ProductMetaConfirmed
Story 1 of 11 in the Friday 6 November editionMeta launches Spaces in Muse for custom interactive tools built from chat
Users can describe an idea to build persistent planners, trackers, and games inside the Muse app, pin them to navigation, and keep them updated through connected apps.
Meta launched Spaces in the Muse application on 6 November 2026, introducing an interactive way for users to build custom experiences by describing an idea in plain language. Rather than keeping recurring projects inside scrolling chat threads, a space turns a prompt into a persistent surface inside Muse, such as a holiday gift tracker, a daily word game, a freelance client hub, or a trip itinerary.
Custom layout and scheduling
Once Muse generates an initial space from a user’s prompt, the user can keep refining its layout, visual styling, and behaviour through conversation. Users choose where each space sits in the interface: spaces can be pinned to the sidebar, promoted into the main navigation tabs, hidden when inactive, or scheduled to appear on specific days, such as showing a work planner on weekdays and a weekend tracker on Saturdays.
Live background updates
Spaces connect to external applications that the user links to Muse, updating automatically in the background as new emails, calendar events, price changes, or marketplace messages arrive. Users can check off tasks, add notes, and edit entries directly inside the space. Spaces are available everywhere Muse operates as individual workspaces, while multi-user collaborative sharing remains in exploration.
Sources
- PrimaryDesign the Muse App, Just for Youabout.fb.com · Meta Newsroom announcement
- On XAlexandr Wang on Muse Spacesx.com · Launch post and examples
- On XMark Zuckerberg on Muse Spacesx.com · Official X post
The rest of the day
Read the whole day02ModelMeta
Meta rolls out specialized Muse and Meta AI models with Active Memory
Trained using Muse Wonder, the upgraded models bring Active Memory and Active Focus to consumer Muse and Meta AI interfaces with 2.4 times lower critical forgetting.
03InfraOpenRouter
OpenRouter launches next-generation Auto Router and Auto Code for coding agents
The new routers pick a model and reasoning effort per request within workspace guardrails, matching Claude Opus 5.5 on coding benchmarks at 74% lower cost.
04ResearchOpenAI
OpenAI and Ligo introduce BioBasicsBench for everyday wet-lab biology
The 100-task benchmark tests whether AI agents can interpret raw gels, flow cytometry plots, plates, and microscopy images, with GPT-6 Astra scoring 66.7%.
05ResearchAnthropic
Anthropic details Claude agent memory architecture and offline dreaming
An Engineering Blog post explains how background consolidation reviews transcripts, extracts corrections, and injects a compact memory layer into new sessions.
Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X







