How I AI: Webflow CPO Rachel Wolan's AI Chief of Staff & Org Adoption Playbook
Learn how Webflow CPO Rachel Wolan built a personal AI Chief of Staff to manage her calendar and prep for meetings, and discover her step-by-step framework for driving team-wide AI adoption through company 'Builder Days'.
Claire Vo
In this episode, I was so excited to sit down with someone who truly embodies the spirit of the AI-native executive. While much of the conversation around AI focuses on individual contributors, we're diving into how C-level leaders can and should be getting their hands dirty with these tools. My guest is Rachel Wolan, the Chief Product Officer at Webflow, who is a fantastic example of a leader who isn't just talking about AI, but is actively building with it to enhance her own effectiveness.
Rachel, who started coding at 16, has returned to her builder roots in a big way. She walked me through the custom "AI Chief of Staff" application she built for herself—a personalized, powerful tool that helps her manage the relentless pace of an executive schedule. It's not just a theoretical concept; it's a running app on her local machine that helps her triage her calendar, tame her inbox, and prep for high-stakes dinners, all while giving her brutally honest feedback.
But what's even more impressive is how Rachel translates her personal AI workflows into organizational momentum. She shared her detailed playbook for running company-wide "Builder Days," a strategic initiative that has dramatically increased AI tool adoption across her entire team. In this post, we'll break down both of these incredible workflows: building your own AI assistant and scaling that knowledge across your company. Let's get into it.
Workflow 1: Building a Personal AI Chief of Staff for Daily Triage
One of the biggest challenges for any executive is the sheer volume of information and commitments. I often call myself a "just-in-time executive," prepping for meetings just minutes beforehand. Rachel built her AI Chief of Staff to solve this exact problem, creating a system to manage her calendar and email with proactive, intelligent assistance.
Step 1: Connecting the Dots with APIs
To get started, the Chief of Staff needs access to your data. Rachel connected her application to her work life by using official APIs and authentication tokens.
- Google Calendar & Gmail: She uses the Google Calendar API and Gmail API to give her agent access.
- Secure Storage: All her API tokens and secrets are stored securely in an
.envfile, a standard practice for managing sensitive credentials in a development environment. - Setting Guardrails: This is a crucial step. Rachel intentionally limited the agent's permissions to prevent mistakes. Her calendar access is read-only, and her Gmail access is limited to reading, archiving, labeling, and—most importantly—creating drafts, not sending emails directly. This keeps her in full control.
Step 2: The Morning Calendar Review & Delegation Prompt
Each day, Rachel uses a simple but powerful prompt to get a strategic overview of her schedule and identify opportunities to delegate. She runs this in her terminal using Claude Code.
"Tell me about my day tomorrow. What can I delegate?"
The agent analyzes her calendar and returns a prioritized list of suggestions:
- Make Meetings Async: It identifies meetings that could be handled via a document or Slack update.
- Delegate Tasks: It suggests specific meetings that a director or another team member could cover, even drafting the message to send them. For example:
"Can [Director's Name] cover this and send me a summary?" - Decline Optional Invites: It flags meetings from unknown organizers or with unclear agendas that she can likely skip.
This workflow forces a critical review of her time, helping her reclaim focus and energy for high-impact work.
Step 3: Getting the "Brutal Truth"
One of the most unique features Rachel programmed is the "Brutal Truth" module. She's instructed her agent to be direct and hold her accountable. The results are both hilarious and incredibly insightful.
After analyzing her calendar, the agent delivered this gem:
The Brutal Truth: "You're operating as a senior PM, not a CPO. You're reviewing PRDs, approving scripts, and recording marketing videos... The only thing that will matter in six months is [a specific strategic conversation]."
This kind of unvarnished, data-driven feedback is something even a human chief of staff might hesitate to give. It’s a powerful way to stay focused on the strategic altitude required of a C-level executive.
Step 4: Email Triage
The same principles apply to her email. The agent helps her manage a 500+ deep inbox by:
- Archiving ruthlessly: It gets rid of newsletters and non-essential communications.
- Surfacing what's important: It identifies emails where someone is waiting on her for a document or a decision.
- Drafting responses: It prepares draft replies for recurring requests or partnership inquiries, saving her from typing the same thing over and over.
Workflow 2: On-Demand Prep for Meetings and Networking Events
Beyond daily triage, Rachel's AI Chief of Staff excels at ad-hoc preparation, turning a time-consuming research task into a fast, automated process. Her workflow for prepping for a networking dinner is a masterclass in multimodal AI and context injection.
Step 1: Ingesting a Guest List with Vision
The process started with a simple, low-fi input: a screenshot of the dinner's guest list.
She simply dropped the image file into her app. The underlying model uses vision capabilities to perform Optical Character Recognition (OCR), accurately reading and extracting the names of every attendee from the image.
Step 2: Kicking Off a Multi-Step Research Agent
Once the names were extracted, a dedicated research agent took over. This wasn't a single call to an LLM; it was a chain of actions designed to gather comprehensive information:
- Initial Web Search: The agent performs a general web search for each person to get a broad overview.
- LinkedIn Search: It then specifically searches LinkedIn to find their professional profile, current role, and career history.
- Deeper Web Search: Finally, it conducts another, more targeted web search for recent news, articles, or talks they may have given.
This mimics the exact process a human would follow but completes it for a dozen people in just a couple of minutes.
Step 3: Leveraging a Markdown-Powered Knowledge Base
This is where the workflow becomes truly personalized. To ensure the output is relevant to her, Rachel feeds the agent several markdown files containing key information:
- `about_me.md`: Contains her professional bio, communication style (from a workshop she attended), and key career highlights.
- `webflow_products.md`: An auto-generated file, updated monthly from release notes, that details all of Webflow's latest products and features.
By including these files as context, the agent can generate talking points that connect her work and Webflow's offerings directly to the interests of the other attendees. This is a brilliant, low-tech way to maintain a personal knowledge base for an AI agent without needing a complex database.
Step 4: Generating the Final Prep Document
The final output is a comprehensive, well-structured prep document displayed right in her web app. It includes:
- Priority Connections: A list of the most relevant people she should try to speak with.
- Personalized Conversation Starters: Tailored opening lines for key individuals based on their background and her own.
- Hot Discussion Topics: Relevant industry trends, like Answer Engine Optimization (AEO), to bring up.
- Venue Information: Details about the restaurant for easy reference.
This entire workflow transforms her from being a "just-in-time executive" to a deeply prepared and confident networker.
Workflow 3: The Playbook for Driving Org-Wide AI Adoption
After mastering AI for her own productivity, Rachel faced the leadership challenge: how do you get an entire organization to adopt these new tools and mindsets? Her answer was the "Builder Day," a focused, company-wide event designed to spark creativity and build AI fluency.
Step 1: Setting the Stage for Success
The goal of Builder Day was to get people over the initial friction hump and show them what's possible. To do this, they provided a structured environment with clear goals and robust support.
- Tool Access: The company provided access to a curated set of AI-powered tools, including Cursor for coding, Figma for design, Make for automation, and of course, Webflow.
- Dedicated Tracks: They created different assignments and tracks for various functions (Product, Design, Data Science, User Research) so everyone could work on something relevant to their role.
- Support Channels: A dedicated Slack channel was staffed with engineers to help troubleshoot technical issues, ensuring no one got stuck.
Step 2: Making it Fun and Engaging
A key part of the day's success was its structure, which was designed to be motivating and rewarding.
- Warm-up Assignment: Participants started with a simple exercise to get comfortable with the tools before diving into their main project.
- Judging Panel: To add a little friendly competition, a judging panel including Rachel and the CEO reviewed the projects.
- Prizes & Recognition: Winners were awarded prizes and recognized in different categories, celebrating the effort and creativity across the company.
Step 3: Measuring the Impact
To prove the event's value, Rachel's team tracked tool adoption before and after. Using a dashboard built in Hex, they could visualize the impact clearly.
The results were astounding. After the first Builder Day, usage of Cursor among the design team went from near-zero to about 50% adoption, and that usage was sustained in the following weeks. They successfully moved a significant portion of the team from the "laggard" to the "early majority" phase of the adoption curve.
The qualitative feedback was just as powerful. A post-event survey revealed that participants found the day to be "fun, empowering, motivating, and eye-opening." It proved that a structured, hands-on event is one of the most effective ways to get an organization truly excited about using AI.
Final Thoughts
Rachel's work is a powerful blueprint for the modern AI-native executive. It starts with a personal commitment to getting hands-on and building tools that solve your own problems. That hands-on experience not only makes you more effective but also gives you the authenticity and credibility to lead your organization through this technological shift.
Her AI Chief of Staff shows the power of personalized software, while her Builder Day playbook provides a repeatable framework for driving cultural change. It’s a one-two punch: improve yourself, then empower your team. The message is clear: the best way to lead in the age of AI is to build.
So, my challenge to all the leaders listening is this: what's the first personal app you're going to build this weekend?
