{"id":97668,"title":"📶 Inconvo: Open source AI agent for customer-facing chat-with-data","tagline":"The easiest way to add reliable chat-with-data to your product","body":"# TLDR;\n\nInconvo helps companies add chat-with-data agents to their product. We provide a platform for configuring agent rules and directions and a simple API endpoint to call them. We’re open source — check out our repository [here](https://github.com/inconvoai/inconvo). We also offer Inconvo cloud — check it out at [app.inconvo.ai](https://app.inconvo.ai)\n\n[**https://www.youtube.com/watch?v=sbDTAbVG-WQ**](https://www.youtube.com/watch?v=sbDTAbVG-WQ)\n\n# The problem:\n\nToday, many product teams are under pressure to add “data agents” to their apps that connect to live databases and answer user questions.\n\nChat-with-data demos are easy. Shipping one to real customers is hard.\n\nMost teams start with “LLM generates SQL + prompts,” then run into three issues:\n\n* **Data safety:** you can’t reliably stop the model from pulling the wrong rows, crossing tenants, or selecting sensitive columns.\n* **Business correctness:** metric definitions, allowed filters/enums, join paths, and formats get split across prompts which can confuse the model and drift over time.\n* **Boundaries:** because the model can generate arbitrary SQL, “only allow these joins/filters/columns” becomes brittle after-the-fact validation.\n\nThe result is a second system of guardrails and checks just to make it safe to ship.\n\n### The solution:\n\nInconvo flips the approach: constrain the agent up front instead of trying to rein it in after.\n\n* **A semantic model as the contract:** define approved tables/columns, metrics, filters/enums, and join paths in one place.\n* **Constrained query plans (not SQL):** the model outputs structured query plans which are validated against your semantic model before execution.\n* **Automatic access rules:** tenant scoping and field restrictions are enforced on every request with deterministic code not prompts.\n\nYou can call your data agent from your application in just a few lines of code:\n\n![uploaded image](/media/?type=post\u0026id=97668\u0026key=user_uploads/1151062/a427ef4c-552e-4a7e-8675-671a08023bbf)\n\n# Our ask:\n\nCheck out our repo and leave us a ⭐ on Github: [**https://github.com/inconvoai/inconvo**](https://github.com/inconvoai/inconvo)\n\nRun Inconvo OSS locally `npx inconvo@latest dev` Or sign up to our cloud for free [**https://app.inconvo.ai**](https://app.inconvo.ai)","slug":"PPI-inconvo-open-source-ai-agent-for-customer-facing-chat-with-data","created_at":"2026-02-10T17:40:07.857Z","updated_at":"2026-05-24T16:33:59.006Z","total_vote_count":6,"url":"https://www.ycombinator.com/launches/PPI-inconvo-open-source-ai-agent-for-customer-facing-chat-with-data","share_image_url":"https://www.ycombinator.com/media/?type=post\u0026id=97668\u0026key=user_uploads/1151062/a427ef4c-552e-4a7e-8675-671a08023bbf","company":{"id":29103,"name":"Inconvo","slug":"inconvo","url":"https://inconvo.com","logo":"https://bookface-images.s3.amazonaws.com/small_logos/42126d50fed615bc74167d22b4985b25e9d25fad.png","batch":"Summer 2023","industry":"B2B","tags":["Artificial Intelligence","Developer Tools","Analytics","API"],"search_path":"https://bookface.ycombinator.com/company/29103"}}