Databox is an agentic analytics platform that brings performance data from across your business together with consistent metrics and business context. Ask its AI Analyst questions about your business, use Routines to surface important changes automatically, and turn insights into reports that explain what happened and why it matters. Databox does more of the recurring reporting and analysis, so you can understand performance faster and take better-informed action.
Products used by Databox
Explore the tech stack and tools that power Databox. See what products Databox uses for development, design, marketing, analytics, and more.
Design & Creative 1
Design & Creative 1
Amazon BedrockEasiest way to build and scale generative AI applications
5.0 (4 reviews)
For Genie's RAG layer, we needed managed infrastructure that wouldn't become its own engineering project to maintain. Bedrock let us connect our knowledge base, manage embeddings, and keep retrieval fast - without running our own vector infrastructure. The alternatives either required too much ops overhead or didn't integrate cleanly with the rest of our stack. Bedrock just worked, and that let us stay focused on the product.
Engineering & Development 3
Engineering & Development 3
Claude CodeAnthropic’s deep-context AI coder
5.0 (735 reviews)
MCP Connectors means implementing an open protocol correctly: parsing tool schemas from any server a user points us to, handling three different auth flows (OAuth, API key, bearer token), and building permission logic that fails safe by default, since this feature can give an AI real access to a CRM, a support desk, or an inbox. That's well-scoped, spec-driven engineering work. We built the connector framework with Claude Code, working through the MCP spec and the edge cases (malformed schemas, expired tokens, servers that don't return what they promise) fast enough to ship a working connector framework, official connectors, and a custom connector option in the same release.
No-code Platforms 1
No-code Platforms 1
n8nWorkflow automation for technical people
4.8 (74 reviews)
The workflow half of the marketplace runs on n8n. The .json workflows handle scheduled automation - weekly SEO reports to Slack, daily paid ads briefs, traffic spike alerts - all powered by live Databox data. n8n makes it possible to ship "set it and forget it" analytics without any coding.
LLMs 3
LLMs 3
LangchainLangChain’s suite of products supports AI development
4.9 (115 reviews)
We evaluated several orchestration frameworks before choosing LangGraph for Artifacts. Generating a document isn't one call and done, it's a multi-step flow: pull the data, structure the layout, apply styling, and hold state across follow-ups like "turn this into slides." The alternatives either abstracted too much away or couldn't handle that stateful, multi-step process cleanly. LangGraph gave us explicit control over each step, so a report doesn't drift into something the user didn't ask for halfway through generation.
OpenAIAPIs and tools for building AI products
5.0 (861 reviews)
Every MCP server describes its own tools a little differently: different schemas, different parameter names, different response shapes. We use OpenAI alongside Claude for the structured side of MCP Connectors: parsing what an arbitrary server's tools actually take and return, and turning that into something Genie can reliably call and reason over. When a user points Genie at a connector we've never tested against, that parsing has to hold up on the first try, not just for the ones we built and QA'd ourselves.
Claude by AnthropicA family of foundational AI models
5.0 (1K reviews)
Routines run without anyone watching. That means the reasoning has to hold up on its own, no follow-up question to catch a mistake, no chance to rephrase and try again. Claude does the actual analysis behind every run: reading the data, working out what changed and why, and writing a result that has to be right the first time, because for most runs, no one checks it before it lands in someone's inbox.
General 2
General 2
LangSmithThe platform for agent engineering
Once Genie was running in production, we needed visibility into what the agent was actually doing - not just whether it returned an answer, but whether it made the right tool calls in the right order. LangSmith was the clearest choice for tracing agentic workflows end-to-end. Other options gave us logs; LangSmith gave us understanding. That difference matters when you're debugging why an AI analyst gave a wrong answer to a business question.
