My agent use cases, part 2

In part 1 I wrote about copyediting, onboarding, expense reports, and Jira management with agents. Here's part 2, covering five more ways I use them in my day-to-day work as a CTO.

Weekly review as a chief of staff

Every Monday morning, I ask Claude to look through my daily notes, calendar, emails, Slack, and meeting transcripts from the past week, and give me an update on what I did. It pulls together threads I'd forgotten about, surfaces follow-ups I missed, and reminds me what's still open.

From there, I review my open projects and priorities, and ask it to help me think through where to focus this week.

I also use a variation at the end of the day: "Out of what I worked on today, what should I be communicating to others?" It's a good forcing function for visibility.

The pattern here is using the agent as a chief of staff who has read access to all your systems. It doesn't make decisions for you, but it gathers the context you need to make good ones faster.

Meeting preparation

Before a day of meetings, I ask Claude to look through my calendar and consider how I might want to prepare for each conversation. For a customer meeting, it'll pull recent activity from our CRM and call recordings. For a 1:1 with a direct report, it'll check our shared notes and recent Slack context.

The most useful part is when it surfaces things I wouldn't have looked up myself: an attendee I haven't met before, a thread from two weeks ago that's relevant to today's topic, or a decision from last quarter that I'd forgotten about.

This takes about two minutes and often saves me from walking into a meeting cold.

Writing role descriptions interactively

I was recently writing a role description for a new hire. Instead of staring at a blank document, I had the agent interview me: what does this person own? What does the CTO keep vs. delegate? What does success look like at 6 months? What's the operating cadence?

It asked me maybe 20 questions over the course of an hour, read our Confluence docs for context, and drafted sections as we went. The result was much more specific than what I'd have produced on my own, because the Q&A format forced me to articulate things I'd been keeping in my head.

I use the same approach for documents where I've done lots of thinking but haven't organized my thoughts yet. Instead of producing content, the agent asks you questions that draw it out of you.

Building skills for your agents

This is the meta one. I use agents to build their own capabilities.

For example, I analyzed my sent emails to identify my communication patterns, then turned those patterns into a skill that helps the agent communicate on my behalf. I built a skill that connects to our call recording platform, so agents can search customer conversations. I'm working on one for Salesforce, so account executives can keep CRM data updated just by chatting.

The interesting thing is how fast the feedback loop is. I notice a gap ("I wish Claude could check Gong transcripts"), build the skill in an afternoon (often with Claude's help), and immediately start using it. A few iterations later it might be enough to share with the team.

Market intelligence

We need to understand which of our prospective customers use certain procurement platforms. Customer lists aren't public, so you can't just look this up. But answers can be pieced together from public sources, supplier documentation, and other breadcrumbs.

I had Claude systematically research about 50 companies, checking several data sources for each one and compiling the results into a table. What would have been a week of manual research by an analyst took 20 minutes of Claude chugging in the background.

The output wasn't perfect, but it gave us a strong starting point and the method is repeatable.