How do AI spreadsheets work?

Sparkco AI transforms natural language into powerful spreadsheets instantly. Just describe what you need in plain English, and our AI agents build formulas, charts, pivot tables, and connect your data sources automatically. No manual Excel work required.

What data sources can I connect?

Connect to databases (PostgreSQL, MySQL, MongoDB), SaaS tools (Stripe, QuickBooks, Salesforce), EHR systems (PointClickCare, Epic), cloud storage, and REST APIs. Our AI automatically syncs and analyzes your data in real-time.

Is Sparkco AI secure for sensitive data?

Yes. Sparkco AI is fully HIPAA compliant and SOC 2 Type II certified. We maintain enterprise-grade security with data encryption, access controls, and regular audits. BAA available for healthcare customers.

How is this different from Excel or Google Sheets?

Traditional spreadsheets require manual formula building and data entry. Sparkco AI builds everything automatically from natural language, connects live data sources, and provides intelligent analysis. It's like having an expert analyst build spreadsheets for you in seconds.

Can I use this for healthcare operations?

Yes. Sparkco AI provides specialized healthcare solutions including patient referral screening, admissions automation, and voice-powered EHR documentation. Our agentic EHR infrastructure transforms skilled nursing facility operations.

How quickly can I get started?

Start building AI spreadsheets immediately - no setup required. For healthcare solutions, most facilities are operational within 2-4 weeks including EHR integration and staff training.

AI Agents for Prediction Markets

Name: Sparkco AI Spreadsheet Agent
Brand: Sparkco AI

## The Problem You're using Claude Code or Cursor for development. You want to ask your AI agent questions about prediction markets — recession odds, oil prices, Fed decisions. But the agent has no access to live market data. ## The Solution: MCP MCP (Model Context Protocol) lets AI agents call external tools. SimpleFunctions provides an MCP server with 16 tools that give your agent real-time access to Kalshi and Polymarket data. # One command to connect Claude Code claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp That's it. Your agent now has access to: | Tool | What it does | |------|-------------| | `get_context` | Full thesis snapshot — causal tree, edges, evaluation | | `scan_markets` | Search Kalshi markets by keyword | | `inject_signal` | Feed observations to your thesis | | `trigger_evaluation` | Force an immediate re-evaluation | | `what_if` | Scenario analysis (zero LLM cost) | | `get_positions` | Your Kalshi positions with P&L | | `get_balance` | Account balance | | `get_orders` | Resting orders | | `get_fills` | Recent trade fills | ## What This Looks Like in Practice In Claude Code: > What are the current recession odds on Kalshi? Using tool: scan_markets({query: "recession 2026"}) KXRECSSNBER-26 is trading at 35¢, implying a 35% probability of NBER-declared recession by end of 2026. Volume is strong at .2M with a 1¢ spread. Your thesis implies 72% — that's a +37¢ edge. The agent doesn't just fetch data — it compares market prices against your thesis model and identifies where they disagree. ## Beyond MCP: CLI and REST The same capabilities are available through the CLI and REST API: # CLI — great for scripts and pipelines sf context --json | jq '.edges[] | select(.edge > 20)' # REST — for custom integrations curl https://simplefunctions.dev/api/thesis//context -H "Authorization: Bearer sf_live_xxx" ## The Agent Loop Whether you're using MCP, CLI, or REST, the pattern is the same: 1. **Read**: Get current thesis state (`get_context`) 2. **Write**: Inject observations (`inject_signal`) 3. **React**: Trigger analysis when something changes (`trigger_evaluation`) The heartbeat engine handles routine monitoring — news scanning, price refreshes, milestone detection — every 15 minutes. Your agent focuses on high-level decisions. ## Getting Started # Install CLI npm install -g @spfunctions/cli sf setup # Create a thesis sf create "Your macro thesis here" # Connect MCP claude mcp add simplefunctions --url https://simplefunctions.dev/api/mcp/mcp Full setup guide: [simplefunctions.dev/docs/guide](https://simplefunctions.dev/docs/guide)