Sarah Rabideau

Perplexity helps Logic handle tasks that need real-time web context. When our automations need current information, Perplexity delivers accurate results without the hallucination headaches.

Gemini gives us another strong option for routing complex tasks. Fast response times and competitive pricing mean we can offer our customers more flexibility in how their automations run.

The OpenAI API powers much of Logic's intelligent routing. Reliable, fast, and the models keep getting better. Their infrastructure handles scale without breaking a sweat.

Claude Code helped us build Logic's automation engine. It can hold our entire codebase in context, so it gets what we're actually trying to do. Massively sped up our development.

Plaid is obviously the industry standard for bank linking and we've been impressed with just how many institutions are supported now.

Alpaca's Broker API is the best in the business. We wouldn't have been able to launch by now if not for their amazing new rebalancing API.

We use Langchain to orchestrate our entire agent framework — from the AI inbox and SDR copilots to outbound flows and long-term memory. It helps manage complex tool use, contextual reasoning, and multi-turn interactions across our platform. Langchain has been critical to scaling structured LLM workflows with modular, maintainable logic. Grateful to the Langchain team and open-source contributors (part of pour team) pushing this ecosystem forward.

We use Deepgram to transcribe live AI-driven training calls, where SDRs and sales reps practice conversations with an AI agent impersonating real prospects. The fast, accurate transcription is essential — it enables our coaching system to deliver instant feedback and correction right after each mock call. This real-time loop helps reps improve faster, and we’re thankful to the Deepgram team for enabling it.

We use LiveKit as the orchestrator for everything voice-related in our platform — from real-time conversations to AI-driven phone calls. It handles signaling, session management, and audio streaming across our voice AI and telephony systems. The flexibility and performance have been critical to delivering reliable, low-latency voice experiences. Thanks to the LiveKit team for building an infrastructure layer we can trust.

We use Groq for ultra-fast inference when analyzing millions of contact records and enriching them with AI. It enables us to run deep research and structured reasoning at speeds that would be impossible on standard GPU setups. This level of performance lets us deliver intelligent outputs in real time, even at scale. We're grateful to the Groq team for building the kind of infrastructure that makes this possible.

We chose Rust for SurrealDB because performance and safety matter. Rust’s memory safety guarantees and zero-cost abstractions let us build a fast, scalable database engine without sacrificing reliability.

The base of much that we've built

Quick, scalable, and simple to implement.

Ease of use, reliability