Coding agents are arriving on your data platform whether you're ready or not. lakecode is built for the team that has to answer for them: the substrate ingests Unity Catalog lineage and notebooks, grounds every agent in lakehouse reality, and projects what agents know back into UC — so you govern them with the tooling you already trust.
Black-box agent memory is a compliance non-starter on a data platform. Before an agent touches production-adjacent work, the platform team needs three answers — continuously, not in a one-time review.
Every piece of substrate knowledge is a structured claim with confidence — inspectable and editable in the console, not embedded in opaque weights or a context window that vanished.
Claims carry provenance: the source file, commit, notebook, lineage edge, or session that produced them. Knowledge without a paper trail doesn't get promoted.
Agent write-back is gated. Proposed knowledge climbs a promotion ladder — local → workspace → org — with review before anything becomes org-wide truth.
The same work → capture → govern → ground loop, wired into the platform you already operate.
Unity Catalog metadata, table- and column-level lineage, and notebook↔table reference graphs flow into the substrate — alongside your repos and docs. The agent learns how your data actually derives, not how the wiki says it does.
Sessions auto-prime from lakehouse knowledge: which band IDs are valid, why a constant is what it is, what failed last quarter. This is the knowledge-bound regime — where grounding flips answers from confidently wrong to correct (0/3 → 3/3, 2026-06-08).
What agents learn is projected into Unity Catalog lineage and audit surfaces. Agent knowledge shows up where your governance reviews already happen — your controls become the distribution channel, not an afterthought.
The Databricks edition ships as an in-workspace Databricks App. We validate the governance projection with your platform team during onboarding, against a pass/fail bar agreed up front.
Governance requires owning the loop — capture at commit time and gated write-back can't be bolted onto someone else's agent. So lakecode has to be a credible agent in its own right. The bar, with receipts:
6/6 = 6/6
Coding parity with Claude Code; bug-fixes byte-identical, same model both arms.
coding-bench v1 · 2026-06 · n=1/task
0/3 → 3/3
On knowledge-bound tasks, one substrate claim flips correctness from 0% to 100% — the regime where lakehouse knowledge lives.
grounded-coding bench · 2026-06-08 · claude-sonnet-4-6
Glass box
Provenance on every claim, gated write-back, promotion governance — and the UC projection validated with your platform team during onboarding.
validation gate agreed per design partner
What we offer design partners today — written into a one-page agreement, not just this website.
The shared org substrate — promotion ladder, review, provenance — works on any codebase. The lakehouse edition is the enterprise wedge, not the boundary.
One org at a time, onboarded personally — with an acceptance bar we agree on before you commit.