BlogMeta Muse for RIAs

Meta Muse for RIAs

Meta's Muse can sign into your apps and work around the clock. Here is where it helps an RIA, and what to check before it touches client work.

By Jason AlafganiOctober 1, 2026 ·

Muse is a capable always-on assistant for a person's own work at an RIA: research, inbox and calendar, follow-ups, and one-off tasks the person checks. For repeated client work like account opening, CRM updates, and service requests, it plans each run fresh and keeps records per user, so most RIAs will want a verifiable agent for that work and keep Muse for the rest.

This fall, three AI companies shipped the same idea within weeks: an agent with its own computer that works for you around the clock. xAI launched Grok Bot in August, Meta launched Muse in September, and OpenAI answered with dots at the end of the month. Operations teams at RIAs are already asking whether one of them can take work off their plate.

This guide is for that question. It covers what Meta's Muse is, where it fits at an RIA, and the five things the firm has to answer before an always-on agent touches repeated client work. Every product fact comes from Meta's own pages as of October 1, 2026, and these products are changing fast.

What is Meta Muse?

Muse is Meta's personal AI agent, launched September 8, 2026 in the US and since expanded to Canada, on iOS, Android, the web, and Mac. It runs on Meta's Muse Spark model inside its own isolated Linux VM with a browser, file system, and terminal. You give Muse a goal; it builds a plan and advances the work on its own, on a schedule and in response to events.

A separate agent called Sentinel is the sole authority over Muse's connector actions and network traffic. On September 29, Meta added Muse for Small Business, with connectors like QuickBooks, Slack, Box, Dropbox, and Stripe inside the same app.

Muse is good at personal operations: planning, research, messages, errands, and a small business owner's admin, with a permission system that was clearly designed with care.

Plans. Free with a usage limit, Power at $20 a month, and Maximum at $100 a month. Meta has not described a team or enterprise plan, an admin console, or SSO.
Model. Muse Spark, running in an isolated VM Meta calls Muse Secure VM.
Permissions. Sentinel allows, denies, or asks you. Grants can be one-time, per session, per task, time-bounded, or perpetual.
Records. An in-app activity log Meta describes as a complete audit trail of what Muse has done and plans to do.
Training. Sanitized trajectories are used for training by default, with an opt-out.
Connectors. Email, calendar, and Meta's apps, plus dozens of small-business tools. Muse can also write its own connectors for services with an API.

Product details as of October 1, 2026, from the vendor's own announcement, help, and security pages.

Where RIAs want to use Muse

Nobody at an RIA needs an agent to do the professional judgment. They want back the hours their teams spend on repeated, system-to-system work:

Account opening. Turning a new household's details into completed custodian forms and sending them for signature in DocuSign.
CRM updates. Getting meeting notes, tasks, and life events into Wealthbox, Redtail, Salesforce, or Practifi.
Service requests. Handling address changes, distributions, and beneficiary updates from the shared inbox.
Billing and reconciliation. Checking fee schedules and balances across Orion, Black Diamond, or Tamarac and the CRM.
Review prep. Assembling the packet for each client review from the portfolio system and the CRM.

Picture an advisor asking Muse to stay on top of client follow-ups: send the meeting recap, remind the client about the missing beneficiary form, and set a task for the next review. Muse plans the work and Sentinel asks before anything goes to a client.

For an RIA the harder questions come after the email is sent. That message is a written communication the firm may need to keep under Rule 204-2, and it went out from a personal agent with a per-user activity log, no stated export, and no admin access. Meta has not named Wealthbox, Redtail, Salesforce, or portfolio-system connectors, so the CRM update is either skipped or done through the browser.

Five questions before Muse touches client work

None of these are reasons to avoid Muse. They are the questions any RIA has to answer for any agent that acts on a client's behalf.

Will Muse do the work the same way every time?

Muse is goal-driven. It plans, then works, and it learns from your conversations as it goes. Meta describes only two parts of Muse as deterministic: its approval cards and its credential storage. There is no saved, step-by-step workflow a reviewer can read before a run.

For account opening, CRM updates, and service requests, that matters. You cannot test a procedure on last month's cases and rely on the result if the next run is planned again from scratch.

Who supervises Muse at an RIA?

Sentinel is a thoughtful design: a separate agent that sits outside Muse, tracks whether a process has read your data, and decides whether an action is allowed, denied, or needs you. Meta also chose not to ask about everything, because constant prompts get ignored. Read-only, previously allowed, or low-risk actions proceed without asking, and grants can be perpetual. That is right for one person's life. In a firm, it means the supervision lives in each user's individual grants.

Under the SEC's compliance rule, Rule 206(4)-7, an adviser needs written policies and procedures reasonably designed to prevent violations, and for dual registrants FINRA Regulatory Notice 24-09 reminds firms that Rule 3110 requires a reasonably designed supervisory system when they use generative AI. A procedure that is re-planned on every run is hard to write a policy around.

Can the firm show what Muse did?

Each user has an activity log of what Muse did and plans to do, and can download their files and memory. Meta has not described an export format, admin access to those logs, or a retention period.

SEC Rule 204-2 requires advisers to keep books and records, including copies of written communications on listed topics, generally for five years. An agent that emails clients or updates account records from a user's login is creating those records, and a per-user activity feed is not a books-and-records archive.

What happens to client data?

Muse uses sanitized trajectories for training unless you opt out. Meta's security page also says the current architecture does not prevent Meta from accessing data when needed to support, secure, or operate the service; a Confidential VM with a user-held key is planned for later this year.

Regulation S-P requires advisers to safeguard customer information and, since the 2024 amendments, to run an incident response program. An agent holding an adviser's email and CRM access is part of that program.

Meta's own security page says "prompt injection remains an open problem."

Does Muse reach the systems RIAs run on?

Muse connects to email, calendar, and Meta's apps, and Muse for Small Business adds QuickBooks, Slack, Box, Dropbox, Asana, Shopify, Stripe, and others. Meta has not named Microsoft 365, Outlook, or Salesforce connectors.

RIA operations run through the CRM (Wealthbox, Redtail, Salesforce, Practifi), the portfolio system (Orion, Black Diamond, Tamarac, Addepar), DocuSign, and a stack of custodian forms. Reaching a system is only half of it; the other half is doing the same thing in it every time.

	Meta Muse	Caddi
How the work is defined	A goal Muse plans against each time	Tested code you can read and change
Same input, same path?	Not claimed by the vendor	Yes, for the coded steps
Role of AI in a run	Plans and performs each step	Named judgment steps, scoped and logged
Human control	Sentinel allows, denies, or asks; grants can be perpetual	Review the procedure; exceptions go to a named person
Record of each run	Per-user activity log; no stated admin export	Every run logged, tied to its source documents
Built for	A person's own varied work	RIAs' repeated back-office workflows

Meta Muse vs. Caddi on what an RIA has to answer before an agent runs client work. Meta Muse details as of October 1, 2026.

What a verifiable agent does differently

The fix is not a better prompt or a stricter approval setting. It is moving the procedure out of the model. A hybrid agent runs the workflow as code, which can be read, tested, and versioned, and calls AI only for the steps that need judgment, each one scoped and logged.

For account opening, that means the code pulls the household from the CRM, fills the custodian's forms, and sends the DocuSign envelope the same way every time, while AI handles the judgment inside it: reading a scanned trust document, matching a beneficiary to the right record, spotting a missing signature. Anything unclear goes to the operations team, logged.

That split is what makes an agent verifiable: a reviewer can read the procedure before it runs, every judgment call is on the record, and changes are made on purpose.

More on the idea in what are verifiable AI agents and what are hybrid agents.

Connect Wealthbox to Caddi
Allow
1Sign in to your tools
One click each for Wealthbox, Docusign and Microsoft Outlook. No API keys.
Automate account opening.
ScreenshareType it
2Show or tell it
Screenshare the job, or type it in chat. Change it any time.
Running
14 done1 for review
3Watch it run
Caddi does the work and flags anything unsure for review.

Show Caddi the workflow on a call or describe it in chat. It runs as tested code across your tools, with the judgment steps scoped and logged.

How RIAs can use both

Muse and a verifiable agent are not competing for the same job. Let people use Muse for the work around them, where every task is different and the person who asked checks the result.

Put the repeated client work, account opening, CRM updates, and service requests, on an agent the firm can verify. That is what Caddi builds: an ops person shows Caddi the workflow on a screen share or describes it in chat, Caddi runs it as code across the firm's tools with the judgment steps logged, and the team changes it in plain English as the work changes. Across Caddi customers, 99% of agent runs complete successfully.

Muse shows how much an agent can now do inside your apps. For RIAs, the next question is whether you can check what it did. Keep Muse for personal work, and run client work on a procedure you can review, with a record for every run.

Keep reading

Caddi

See how Caddi AI Agents can run your RIA's back office the same way every time and log every run for compliance

Or sign up free

Frequently asked questions

Is Meta Muse safe for RIAs?

Muse has real safeguards: sentinel allows, denies, or asks; grants can be perpetual. For a person's own work, those are sensible. For repeated client work, an RIA also has to answer for supervision, records, and confidentiality, and Muse plans each run fresh with records kept per user. Most firms will keep it for personal work and use a verifiable agent for client workflows.

Can Meta Muse run account opening, CRM updates, and service requests unattended?

It can attempt it: Muse works in the background and can reach many apps. But it decides how to handle each case on that run, and the vendor does not claim repeatable runs, so the firm cannot test the procedure once and rely on it. For unattended client work, a verifiable agent that runs the steps as code is the safer fit.

Does Meta Muse keep an audit trail?

Each user has an activity log of what Muse did and plans to do, and can download their files and memory. Meta has not described an export format, admin access to those logs, or a retention period. For RIAs, check whether that record can be exported, retained, and reviewed at the firm level before relying on it.

Does Meta Muse train on our data?

What should an RIA use for repeated client work?

A verifiable agent: one whose procedure you can read, whose judgment steps are logged, and whose every run leaves a record. Caddi builds these for RIAs. Your team shows the workflow on a screen share or describes it in chat, and Caddi runs it as code across your tools, with exceptions routed to a named person.