This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+2 more
Summary
AI summaryAdded sixteen new verticals with named human sign‑off and thirty‑three new connectors.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds 33 new connectors (65 total). Adds 33 new connectors (65 total). Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Adds 7 new compliance reviewers. Adds 7 new compliance reviewers. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Adds safety invariant: irreversible step behind human gate with accountable owner for every flow. Adds safety invariant: irreversible step behind human gate with accountable owner for every flow. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Adds 250 library tests and live run verification for all 16 flows. Adds 250 library tests and live run verification for all 16 flows. Source: llm_adapter@2026-06-07 Confidence: high |
— |
Full changelog
Research-backed US-market expansion beyond the original 6. Each new vertical pairs a large displaceable-labor pool with a legally-required named human who signs the risky call — the shape the v2.43.0 safety engine is built for. All sixteen ship green on --validate and were verified with live flow runs.
New: prior-auth ($35–56B) · aml ($61B) · soc ($4–6B) · insurance ($36–38B) · mortgage ($40B+) · title ($16.2B) · credentialing · collections ($13.5–16B) · freight ($19–125B) · cro ($20–28B). Each escalates the liability-bearing call to a named human (medical director, BSA Officer, SOC analyst, underwriter, DE underwriter, title officer, credentialing committee, attorney, licensed broker, PI).
- 33 new connectors (65 total), reusing live adapters (sanctions-screen, e-signature, ehr-fhir, payment-rails) so several new verticals run live on day one.
- 7 new compliance reviewers; insurance/mortgage/cro reuse existing reviewers.
- Every flow carries the safety invariant — irreversible step behind a human gate + accountable owner.
- 250 lib tests; live runs of all 16 pause cleanly at their human gate.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About great_cto
Engineering-management layer of 34 specialist AI agents covering the full SDLC (architect, PM, senior-dev, reviewer, QA, security, devops, L3-support + 18 archetype-specific reviewers) with auto-detected archetypes and compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Runs in Claude Code, Cursor, Codex CLI, Aider, and Continue via AGENTS.md + MCP. MIT.
Related context
Related tools
Earlier breaking changes
- v2.72.2 Removes Autopilot sidebar item and Operate topbar button from dev board.
- v2.55.0 Hard-gates the Build board; redirects invite sessions to Operate for operators.
- v2.43.0 Runtime now blocks autonomous execution of irreversible actions without prior human checkpoint.
- v2.43.0 Adds reversible and blastRadius fields to every flow step.
- v2.32.0 Removed AgentShield scanner and its CLI commands.
Beta — feedback welcome: [email protected]