LoginSign Up
← Back to all sparks
D

Deepnote

ANALYTICS
Velocity3.8

Deepnote turns the notebook into shared context for AI coding agents

data-notebooksai-agentsreproducibilitygit-integrationpolarsai-governance
◆Current state
Deepnote has spent the year hardening the fundamentals of a collaborative notebook — Git sync, run snapshots, Polars, multi-format interop, AI cost visibility — and is now opening that accumulated workspace context to external agents. The June move wiring Codex directly into the workspace signals where the bet is going.
◆Where it's heading
The platform is positioning its notebooks, scheduled jobs, and integrations as the grounding context layer for AI exploration, while steadily closing the engineering-workflow gaps (Git, snapshots, reproducibility) that made notebooks hard to trust. Reproducibility plus agent-readable context is the combined thesis.
◆Prediction
Expect deeper agent integration — more tools beyond Codex able to read and act on workspace context — alongside continued reproducibility and governance features like the AI usage metering already shipped.

◆Recent moves

  1. 6d ago

    Your workspace as the context for every exploration

    ⚡ SPARK

    Opens the accumulated Deepnote workspace — notebooks, scheduled analyses, data apps, integrations — as native context for Codex, turning the platform from a place you work into context an agent works from.

    View source ↗
  2. 1mo ago

    Run snapshots, Git sync, & AI usage visibility

    Another record of the same release highlighting run snapshots, Git sync, and AI usage visibility — the reproducibility-and-governance bundle that makes notebooks trustworthy enough to expose to agents.

    View source ↗
  3. 1mo ago

    Run snapshots, Git sync, Polars support, PDF export, & a cleaner notebook

    A cut of the late-April release emphasizing immutable run snapshots, Git sync, and admin-facing AI usage visibility — reproducibility plus early AI governance.

    View source ↗
  4. 1mo ago

    Run snapshots, Git sync, Polars support, PDF export, & a cleaner notebook

    The full April 27 release: immutable run snapshots for debugging and audit, two-way Git sync with reviewable .deepnote diffs, first-class Polars, PDF export, and workspace cleanup — a broad reproducibility and workflow push.

    View source ↗
  5. 1mo ago

    Polars support, PDF export & a cleaner notebook

    An earlier slice of the same work bringing first-class Polars DataFrames, PDF export, and notebook UI cleanup — incremental polish on the data and authoring surface.

    View source ↗
  6. 2mo ago

    How many KitKats to run your AI?

    Behind the April Fools' framing, ships real AI usage metering — per-model token and dollar cost visible to workspace admins — an early governance feature for AI-heavy teams.

    View source ↗