Resources
Videos
Demos, tutorials, and deep dives on building AI copilots with Pillar.
2:46Pillar within a DevTool Example
Pillar is an open-source SDK that lets SaaS companies ship an AI copilot directly inside their product. It reuses the frontend code you've already written — you wrap your existing React components and functions, expose them to a reasoning server, and the copilot can call those functions live in your app. In this demo, we walk through a DevTool Example dashboard with the Pillar copilot panel embedded on the right side. The copilot has full access to 20+ tools across the entire app, and can both read data and take actions on behalf of the user. ### What the copilot can do in this demo: **Dashboard & Metrics** - Pull real-time KPIs: events tracked, active plans, MRR, and error rates - View monthly trend data and chart breakdowns - Create and manage scheduled reports (daily/weekly/monthly) with custom recipients **Plan Management** - List, sort, and search plans by subscribers, MRR, name, or usage - View detailed plan info (subscribers, revenue, status, environment) - Create new plans via natural language — the copilot pre-fills the form with pricing, billing interval, free trial duration, and card requirements, then opens it for the user to review - Export plan data as CSV with optional filters **Webhooks & Integrations** - List all configured webhooks and their statuses - Set up new webhook endpoints with specific event subscriptions (invoice, subscription, etc.) - Retrieve signing secrets for payload verification - Delete webhooks by ID or URL **Team & Settings** - List, search, invite, and remove team members - Change user roles (Admin, Editor, Viewer) - Generate and revoke API keys across production, staging, and development environments - View and toggle notification preferences **Navigation** - The copilot navigates the app itself — opening pages, drilling into plan details, and routing to the right screen before presenting results Reach out at jmaxwell@trypillar.com to get a personal demo setup!
3:05How Any SaaS Can Build a Copilot — and Securely Handle Secrets for AI Agents
AI agents are starting to sign up for services, request API keys, and interact with your product autonomously. OpenClaw, Gemini, and others are just the beginning. But handing secrets to an agent introduces real security risks that most apps aren't ready for. Pillar lets any SaaS add a Copilot by exposing your existing API calls and UI actions to a reasoning server with minimal frontend code. The server can then call those functions and take action inside your app on behalf of users — or agents. In this video, we walk through how Pillar handles one of the trickiest parts of this new world: secure secret exchange. Here's how it works: - A user or third-party agent (like Gemini) asks your app for a dev API key - Your app calls a create_api_key endpoint - Instead of returning the raw secret, your app returns a SECRET_REF and SECRET_REF_URL - The Pillar client displays a "Reveal Secret" button — clear to both humans and agents - The secret is redeemed once via the reference URL, then the reference is burned OR you can also just return the secret directly and mark it as sensitive. Pillar handles the rest — storing it briefly in Redis with a short TTL, redeemable exactly once. As autonomous agents become first-class users of your product, patterns like this aren't optional. They're table stakes. Try it out: https://trypillar.com #AI #Copilot #SaaS #APIKeys #Security #AIAgents #DevTools #OpenClaw
3:30Implementing WebMCP API with Pillar's SDK in a React App
Watch a Pillar developer implement WebMCP through Pillar in a React App.
2:21Demo of Pillar Product Copilot - Mercury
A demo of what the Pillar Copilot can do inside of a Banking App like Mercury. Define your client tools, and have a AI reasoning server call them. Give power back to your users, right inside your app.
1:20Introducing Pillar - Your App's Copilot
Pillar (https://trypillar.com) is an embedded AI co-pilot that executes tasks inside your product. Users type what they want, the co-pilot does it client-side with their existing session and permissions. You install the SDK via npm and register your existing code as tools. On a banking site, a user says "send $200 to my cleaners" and the co-pilot searches their recipients, finds the match, navigates to the transfer page, and pre-fills the form. The user still confirms. If your app requires 2FA for that action, so does the co-pilot.