Releasesby GlyphChat with Lovable across your workspace or inside a project
You can now chat with Lovable to think, ask, and plan without changing any code. Chatting is free within a daily chat allowance on Free, Pro, and Business plans. Chats , outside your projects: private conversations where you think through an idea, ask about your apps and workspace, work in your connected tools, create files, and send work to a project when...
Also shipped Sep 21, 2026Lovable in September 2026 →
BigQuery Studio query results pane shows recent run history
The Query results pane now shows a short history of recent runs for a query, including multi-statement queries, without switching to the Job history tab. It is generally available.
The query history system table is now generally available
The system.query.history system table is now generally available. Use it to access account-wide records for queries run on SQL warehouses or serverless compute, including execution status, duration metrics, and query source. See Query history system table reference .
Cortex AI Function Evaluation for measuring quality (Public Preview)
Snowflake Cortex AI Function Evaluation is now available in public preview, enabling customers to measure the output quality, cost, and token usage of custom AI Functions and Cortex AI calls against labeled datasets.
Cortex AI Function Optimization for more efficient AI implementations (Public Preview)
Snowflake Cortex AI Function Optimization is now available in public preview, enabling customers to automatically search across prompts and models for improved implementations of custom AI Functions.
Cortex Agents Compact API (Preview)
The Cortex Agents Compact API is now available in preview. Use the agent:compact endpoint to summarize a conversation and pass the compact representation to subsequent agent:run requests. Compacting conversation history reduces token consumption and helps conversations stay within the model context window.
You can now use the AlloyDB Columnar Engine as a read-optimized, in-memory cache for HNSW vector indexes
You can now use the AlloyDB Columnar Engine as a read-optimized, in-memory cache for HNSW vector indexes. This feature is generally available ( GA ). It accelerates vector search performance and increases queries per second (QPS) for vector workloads. For more information, see Accelerate queries with the Columnar Engine .
More from LovableEvery Lovable release →
Jev for typed decisions in your app's AI features
Your app's AI features can now use Jev Latest , a typed decision model from TypeSafe that returns a category, a score, or a yes/no probability instead of generated text. Ask Lovable to use it for ticket triage, content moderation, routing, or search ranking.
Use your connected tools from Lovable in Telegram
Lovable in Telegram can now work in your connected tools, such as Slack, Notion, or HubSpot, under the same rules as Chats. Lovable reads from a connected tool without asking, and asks for your approval in the chat, with a Permission needed card, before it creates, sends, or changes anything through a tool.
Set a default design system for each group
Workspace admins and owners on Business and Enterprise plans can now set a default design system for a group from the group's detail page in Settings → Groups . Members of the group get it pre-selected when they create a project, in place of the workspace default, so each team builds on its own components and styles.
Manage agent permissions from your account settings
You can now review and change every agent permission from one page, Settings → Your account → Preferences → Agent permissions . It lists what Lovable may do without asking you first, for each connector available in your workspace and for creating or editing projects from a chat.
Connect your app to Parallel
You can now connect your Lovable app to Parallel to search the live web, read any public page or PDF as clean text, get cited answers to research questions, and run deep research tasks that fill structured data with sources. It fits lead enrichment, due diligence, market research, and chatbots grounded in current sources.
Organize project files into collections
The project Files tab has a new layout. You can now group files into collections, where one file can belong to several collections at once, upload your own files or drag them onto the tab, and see new files appear as Lovable creates them.
Claude models for your app's AI features
Your app's AI features can now use Anthropic's Claude models, with no Anthropic account or API key. Ask Lovable to add Claude to any newer app (created from May 13, 2026, which uses TanStack Start) for chatbots, document and image analysis, field extraction from uploaded PDFs, and structured output.
App + chat connectors: AWS API, Azure Cloud API, Azure Graph & Entra API, Google Cloud API, and Looker
Five new app + chat connectors let your apps work with your AWS, Azure, and Google Cloud accounts and with the metrics your team defines in Looker. The cloud connectors give your app access to those services and do not host or publish your Lovable app on them. Add them from Connectors , or ask Lovable in a project to connect one.