Release Date: Jun 23th, 2026

1. Overview

Version 2.21.0 brings BrightSignals fully end-to-end, launches "Log in with Okta" for enterprise single sign-on, expands MCP connectivity, and introduces a full audit trail for engineering agent actions.

Highlights include:

• BrightSignals End-to-End: Real-time Slack alerts now flow from every quality run, with full monitoring in place.

• Enterprise SSO Live: "Log in with Okta" is now live, with automatic enterprise user provisioning.

• Expanded MCP Connectivity: Three new read-only workspace tools are available over MCP, with live connectivity testing in the web app.

• Engineering Agent Audit Trail: Every mutating action taken by engineering agents is now automatically logged and traceable.

• Platform Stability: Resolved a series of production issues affecting reliability, timeouts, and deployments.

  
  

2. Key Enhancements and Fixes

BrightSignals

• Delivered end-to-end, real-time push delivery for Slack alerts triggered by quality runs.

• Added monitoring and an on-call runbook for notification delivery.

Enterprise Auth

• "Log in with Okta" is now live, with automatic just-in-time provisioning for newly authenticated users.

• Hardened the authentication chain and added safeguards preventing users from being silently redirected to unprovisioned workspaces.

• Added workspace isolation for multi-workspace conversation threads.

MCP Connectivity

• Added three new read-only workspace tools available over MCP: workspace context, schema details, and model impact analysis.

• Improved the live connectivity card in the web app, including real-time tool listing and request testing.

Governance & Audit

• Introduced an audit trail for engineering agents: every mutating action is now automatically logged with full traceability back to the data that informed it.

Platform Stability

• Resolved a timeout issue affecting request handling under load.

• Fixed a data-type overflow issue affecting Snowflake timestamp handling.

• Hardened cross-origin request handling across MCP and agent routes.

• Improved deployment reliability with a more robust release process.

3. Feedback

We value your feedback to continue improving the Brighthive platform. Please share your thoughts or report issues to support@brighthive.io.

About Brighthive 

Brighthive is an agentic data platform that functions as a data team in a box — a coordinated set of specialized AI agents (BrightAgent) that work the full data lifecycle around the clock: connecting to your sources, cleaning and validating data, enforcing governance and data contracts, and keeping pipelines self-healing and live. Underneath every workspace, Brighthive builds and maintains a living knowledge graph and enterprise data catalog — capturing not just schemas and metadata but the tribal knowledge about your business, use cases, and policies that normally lives only in people's heads. That context is what lets the platform, and every downstream tool, reason accurately about your data instead of guessing. The result: every team inside the enterprise gets to skip the grunt work and go straight to trustworthy, self-service insight — querying, visualizing, and analyzing data faster, on a foundation that's clean and governed by default. Brighthive connects to your existing data stack or stands one up from scratch, augmenting or replacing point tools without disrupting how your team already works.