Productivity · Newsletter · 🇺🇸 United States · via agentusecases.ai
Non-coding CEO uses Claude Code for email and budgeting
Michael Crist asked for only the emails from real people waiting for a reply and built the family budget from statements.
- Profession
- Executive
- Tools
- Claude Code
- Country
- 🇺🇸 United States
- Found via
- agentusecases.ai (Alex Finn) ↗
- Report date
- no date
- Verified on
- October 25, 2026
What they did
He ran Claude Code in a project folder and connected Gmail. He asked for only the emails from real people who were waiting for a reply. For the budget, he loaded bank transactions and card statements, and the agent categorized them and built the summary.
How it went
The post describes both workflows working for a non-programmer.
Good to know
The "real people waiting for a reply" filter is great for anyone drowning in email.
The prompt
From my emails over the last [days], list only those sent by people (not newsletters or automated messages) who are waiting for a reply from me, with a one-line summary of context and the urgency.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Case found via agentusecases.ai (Alex Finn); text and prompt rewritten by us. Found a mistake?
Similar cases
01Executive builds an "anti-system" task system
Hilary Gridley captures tasks with a tap on her iPhone and lets Claude organize them and learn her preferences.
02Claude doubled the speed of a home Wi-Fi network
A user asked for help with slow internet; the agent ran tests, read the Mac's signal data and walked them through the router settings.
03Product manager turns scattered notes into a priority list
Ron Forbes dumps meeting notes into a folder and Claude Code returns summaries and tasks sorted by priority.
04The agent called the restaurant when the online booking failed
Nick Larkins asked for a dinner reservation; with the site fully booked, OpenClaw built a calling app and phoned.
05When your AI limit runs out in the middle of the day
A dev running four subagents across four repositories ran out of tokens and reflected on their dependence on AI.
06Estimating how long your AI plan will last before it runs out
A dev published an open calculation to estimate how many tokens fit into the Pro/Max plans.
07A table at a hard-to-book restaurant without refreshing the website
The user asked the concierge to watch for an opening at Don Angie; the agent booked it as soon as one appeared.
08Daily newsletters become a podcast at 5 a.m.
The agent reads the newsletters under a label, skips the weak ones, summarizes the rest and generates audio with a local voice.