Release Date: Sep 29th, 2026

1. Overview

Version 2.16.0 completes the BrightStudio custom agent story with reusable Skills and true multi-person collaboration, delivers the dbt transformation pipeline in full, and adds governance policy tiers, Azure Synapse support, and Human-in-the-Loop credentialing.

Highlights include:

• BrightStudio Custom Agents, Complete: composable Skills that attach to any custom agent, plus collaborators who can manage an agent together.

• dbt Transformation Pipeline: full delivery, an entire connect-to-transform workflow now live inside Brighthive.

• Governance & Ingestion: policy enforcement tiers, Azure Synapse (BYOW) support, and secure mid-flow credentialing.

2. Key Enhancements and Fixes

BrightStudio

• BrightStudio Skills launch — composable, first-class agent capabilities built once and attached to any custom persona.

• A Skill built for one agent can be reused across any number of other custom agents.

• Collaborative BrightStudio launches — collaborators, not just the original creator, can now manage a custom agent together.

dbt Transformation Pipeline

• Reaches full delivery: connect a GitHub repo, select a dbt Cloud job from a dropdown (no manual job IDs), view model-level metadata (SQL, lineage, PR links), and trigger transformations, an entire workflow now live inside Brighthive.

• The dbt agent migrated to a more flexible reasoning pattern, resulting in fewer unnecessary interrupts and better auto-reading of workspace configuration.

Data Governance

• Workspace policies can now be set to Active, Enforced, or Admin Only, and are automatically applied to agent behavior.

• Agents can pull schemas, glossary terms, and policy definitions on demand.

Ingestion

• Azure Synapse support (Bring-Your-Own-Warehouse), including dedicated ingestion routing, quality-check support, and a provider-specific setup UI.

• Human-in-the-Loop credentialing — ingestion flows can now pause to securely collect credentials mid-flow.

Platform & Reliability

• Began migrating BrightAgent's model routing to a modernized runtime (early groundwork).

• Decommissioned legacy pipeline infrastructure.

• Upgraded the web app's core framework.

• Tightened the Slack bot to only respond to @mentions, DMs, and thread replies.

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.