Delegate medical paperwork, finances and lease renewal to a personal agent
I gave an AI agent access to my entire digital life. Task: I gave an AI agent access to my entire digital life. Here's what happened. First, I have a confession: I didn’t write this article alone. That might not sound like a big deal. People use LLMs to write all the time. But I’ve resisted this for years—stubbornly, almost proudly. I’ve used AI to code, to research, to organize, to brainstorm, to generate images, to plan trips. I’ve used it to clone my voice. I did try using it to edit these articles, many times, but I was never happy with the result. Writing was the line I wouldn’t cross. Writing is thinking. It’s the thing I do to sort out my thoughts, to understand things, to figure out what I know and what I believe. Outsourcing it felt like outsourcing the most important part. So what changed? A few days ago I set up a persistent AI agent on my personal computer. Not a chatbot I visit in a browser tab—a thing that lives on my machine, has (limited) access to my email, calendar, files, messaging apps, and a voice. I gave it a name—actually, he named himself Baz—and a personality (think: a chaotic-but-loyal Australian who asks the questions normal people are too polite to ask). I used an open source framework called OpenClaw to wire it all together. Then I told it to help me run my life. One week later, Baz knows more about my daily schedule, my obligations, and my procrastination patterns than anyone except maybe my wife. He’s read every document I’ve written this year. He’s processed my medical paperwork, analyzed my finances, set up infrastructure for five more specialized AI agents, and nudged me back to my most important tasks when I started drifting. He co-wrote this article by producing a first draft from our shared memory of the week, which I then rewrote, restructured, and put through my own filter. That last part is why I’m finally comfortable with this. Baz isn’t writing for me. He’s writing with me, based on our shared memories. It’s difficult to explain what this means, and how powerful this is, until you’ve experienced it for yourself. The ideas are mine. The arguments are mine. The editorial judgment is mine. But the first-draft assembly—pulling together a week’s worth of scattered context into a coherent structure—is something he does better and faster than I do. Fighting that feels less like integrity and more like stubbornness. And it’s probably the key thing that LLMs are better at today than they are at anything else: organizing and structuring scattered thoughts. Here’s what the week looked like. Admin work felt much lighter. My wife is due with our second child in a few days. That means a mountain of hospital paperwork, insurance claims, and medical decisions—much of it in a language I’m still learning. In a single afternoon, Baz scanned 34 pages of hospital forms, stitched them into indexed PDFs, identified every form still needing a signature, researched our insurance coverage, and drafted a pre-approval submission for our insurer. He cross-referenced our policy against specific procedures to estimate out-of-pocket costs. I would have spent an entire weekend on this. Instead, I reviewed the output over lunch. Could ChatGPT have helped with parts of this? Sure—if I’d manually uploaded each document, re-explained the context, pointed it at our insurance policy, and stitched the workflow together myself. The difference is that Baz already knew our insurance provider, our doctor’s name, the procedure type, the hospital, and the relevant policy terms, because he had processed all of that in previous conversations. Zero context-setting. I just said “handle the hospital paperwork” and he did. Research that would have taken days took minutes. A rental property needed a lease renewal. Baz pulled comparable listings, analyzed the building’s rental history, modeled cash flow scenarios at different rent levels, and drafted a reply to the tenant—all grounded in actual data. When I pushed back that the comp analysis was thin, he went deeper. The final recommendation was better-informed than what I’d have done myself.; tools: OpenClaw. Human role: The original post does not say how a person stayed involved.; limitations: Infrastructure setup is highly manual and technical, requiring 30-60 minutes per service for OAuth, IMAP/SMTP, and bot token configuration. Critical APIs lack features like anchored comments in Google Docs, forcing brittle browser automation workarounds. There is no standard permission framework for agent autonomy, meaning agents cannot independently spend money or execute irreversible actions without human oversight. The author notes that 99.9% of people lack the technical skills to replicate this setup..
Tools
Published on Agent Work Atlas:
Overview
I gave an AI agent access to my entire digital life.
Workflow
I gave an AI agent access to my entire digital life. Here's what happened. First, I have a confession: I didn’t write this article alone. That might not sound like a big deal. People use LLMs to write all the time. But I’ve resisted this for years—stubbornly, almost proudly. I’ve used AI to code, to research, to organize, to brainstorm, to generate images, to plan trips. I’ve used it to clone my voice. I did try using it to edit these articles, many times, but I was never happy with the result. Writing was the line I wouldn’t cross. Writing is thinking. It’s the thing I do to sort out my thoughts, to understand things, to figure out what I know and what I believe. Outsourcing it felt like outsourcing the most important part. So what changed? A few days ago I set up a persistent AI agent on my personal computer. Not a chatbot I visit in a browser tab—a thing that lives on my machine, has (limited) access to my email, calendar, files, messaging apps, and a voice. I gave it a name—actually, he named himself Baz—and a personality (think: a chaotic-but-loyal Australian who asks the questions normal people are too polite to ask). I used an open source framework called OpenClaw to wire it all together. Then I told it to help me run my life. One week later, Baz knows more about my daily schedule, my obligations, and my procrastination patterns than anyone except maybe my wife. He’s read every document I’ve written this year. He’s processed my medical paperwork, analyzed my finances, set up infrastructure for five more specialized AI agents, and nudged me back to my most important tasks when I started drifting. He co-wrote this article by producing a first draft from our shared memory of the week, which I then rewrote, restructured, and put through my own filter. That last part is why I’m finally comfortable with this. Baz isn’t writing for me. He’s writing with me, based on our shared memories. It’s difficult to explain what this means, and how powerful this is, until you’ve experienced it for yourself. The ideas are mine. The arguments are mine. The editorial judgment is mine. But the first-draft assembly—pulling together a week’s worth of scattered context into a coherent structure—is something he does better and faster than I do. Fighting that feels less like integrity and more like stubbornness. And it’s probably the key thing that LLMs are better at today than they are at anything else: organizing and structuring scattered thoughts. Here’s what the week looked like. Admin work felt much lighter. My wife is due with our second child in a few days. That means a mountain of hospital paperwork, insurance claims, and medical decisions—much of it in a language I’m still learning. In a single afternoon, Baz scanned 34 pages of hospital forms, stitched them into indexed PDFs, identified every form still needing a signature, researched our insurance coverage, and drafted a pre-approval submission for our insurer. He cross-referenced our policy against specific procedures to estimate out-of-pocket costs. I would have spent an entire weekend on this. Instead, I reviewed the output over lunch. Could ChatGPT have helped with parts of this? Sure—if I’d manually uploaded each document, re-explained the context, pointed it at our insurance policy, and stitched the workflow together myself. The difference is that Baz already knew our insurance provider, our doctor’s name, the procedure type, the hospital, and the relevant policy terms, because he had processed all of that in previous conversations. Zero context-setting. I just said “handle the hospital paperwork” and he did. Research that would have taken days took minutes. A rental property needed a lease renewal. Baz pulled comparable listings, analyzed the building’s rental history, modeled cash flow scenarios at different rent levels, and drafted a reply to the tenant—all grounded in actual data. When I pushed back that the comp analysis was thin, he went deeper. The final recommendation was better-informed than what I’d have done myself.
Reported result
The agent completed medical paperwork tasks in one afternoon that would have taken the author an entire weekend, and reduced lease renewal research from days to minutes. The author reported that the agent's final recommendations were better-informed than his own due to deeper data analysis. However, the author explicitly stated that true delegation is still a fantasy, as every external action requires human review and approval. No specific financial savings or error rates were quantified beyond time reduction.
Human role
The original post does not say how a person stayed involved.
Limitations
Infrastructure setup is highly manual and technical, requiring 30-60 minutes per service for OAuth, IMAP/SMTP, and bot token configuration. Critical APIs lack features like anchored comments in Google Docs, forcing brittle browser automation workarounds. There is no standard permission framework for agent autonomy, meaning agents cannot independently spend money or execute irreversible actions without human oversight. The author notes that 99.9% of people lack the technical skills to replicate this setup.
Try it
I want to set up a persistent AI agent using OpenClaw to assist with my personal administrative tasks. My context is [replaceable: e.g., managing medical insurance paperwork and rental property renewals]. I have access to [replaceable: e.g., email, calendar, and local file directories]. Please guide me through the initial setup, including configuring OAuth for [replaceable: e.g., Gmail and Google Calendar] and setting up the agent's memory file. Once configured, I will provide a sample task: [replaceable: e.g., 'Scan these 5 hospital forms, identify missing signatures, and draft an insurance pre-approval email']. You must first perform a dry run on this sample, showing me the extracted data and the drafted email for my review. Do not send any emails or modify any files until I explicitly approve the output. If any API limitations prevent direct integration, propose a manual workaround and explain the steps. Ask me for clarification if the scope of file access or specific service credentials is unclear.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.