Using Meta’s Muse for Meal Planning, Refunds and To-Do Lists

Matthew Berman demonstrates four tasks for Meta’s personal AI agent, with user approval before selected actions.

MBMatthew Berman登壇者 · Forward Future
チャンネル
Matthew Berman
公開日
2026年10月1日
動画
1:06
読了時間
1 分
スライド
1
原文
英語
YouTube で開く
スクロールすると動画は右下に小さくなって再生を続けます。字幕は閲覧言語に合わせて切り替わります。
閲覧言語2 言語で読めます
この記事はまだ日本語に翻訳されていないため、英語の原文を表示しています。
要約

30 秒でわかる

In a video sponsored by Meta, Matthew Berman demonstrates Muse, a personal AI agent, with examples including a birthday card, meal planning, a refund request and subscription management. He describes user approval for ordering groceries and contacting support, and says users choose what the agent can access.

  1. 1A personalized cardBerman asks Muse to create a birthday card using details about what the recipient enjoys.
  2. 2Dinner and groceriesHe provides preferences, budget and refrigerator contents; Muse helps plan meals and a shopping list, with approval before the order.
  3. 3A refund requestAfter receiving the order details and problem, Muse asks permission to contact customer support.
  4. 4Subscriptions and preferencesMuse helps identify unused subscriptions for Berman to review and can be personalized with a name, appearance and personality.

ポイント

  1. Muse can help create a personalized birthday card from the recipient’s interests.
  2. A meal-planning request can include dietary preferences, a budget and food already on hand.
  3. In the demonstrated workflow, Berman approves an order and decides whether Muse may contact customer support.
  4. Muse can help work through a to-do list, including identifying subscriptions for the user to review.
  5. The video is sponsored by Meta; its examples are demonstrations rather than independent guarantees of results.
全文

チャプターごとに整えた全文を読む

文字起こしのみ
01

Birthday cards and dinner planning

Berman introduces Muse and gives examples of personalized cards and meal planning. He says he approves a grocery order before it is sent.

I give my to-do list to Muse, Meta’s personal AI agent. In this Meta-sponsored demonstration, I start with a customized birthday card: tell Muse what the recipient enjoys, such as hiking, food or belly rubs, and it can help create a card tailored to them.

For dinner, I give Muse my food preferences, budget and what is already in my fridge. It can plan meals around those details and make a grocery list. I also ask it to help place an order, but I approve it before it goes out.

02

Refunds and to-do lists

He demonstrates a refund request and asks Muse to find unused subscriptions. He describes permission and review before actions.

Drafting a refund request in Muse
スライド 1 / 1Drafting a refund request in MuseThe phone screen shows a draft support request for a damaged item; the demonstration says the user decides whether Muse may contact support.

Next, I provide order details and explain a problem to get help requesting a refund. Muse asks permission to contact support, and I decide whether it can proceed. The video shows a draft request; it does not establish that a refund was obtained.

I also ask Muse to work through my to-do list, starting by finding subscriptions I no longer use. I review which ones to cancel, and I can add other tasks from my phone while I am busy elsewhere.

03

Personalizing the agent

Berman says users can choose the agent’s appearance and personality, and control what it accesses.

You can give Muse a name, choose its look and shape its personality. I say it remembers preferences and that you choose what it can access. Meta describes the app and its permissions in its [Muse announcement](https://about.fb.com/news/2026/09/introducing-muse-personal-ai-agent/).

同じチャンネルの記事

スライド 12 枚34:21EN
Matthew Berman· 2026年10月27日Matthew Berman Examines Anthropic’s IPO Filing, AI Growth and GovernanceMatthew Berman, Sam Altman · Forward FutureThe presenter reviews the S-1’s financial metrics, compute strategy and voting structure while questioning the tension between rapid AI development and safety.AnthropicAI Safetyエンタープライズ AI+2
0:26EN
Matthew Berman· 2026年10月25日Sam Altman on Human Values and Problem-Solving in an AI WorldSam Altman · OpenAIIn a short interview excerpt, Altman considers the enjoyment of solving hard problems and the human role in interpreting results.Human-AI CollaborationFuture of WorkAI Strategy
スライド 2 枚0:36EN
Matthew Berman· 2026年10月25日Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.評価(Evals)コーディングエージェントOpen-weight models
スライド 2 枚0:21EN
Matthew Berman· 2026年10月24日An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.Benchmarks評価(Evals)Generative media
スライド 6 枚25:50EN
Matthew Berman· 2026年10月24日Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.Open-weight modelsBenchmarksAI cost & performance+1
スライド 2 枚32:20EN
Matthew Berman· 2026年10月23日Who Is Local AI For? The Costs, Trade-offs and a Hybrid FutureMatthew Berman · Forward FutureMatthew Berman weighs data control and independence against hardware cost, setup complexity and inference speed.Local inferenceOpen-weight modelsAI cost & performance+1