Launch HN: Livedocs (YC W22) – An AI-native notebook for data analysis
Source: Hacker News
Introduction
Hi HN, I’m Arsalan, founder of LiveDocs (https://livedocs.com). We’re building an AI‑native data workspace that lets teams ask questions of their real data and have the system plan, execute, and maintain the analysis end‑to‑end.
Background
We previously posted about LiveDocs four years ago (https://news.ycombinator.com/item?id=30735058). Back then, LiveDocs was a no‑code analytics tool for stitching together metrics from tools like Stripe and Google Analytics. It worked for basic reporting, but over time we ran into the same ceiling our users did. Dashboards are fine until the questions get messy, and notebooks slowly turn into hard‑to‑maintain piles of glue.
New Architecture
Over the last few years, we rebuilt LiveDocs almost entirely around a different idea: data work should behave like a living system, not a static document or a chat transcript.
- Reactive notebook environment backed by real execution engines.
- Notebooks are not linear; each cell participates in a dependency graph, so when data or logic changes, only the affected parts recompute.
- Mix SQL, Python, charts, tables, and text in the same document while staying in sync.
- Local execution uses DuckDB and Polars; when you connect a warehouse like Snowflake, BigQuery, or Postgres, queries are pushed down instead of copying data out.
- Every result is inspectable and reproducible.
AI Agent
An AI agent sits on top of this environment, but it is not just “chat with your data.” The agent works inside the notebook itself:
- Plans multi‑step analyses.
- Writes and debugs SQL or Python.
- Spawns specialized sub‑agents for different tasks.
- Runs code in a terminal and browses documentation or the web when it lacks context.
- Operates within the same execution graph as humans, allowing you to see exactly what it ran, edit it, or take over at any point.
Canvas Mode & Interactive Apps
- The agent can build custom UI for your analysis, not just charts.
- Includes tables with controls, comparisons, and derived views that stay wired to the underlying data.
- When a notebook isn’t the right interface, you can publish parts of it as an interactive app, behaving like lightweight internal tools (similar in spirit to Retool) but backed by the same analysis logic.
Real‑Time Collaboration
Everything in LiveDocs is fully real‑time collaborative:
- Multiple people can edit the same notebook simultaneously.
- Results update live, comments can be added inline.
- Documents or apps can be shared without exposing raw code unless desired.
Use Cases
Teams use LiveDocs to:
- Investigate questions that don’t fit cleanly into dashboards.
- Build analyses that evolve over time without constant rewrites.
- Automate recurring questions without turning them into brittle pipelines.
Pricing
- Pay‑as‑you‑go, starting at $15 per month.
- Free tier available for trial (requires sign‑up to provision a sandbox).
Demo video: https://youtu.be/Hl12su9Jn_I
Call for Feedback
We are still learning where this breaks. Long‑running agent workflows on production data surface a lot of sharp edges. We would love feedback from people who have built or lived with analytics systems, notebooks, or “chat with your data” tools and felt their limits. Happy to go deep on technical details and trade notes.