating your product pre-launch, and building a local AI-chat product. This is The Grid #019 by Rubric Labs. - [018](https://rubriclabs.com/newsletter/018): AGI timelines, driving the world's fastest camera drone, and building aligned relationships. This is The Grid #018 by Rubric Labs. - [017](https://rubriclabs.com/newsletter/017): Writing as a superpower. This is issue #017 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [016](https://rubriclabs.com/newsletter/016): Moats are overrated, setting up unique developer pipelines, and brainstorming ideas. This is The Grid #016 by Rubric Labs. - [015](https://rubriclabs.com/newsletter/015): Open-source JSON mode template, streaming structured data, and finding the balance to saying yes to more things. - [014](https://rubriclabs.com/newsletter/014): Coming soon This is issue #014 of The Grid, Rubric Labs' newsletter for people building and shipping AI products. - [013](https://rubriclabs.com/newsletter/013): Open-weight LLMs, revenue per employee, and batched user interviews. Find three links in The Grid #013 by Rubric Labs. - [012](https://rubriclabs.com/newsletter/012): MVP breadth, thinking through problems in the moment, and demystifying web animations. This is The Grid #012 by Rubric Labs. - [011](https://rubriclabs.com/newsletter/011): Scoping for input goals, truth-seeking as a trust exercise, and pretty TypeScript errors. This is The Grid #011 by Rubric Labs. - [010](https://rubriclabs.com/newsletter/010): Business as offering help, startups from essays, and authenticity in uncertain times. This is The Grid #010 by Rubric Labs. - [009](https://rubriclabs.com/newsletter/009): Every comment 1% better, audacity as sustainability, and engineered marketing. This is The Grid #009 by Rubric Labs. - [008](https://rubriclabs.com/newsletter/008): This week's installment of The Grid, a roughly-weekly newsletter by Rubric Labs, contains an easter egg. Sorry about that. - [007](https://rubriclabs.com/newsletter/007): GPU kernels, automated doom-scrolling, and math for deep learning. Find three links in The Grid #007 by Rubric Labs. - [006](https://rubriclabs.com/newsletter/006): Dynamic fonts, unblocking color palettes, and what even is interaction design? This is The Grid #006 by Rubric Labs. - [005](https://rubriclabs.com/newsletter/005): Running LLMs on a MacBook, optimistic UI, and requests for startup. Find three links in The Grid #005 by Rubric Labs. - [004](https://rubriclabs.com/newsletter/004): Being model agnostic, naivety as an asset, and calculated moonshots. Find three links in The Grid #004 by Rubric Labs. - [003](https://rubriclabs.com/newsletter/003): Cache as component state, AI pins vs AirPods, and small tasks with outsized impact. This is The Grid #003 by Rubric Labs. - [002](https://rubriclabs.com/newsletter/002): Vetting clients, open-source bounties, and optimizing for momentum. Find three links in The Grid #002 by Rubric Labs. - [001](https://rubriclabs.com/newsletter/001): AI agents, launch teasers, and money on the table. Our first installment of The Grid, a weekly newsletter by Rubric Labs. ## Team members - [Dexter Storey](https://rubriclabs.com/team/dexter): Dexter Storey is the co-founder of Rubric Labs working on infrastructure for AI products, including deployment, permissions, and agent verification. - [Sarim Malik](https://rubriclabs.com/team/sarim): Sarim Malik is the CEO and co-founder of Rubric Labs. He works across product design and engineering, with a focus on coding agents and interaction models. - [Ted Spare](https://rubriclabs.com/team/ted): Ted Spare is the co-founder of Rubric Labs working on agent systems and applied AI products, including model capability and autonomous iteration. ## Interactive demos - [The filterable dashboard](https://rubriclabs.com/blog/iterative-improvement/demos/dashboard): An interactive demo of iterative improvement: the agent built this page, screenshotted it, critiqued the result, and improved it over iterations. - [The landing page](https://rubriclabs.com/blog/iterative-improvement/demos/landing): An interactive demo of iterative improvement: the agent built this page, screenshotted it, critiqued the result, and improved it over iterations. - [The onboarding flow](https://rubriclabs.com/blog/iterative-improvement/demos/onboarding): An interactive demo of iterative improvement: the agent built this page, screenshotted it, critiqued the result, and improved it over iterations.