Polaris
The Product
Your north star — a company operating system built for humans and AI agents
Polaris is an internal operating system for running a company. It replaces the patchwork of spreadsheets, Notion pages, Slack channels, and scattered markdown files with a single dashboard where everything — goals, metrics, updates, roadmap, and company values — lives in one place.
What makes it different: both humans and AI agents read from the same source of truth. The AI runs locally on your machine, and the entire project lives in a monorepo so the agent always has full context.
Timeline
Feb 2026 – Present
Platform
Internal Web App
Role
Product Designer + Developer
Home dashboard — click to enlarge
The Problem
Running a company — even a small one — means juggling a dozen tools that don't talk to each other. And none of them were built for a world where AI is part of the team.
Tool Sprawl
Goals in a spreadsheet, updates in Slack, metrics in a dashboard, docs in Notion, brand guidelines in a PDF. Every context switch costs time and fragments your understanding of the bigger picture.
Fragmented Knowledge
Company knowledge gets siloed across services. When you need to connect a goal to a metric to a roadmap initiative, you're stitching together three different tools manually.
AI Without Context
Most AI tools require you to copy-paste context into a chat window. The AI can't see your goals, your metrics, or your company values — so its suggestions are generic, not grounded.
Cloud Lock-In
Most dashboards require accounts, subscriptions, and sending your data to someone else's servers. For an early-stage company, that's overhead and risk you don't need.
The thesis behind Polaris: what if your operating system was designed so that both you and your AI could read from the same source of truth? And what if the AI ran locally on your machine — no cloud dependency, no API costs, full privacy? Bring your own model via Ollama, or plug in an API key if you prefer.
The Stack
Deliberately opinionated — zero cloud dependencies for the core product. Everything runs on your machine.
Next.js 16
App Router with React 19 and server components. Fast to build, easy to reason about, and the file-based routing maps cleanly to each dashboard tab.
SQLite
Zero-config, single-file database. No cloud dependency, no connection strings, no managed service. Your data lives on your machine as a single file.
Tailwind CSS
Utility-first styling paired with JetBrains Mono for a monospace, retro-modern aesthetic. Dark mode as the default — because that's how developers actually work.
Ollama + Gemma 3
Local AI inference via Ollama. No cloud API required — the model runs on your machine. Zero API costs, full privacy, and works offline.
Vercel AI SDK
Streaming responses with a provider abstraction. Swap between local models (Ollama) or bring your own API key — the interface stays the same.
Monorepo
App code, documentation, brand guidelines, and agent instructions — all in one repository. The AI development agent has full context across everything, always.
Core Features
Each tab in Polaris serves a specific purpose — no feature bloat, no empty dashboards. Every screen exists because the team actually uses it.
Values
Company identity rendered as interactive cards — brand voice, design language, color theory, vision. Not a static PDF buried in a drive folder. The AI reads from the same source, so its output is always on-brand.
Updates
Async standups that replace daily meetings. Structured fields — working on, blocked by, shipped today — with an AI draft button that pre-populates based on recent activity. A summarize button digests all updates into a single overview.
Goals
Quarterly and yearly goal tracking with visual progress bars. Goals are seeded from the company's identity document, so there's always alignment between what you say matters and what you're tracking.
Metrics
Key business metrics with sparkline charts and trend indicators. Revenue, MRR, churn, activation rate — with support for custom metrics. Log entries with optional notes for context on why a number changed.
More Features
The rest of the dashboard — planning, documentation, and a persistent AI conversation.
Roadmap
Initiatives grouped by quarter with status tracking. Link roadmap items to goals, assign owners, and generate PRDs with a single click — the AI has full context on what you're building and why.
Docs
Renders all markdown files from the monorepo's docs folder. Specs, ideas, brand guidelines — accessible without leaving the dashboard or opening a separate editor.
AI Chat
A persistent AI conversation interface that runs locally. Ask questions about your goals, brainstorm roadmap ideas, or draft messages — the AI has access to everything in the dashboard.
Contextual AI Actions
The feature that makes Polaris more than a dashboard — AI that acts on your data, not just displays it.
Hover over any entity to surface contextual AI actions — click to enlarge
Hover over or select any entity in Polaris — a goal, an update, a metric, a roadmap item — and a floating action button appears with AI-powered actions specific to that context. The AI doesn't just know what you're looking at; it knows the full state of your company.
Create Task
Turn any piece of content — a blocked item, a goal milestone, a metric anomaly — into an actionable task with one click.
Draft Message
AI composes messages with full context — it knows who you're writing to, what they're working on, and what matters to the company right now.
Generate PRD
Draft a product requirements document directly from a roadmap item. The AI pulls in related goals, metrics, and company values to create a grounded spec.
Summarize
Digest complex content — a week of updates, a long doc, multiple metric entries — into a concise overview you can act on.
Research
Find related context across your workspace. Blocked on something? The AI searches your goals, docs, and updates to surface relevant information.
Update Progress
AI-assisted goal progress updates. The AI suggests a progress percentage based on recent activity, shipped items, and metric trends.
Different entity types surface different actions — the menu adapts to what you're working on
Agent-First Development
How building inside a monorepo changes the relationship between you and your AI development partner.
With Kaizen Tracker, I used Claude Code as a development assistant — I'd describe what I wanted, it would scaffold components, and I'd review the output. The relationship was prompt → response → refine.
With Polaris, something shifted. Because the monorepo contains not just code but also the company's identity document, brand guidelines, product specs, and architectural decisions, the AI development agent has full context at all times. There's no "feeding context" step — no copying and pasting a brand guide into a chat window.
When the agent writes a component, it already knows the color palette. When it generates a PRD, it already knows the company values. When it suggests a metric to track, it already knows the quarterly goals. The monorepo isn't just a developer convenience — it's an information architecture decision that makes the AI a genuine team member instead of a generic assistant.
When you ask the agent to update a feature, it doesn't just change the code. Because everything lives in the monorepo, the agent also updates the documentation to reflect the change, revises the pitch deck and marketing copy with the new capability, and ensures everything stays aligned. One request, multiple artifacts updated coherently — no manual sync step, no "oh I forgot to update the docs."
"The monorepo isn't a developer convenience — it's an information architecture decision. When the AI agent reads the same docs, brand guidelines, and codebase that you do, you stop managing context and start collaborating."
Reflection
What building Polaris taught me about designing for AI-augmented workflows.
Opinionated > Flexible
SQLite instead of Postgres. Localhost instead of cloud. Local AI instead of API calls. One repo instead of many. Every opinionated choice removed a category of complexity and made the system easier for both humans and AI agents to reason about.
Values as Code
Encoding company identity directly in the app — not as a reference document, but as a living, rendered page — changes how you think about alignment. The values aren't aspirational wall art. They're data the entire system reads from.
Designing for Two Users
Every information architecture decision in Polaris had to work for both humans and AI agents. Structured data, consistent naming, predictable locations — what makes an app navigable for people also makes it readable for machines.
Next Steps
- Multi-user team support — extending Polaris for small teams with shared goals and individual dashboards
- Mobile companion — quick updates and goal check-ins from your phone
- Plugin system — custom AI actions that teams can define for their specific workflows
- Webhook integrations — pull in external data (GitHub commits, revenue from Stripe) automatically
Thank you
Thank you for your time reviewing my work on Polaris!
If you'd like to get in touch, please say hi!
claytonanderson.work@gmail.com