Explore the key innovations in this roadmap, which highlight upcoming improvements and advancements.
- Hubs
- Appearance & Branding: Adds a new organization-level configuration that lets Organization Administrators customize the appearance of Hubs. You can configure themes and colors for Light and Dark modes, upload logos and a favicon, set the platform name and accessibility text, and configure the default language and languages available to users.
- Agentic Hub
- Processes in Monitor provides a dedicated view to monitor the execution of Agentic Processes.
- Processes monitoring: Lets you search by process name, filter by date range, review executions in a tabular view, open process details, stop running processes, and automatically refresh process statuses to reflect asynchronous updates.
- Processes Overview: Lets you review process details in an overview card, search and filter artifacts, and view artifacts in a tabular view.
- Processes History: Lets you search activities by name, filter history by date range, and review activity execution history and steps in a tabular view. Supports scenarios involving user file attachments, generated files, disabled logs, failed Tool executions, multiple Agents, and conditional or parallel workflows.
- Configurable access: Lets you enable or disable the Processes section from the application settings.
- You can interact with a Chat with Data Assistant in Run to query and analyze data using natural language, refine your queries, and explore results through interactive visualizations. For more information, see Chat with Data Assistant queries in Run.
- Console
- Enhancing Quota Management capabilities.
- Simplifying quota administration and automation for easier usage limit management across the platform.
- Improving aspects to ensure that organizational limits appear correctly in the interface.
- Ensuring that previously configured organizational limits are consistently displayed.
- Preventing discrepancies in limit visibility that could make it difficult for users to monitor and manage resource usage.
- Ensuring that appropriate limit information is displayed.
- PyGEAI v0.8.0
- The pygeai.proxy module will be deprecated and moved to a standalone package. You must migrate to the new pygeai-proxy package.The proxy functionality for managing MCP and A2A servers has been extracted from the main pygeai package into a dedicated pygeai-proxy package. This change provides better separation of concerns and allows the proxy functionality to evolve independently.
This section lists features and improvements still in development, with no confirmed release date.
- Agentic Hub
- Corpus is an indexed store that holds your documents, called resources, along with their associated metadata. Unlike a RAG Assistant, which combines ingestion, retrieval, and generation into a single component, Corpus keeps ingestion and retrieval separate, so an Agent can decide when to query it and use the results to generate a response. To create or update a Corpus, you can use the Corpus API or work directly in Agentic Hub by following the steps in How to create a Corpus. If you don't see the Corpus option in the Build section, follow the steps in How to enable the Corpus option in the Build menu to activate it.
- Corporate Hub
- Introducing an async Python User SDK that you use to consume Corporate Hub connectors and services.
- Allows you to work with a single CorphubClient that resolves typed handles and communicates over REST through the Gateway; no message broker is required. You can access relational and writable databases, vector indexes, the semantic mapper, Agents, MCP bridges, provisioner, and ontology catalog from one client
- Intelligence Hub
- New custom LLM provider management to let Organization Administrators register and govern external model provider.
- Allows admins to define provider connection settings.
- Allows admins to register the Models exposed by each provider.
- Supports organization-wide or project-level visibility for provider availability.
- Adding OpenAI / Azure AI Foundry Speech-to-Text models support:
- whisper-1
- gpt-4o-transcribe
- gpt-4o-mini-transcribe
- API
- New /videos/generations endpoint so you can generate videos via Vertex AI’s Veo 2, with proxy handling for long-running operations and MP4 decoding.
- New token management API so you can create, revoke, and update project-level API tokens using secure, role-validated endpoints (project tokens cannot manage tokens).
- New secure endpoints to list Organizations and Projects by user email that use OAuth and restrict access to ProvisioningServices or GAM Administrator roles, so you manage roles effectively across platforms.
- Improved portability via CLI and Python SDK export that lets you programmatically export Agents, Tools, and Agentic Processes for backup and reuse.
- Improved observability for the Data Analyst Assistant that forwards logs and traces via OpenTelemetry, so you correlate requests using trace_id, span_id, and trace_flags across your monitoring tools.
- Console
- Prompt Files: It allows you to upload files at the Organization and Project level so that the Agents you define can use them to answer questions.
- Quota Alerts: Email notifications will be sent when a Project or Organization reaches its soft limit, helping teams manage usage proactively.
- Model Configuration Controls: Projects will gain the ability to define which LLMs are enabled, improving governance and cost management.
- Evaluation module backoffice.
- Security consent Flow so you must read and accept Terms and Conditions in Agentic Hub and Console, with identity, date, and time recorded; consent persists across future logins.
- Improved governance with token consumption usage limits so you can set quotas in millions of tokens at Organization and Project level for tighter control and accountability.
- Improved global navigation consistency that introduces a standardized navigation bar across Console, Workspace, and Agentic Hub with unified links, placement, and accessibility.
- Hubs
- Enhancing Iris in Agentic Hub helps you find existing solutions from natural-language requests before creating new ones.
- Will use semantic search to recommend relevant solutions.
- Will highligh matched solutions by name in chat.
- Will open the filtered Discover view automatically through the UI action flow.
- Will preserve conversation context across module navigation and organization or Project changes.
- Options to export/import Agentic Processes and Flows.
- RAG Assistant and API Assistant will migrate from the Console to Agentic Hub:
- This gives Assistants access to advanced configuration, custom Integrations, and a flexible development workflow in Agentic Hub.
- New RAG Agents so you can connect Agents to Knowledge sources (document repositories, vector stores, databases, or graphs) and configure retrieval Integrations. You link Knowledge to prompts and Integrations, create Agents with templates or via an Assisted flow, and start chatting after uploading documents.
- New RAG‑enabled Agents that let you define Knowledge sources, attach retrieval tools, and chat over documents, databases, vectors, or graphs, with a simple path to migrate from current RAG Assistants.
- Knowledge abstracts your sources.
- Retrieval tools define access, chunking, and prompts.
- Agents tie prompts, tools, and selected Knowledge for seamless RAG.
- Audit Logs: Agentic Hub will begin tracking user actions related to entity creation, updates, and deletions—strengthening traceability and accountability.
- New per-project avatar prompt templates with dynamic variables so you can differentiate brand and style across projects while preserving agent name and role; the generator compiles the project prompt with safe defaults and runtime variables.
- New prompt files in agents so you can reference uploaded prompt files directly inside an agent’s prompt to enrich context.
- Security guardrails per agent so you can prevent prompt injection and moderate both inputs and outputs with versioned checks validated against supported providers.
- Import MCP remote servers as Integrations with auto-detected authentication and optional auto-registration.
- Improved autosave behavior so you can keep work safe during connection loss.
- Use an offline/local autosave buffer that syncs when the connection resumes.
- See clear status feedback such as “Saving…”, “Last saved…”, “Saved offline – syncing soon”, or “Save failed – retry”.
- Flows
- Improved BPMN compliance in the agentic process engine that enables throw/catch handling for intermediate signal events, so you coordinate process parts reliably.
- New deterministic Gateway conditions that let you define boolean routing rules using process variables (AND/OR), including natural language entry that the system translates into verifiable expressions you can review and edit.
- Improved editing confidence that adds resilient autosave with a local offline buffer and clear status messages (e.g., Saving…, Last saved…), so you avoid losing work during disconnects or session expiry.
- LLMs
- Improved cost accuracy with conditional handling based on tokens consumed so you can align billing to provider models. Support includes Vertex AI (e.g., Gemini 2.5 family, including audio tokens), cached-token pricing, and regional pricing for providers such as OpenAI and Azure OpenAI.
- Improved cost accuracy that applies provider‑specific conditional pricing based on token counts (including audio and cached tokens) and regional pricing for providers such as Vertex AI, OpenAI, and Azure OpenAI.
- VoiceAgents: Real-Time Conversational AI with Speech
- VoiceAgents introduces real-time, voice-based interactions with AI agents, enabling natural, two-way conversations through speech. Powered by advanced audio transcription, natural language understanding, and text-to-speech synthesis, this feature allows users to speak directly with AI agents and receive immediate spoken responses, bringing human-AI interaction to a whole new level of fluidity and accessibility.