> For the complete documentation index, see [llms.txt](https://bloomfilter.gitbook.io/bloomfilter.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://bloomfilter.gitbook.io/bloomfilter.ai/change-logs/2026-change-logs.md). # 2026 Change Logs ## June 2026 ### AI and Agent Capabilities Flora gained user feedback (thumbs up/down with reasons and an admin view), the ability to stop mid-conversation, sprint summaries, and risk scores in its data tools. Superusers can now pick the underlying model (Sonnet, Opus, GPT), reasoning effort, and configurable prompt caching.
### Automation and Workflow System A new Flora Automations skill introduced manual, cron, and event triggers with approval gating and Slack, email, and Teams delivery, plus a runs-history view. Work-period start/end triggers, smarter automation prompts, and better missed-target alert windows shipped, while the legacy Scheduled Job model and old workflow settings were retired.
### Metrics and Analytics New tooling included a Custom Calc admin with an AI calculation builder, a visual Custom Metric Builder, a "time in bucket" cycle-time metric, and agent dashboard filters for story points and work-item type. The CS team also got a batch of adoption-metrics commands covering logins, spending, targets, and integrations by category.
### Microsoft Teams Integration Teams support rolled out end-to-end over the month, moving from a backend-only developer build that mirrored Slack (AAD OAuth, Bot Framework bridge) to a full connect/disconnect UI with org-wide admin install, and finally to delivery of automations and daily digests into Teams DMs and channels alongside email and Slack. ### Performance and UX Improvements Significant fixes landed for dashboard charts (burn-up, burn-down, cumulative-flow, and active-sprint data), N+1 query fixes in Agent Miner, async DB hardening, Redis Channels SSL/timeout handling, and large code cleanups across 50+ modules.\
### Security and Breaking Changes Several cross-org access bugs were closed on 06-16 (RBAC enumeration leaks, a privilege-escalation path, and org-scoped agent sessions). Two breaking changes shipped the same day: org-update endpoints now accept only a limited field set and no longer process membership changes, and the project-members and health-tracking API endpoints were removed. ## May 2026 ### AI and Agent Capabilities Claude and CoPilot integrations providing real time usage statistics tied to JIRA work items providing visibility into the ROI of agentic spend. ### Automation and Workflow System \ The third-party ActivePieces automation engine was retired and replaced with an internal workflow system, featuring a new backend model with hook triggers and a frontend Automations tab in Flora Agent. ### Performance and UX Improvements \ Several releases included significant performance optimizations and user experience enhancements across various modules, such as Process Analysis loading, financials screens, and dashboard chart rendering. ### Slack Integration Enhancements Multiple releases focused on improving and productional-izing the Slack integration, including OAuth installation, per-user authorization, channel/DM delivery for scheduled jobs, and end-to-end chart artifact posting. ## April 2026 ### AI and Agent Capabilities Cursor and Codex integrations providing real time usage statistics tied to JIRA work items providing visibility into the ROI of agentic spend. Introduction of new ETL pipelines for GitHub Copilot and enhanced AI reasoning over GitHub PRs and task comments. ### Platform Infrastructure and Security The platform underwent substantial infrastructure upgrades and security enhancements, including a migration to Confluent Cloud for Kafka, Python version upgrades, retirement of legacy systems, and improved security measures for data handling and access control. ### Process Analysis Process Analysis dashboards have been enhanced with agentic data feeds, enriching cycle-time, throughput, and workflow-efficiency metrics. Teams can now correlate AI-assisted activities with overall process performance. ## March 2026 ### AI and Agent Capabilities Financials dashboard now supports additional AI models, ensuring accurate cost attribution as the platform evolves. Organizations benefit from transparent, up-to-date billing that reflects actual model usage across all Flora interactions. We've also incorporated agentic data, giving stakeholders a unified view of delivery costs alongside AI-driven insights. This integration supports more informed budgeting and resource-allocation decisions. ### Dashboards Dashboard access can now be scoped by role, ensuring that each user sees only the data relevant to their responsibilities. Administrators can configure visibility rules to align with organizational security and compliance requirements. ## February 2026 ### AI and Agent Capabilities Agents now leverage a persistence database layer, improving reliability and enabling more consistent state across sessions. Automatic compaction keeps Flora's data footprint optimized without manual intervention. A range of interface and tooling refinements improve overall usability and responsiveness. Global filters can now be applied at the project level, giving teams a consistent, scoped view across all relevant data. ### Adherence Module The Adherence view now supports filtering by workflow status, making it easier to identify where work stands relative to your defined process at a glance. ### Dashboards Module Pull request review time is now tracked and surfaced within the dashboards giving teams clearer visibility into where time is being spent across the delivery cycle. ### Financials Module Financials data is now governed by role-based permissions, ensuring users see only the financial information relevant to their access level. ## January 2026 UX enhancements represents a major user experience evolution for Bloomfilter, introducing three entirely new modules and significantly enhancing Process Analysis. This release breaks out Work Periods, Agentic Process, and Automation as independent modules, providing organizations with specialized tools for work period management, AI usage analytics and workflow automation alongside enhanced process intelligence capabilities. ### Key Highlights Introduction of three new standalone modules: Agentic Process, Automation and Work Periods. Major enhancements to Process Analysis (BETA) for improved consistency of metrics across Portfolios, Teams, and Boards with a clear separation of responsibilities between modules for better scalability and user clarity. ## Modules Overview ### **Agentic Miner (New):** Complete AI agent usage analytics enabling organizations to track, analyze, and optimize AI tool deployments across tasks, sessions, and costs.
### **Automation (New):** Visual workflow builder with extensive integration library, AI capabilities, and flexible utility functions for creating sophisticated automated processes without coding.
### **Process Analysis (BETA):** Enhanced process intelligence with consistent measures across Portfolios, Teams, and Boards, plus advanced initiative tracking and capacity management at Portfolio and Team levels.
### **Work Periods (New):** Independent module for comprehensive sprint and iteration management, separated from Process Analysis with dedicated Assessment and Comparison capabilities.
**Field Guides:** [Process Analysis](/bloomfilter.ai/modules/process-analysis.md), [Work Periods](/bloomfilter.ai/modules/work-periods.md), [Agentic Process](/bloomfilter.ai/modules/agentic-process.md), [Automation](/bloomfilter.ai/modules/automation.md) *** --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://bloomfilter.gitbook.io/bloomfilter.ai/change-logs/2026-change-logs.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.