Today we’re previewing our work to build an open standard @Meta (@muse and Meta Business Agent) and Sierra are developing along with industry partners at Genesys, NiCE, Decagon, Rocket, Shopify, Stripe, and Walmart that defines how personal agents interact with businesses. What motivates this work is making things even better. More frictionless for people using Muse, and better for the businesses serving our shared customers. Excited to build this together.

Today we’re announcing Personal Agent Protocol — an open standard @Meta and @SierraPlatform are developing along with industry partners at @Genesys, @instinct, @RocketOTD, @Shopify, @stripe, and @Walmart. It will help define how personal agents interact with businesses and is open for anyone to implement. You can read more here - and if anyone is interested in joining let me know!

Scheduled Tasks on @Muse - An update on reliability We deployed a fix to Muse to improve scheduled task and cron recovery and reliability especially, and have hardened our monitoring and alerting of the cron systems in the VMs. Over the last few days the Muse team has been deploying a few changes to: Improve the KV cache hit rate after increasing the context window size of the underlying model Improve our VM scheduling algorithm to reduce downtime during deployments Deploy a new authentication token format across the fleet for more fine-grained access. During these changes we had a few SEVs (outages) where the inference tier was unresponsive, and the VM scheduling resulted in VMs not being available for longer periods of time during deployment and being unresponsive to clients. We observed after we recovered from these outages that several crons and scheduled tasks failed to resume / heal properly when the outage was done, resulting in several users receiving reports from their Muse that the crons have been failing for a while. We apologise for this incident, and know how much this disrupts your flow especially since many users rely on muse to reliably deliver outcomes for them. We take these outages seriously, and are running a full audit of our recovery systems and tools, and are adding more dashboards and alerts so you can continue to receive the high quality service we want all users to have.

Muse was down this morning for some of our users. We were able to debug the issue and rolled out a fix. Sincere apologies for everyone who had this issue. We are taking steps to prevent these issues from happening and to also communicate them clearly when they do.

David from the Muse team here. I responded to Matt on Threads and sent him a couple of DMs offering to help and look into what happened. In the past, when we’ve worked with users to investigate similar reports, we’ve consistently learned that Muse was following direct instructions and correctly asked for permission. Would love to help and figure out what’s going on here!

Things my Muse agent got done while I took a nap this afternoon: 1. Cleaned up my ancient Hotmail inbox from 96% full to 60%. Went through 80K emails, deleting 20k+ old promos and newsletters with my approval, keeping a full audit log of everything. 2. Chased down a missing refund from my old internet provider. Chatted with customer support, pulled the details from my emails, and got me an exact refund date. 3. Scheduled my HVAC tune-up based on previous years maintenance history. All while I was peacefully napping. Didn't even lift a finger. I took a nap. My AI ran my errands. Jaw dropping stuff 🤯 $META

Very proud of my former colleagues at @Meta for shipping such great products again and going from underdogs in the AI race to having one of the best mass-market consumer products with @Muse. Shipping velocity is so back too!