πŸ“’

v4.10.0 β€” One AI budget, clearer Findings

A shared monthly AI allowance and focused Finding detail make usage, evidence, and resolution easier to understand.

NEW

v4.4.0 β€” Notion Sources, cross-source edges, and conflicting claims

Connect Notion beside GitHub, auto-propose cross-source relationships, and surface conflicting claims with both Evidence trails side by side.

Galileo 4.4.0 connects Notion beside GitHub, proposes cross-source relationships automatically, and surfaces conflicting claims β€” so lying documentation shows up with both Evidence trails side by side.

New

  • Notion Connector β€” connect a Notion workspace as a Source; every page the integration can read lands as a document Artifact with bounded page-block Evidence.
  • Cross-source Edges β€” after Sync, Galileo proposes Notionβ†’GitHub describes Edges (LLM suggests, deterministic grounding decides), so Findings can span both Sources.
  • Conflicting-claims Findings β€” when two Sources disagree about the same service, Galileo opens one Finding on that service with both grounded quotes side by side β€” never picking a winner for you.
  • Source edit β€” rename a Source or rotate its credential without deleting it. Identity stays immutable; a credential change is re-verified against the same system.
  • Duplicate-Source protection β€” connecting the same GitHub repo or Notion workspace twice is blocked at creation with an immediate form error.

Improved

  • Realistic README grounding β€” GitHub READMEs are stored as structured blocks (like Notion pages), so cross-source quotes match what you actually read β€” not raw markdown markup.
  • Notification delivery β€” invitation emails honor email opt-outs for existing users; bulk changelog announcements are safely re-runnable without double delivery.
  • Admin and org tables β€” Graph, Findings, and admin indexes share one DataTable driver for search, filters, and live refresh.

Fixed

  • Transferring ownership to yourself no longer leaves the Org without an owner.
  • Cross-source proposal calls have more headroom so thinking models are less likely to truncate mid-response.