30 秒でわかる
Matthew Berman shows a research outline produced by his personal assistant after connecting it to Asana and Grok, then describes possible email alerts and a customizable personality file. The project was then called Clawdbot and was subsequently renamed Moltbot and OpenClaw. The title's round-the-clock framing is an aspiration, not an uptime guarantee: proactive operation needs a running host, configured schedules, authorized integrations and available services. The demonstration does not establish that every post or email is accessible or that its summaries are always accurate. No sponsor is identified.
- 1Research assistantBerman says his assistant helped prepare the video after he connected Asana and Grok.
- 2Proactive emailHe describes a potential workflow that notices urgent messages, summarizes them and drafts replies, subject to appropriate access and configuration.
- 3Configurable behaviorHe shows SOUL.md as a way to customize the assistant's tone and priorities.
ポイント
- Berman says his connected assistant gathered posts and helped prepare a video outline in Asana.
- A proactive email workflow requires access to the relevant account and configured triggers, and generated summaries and drafts need review.
- A SOUL.md file supplies editable behavioral instructions; it is not evidence of a sentient personality.
- Clawdbot later became Moltbot and then OpenClaw; the names refer to the same project's history.
- Continuous availability depends on the host, connectivity, credentials, scheduling and service reliability.
チャプターごとに整えた全文を読む
A personal agent at work
Berman shows a research outline and describes connections used to gather posts. The example depends on the permissions and services configured.
This is Clawdbot, the personal assistant project later renamed Moltbot and then OpenClaw. I compare it favorably with Siri and say it helped research and prepare this video. I connected it to Asana and Grok, and it put together an outline that includes specific X posts and view counts. The short shows the resulting outline, not independent verification of every item or access to all current information.
Alerts and personality
He suggests an email-alert workflow and displays the assistant's editable SOUL.md instructions. These are capabilities to configure, not guarantees of uninterrupted or correct operation.
I describe a proactive workflow: check my email, notify me about an urgent message, summarize it and draft a reply. That requires an authorized email connection, suitable triggers and a running service; the short does not show this workflow working continuously. Availability depends on the host, connectivity and connected services, and generated classifications and drafts can be wrong.
The assistant's behavior can be guided by an editable `SOUL.md` file. The example asks it to be helpful, express opinions, try to solve problems before asking and earn trust through competence, while observing boundaries. I say you can change those instructions to fit a preferred style; they guide behavior but do not establish consciousness or guarantee compliance.
You can tell the assistant what personality you have in mind and adjust the file accordingly. At the time I see many people discussing the project on X. That enthusiasm and the video's 24/7 title do not themselves establish uninterrupted operation or reliable access to private information.
同じチャンネルの記事
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.
0:26ENMatthew 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.
0:36ENMatthew 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.
0:21ENMatthew 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.
25:50ENMatthew 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.
32:20ENMatthew 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.