Cube vs Chord
Side-by-side trajectory, velocity, and editorial themes.
Cube ships Creator Mode and a Slack agent — embedded BI and agent surfaces in the same month.
Cube is shipping weekly across three coherent fronts: AI agent surfaces (Slack Agent for ad-hoc questions, Analytics Chat under the hood), embedded analytics (Creator Mode lets customers embed the full Cube app, not just dashboards), and the semantic-layer fundamentals (calculated fields in Explore/Workbook, workbook versions, custom chart palettes, refined filtering). Earlier in the period, data masking, the Viewer role, and scheduled-screenshot notifications rounded out the governance and distribution story.
Two compounding bets: (1) the semantic layer + AI agent combination is the moat — every release deepens what an agent or human can do over governed data without writing SQL, and (2) embedding goes from "put a dashboard in your app" to "give your users a full BI app inside your product." These are complementary — Creator Mode is more compelling when the embedded experience can also answer questions in Slack and self-heal queries with calculated fields.
Expect Creator Mode to grow more embedding controls (white-labeling, role mapping, audit) since it's positioned for ISVs serving downstream customers. The Slack Agent likely gets siblings (Teams, in-app chat) and tighter wiring to dashboards so an agent can produce a chart, save it, and share it back. Calculated Fields expansion (filtered measures, more types) is already telegraphed in the release notes.
Chord is rebuilding Copilot on Anthropic models, Enriched Context, and a breaking SQL infra change.
Chord is a CDP that has spent the last quarter rebuilding its Copilot AI from the inside. The reasoning layer switched to Anthropic models, the context capture got expanded as Enriched Context, and the SQL generation pipeline took a breaking infrastructure change. Around that, the regular CDP work — Iterable data modeling, searchable tables, Activations sync redesign — continues at a steady release cadence.
Copilot is becoming the product. Each release this year has tied AI further into the CDP's core data plane — modeling, querying, activations — rather than treating it as a sidebar. Live documentation grounding and feedback memory in the latest release signal a push to keep Copilot accurate as the schema evolves underneath it.
Expect a deeper agentic move where Copilot proposes activations or builds segments end-to-end. The Iterable-style data modeling work hints at where AI assistance lands next.
See more alternatives to Cube →
See more alternatives to Chord →