We Built an AI Employee in 62 mins (Cursor, ChatGPT, Gibson, Crew AI)

Jun 1, 2025

Harish Mukhami, founder of GibsonAI, shares his journey in creating an AI customer success agent that enhances business efficiency. He discusses how AI can analyze data and generate actionable insights, emphasizing a rapid shift from prototypes to production-ready solutions. The conversation dives into the integration of AI tools like Cursor and CrewAI for managing customer success dashboards and driving engagement. Harish highlights the power of dynamic agents in mitigating churn and augmenting human capabilities to create superhuman teams.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Gibson Powers Scalable Backend

Gibson AI is an AI-powered cloud database that manages design, deployment, and scaling automatically.
It underpins production-ready applications that can handle thousands of users instantly without rebuilding.

ADVICE

Use AI to Plan Dashboards

Start dashboard planning with AI tools like O3 Mini to identify key metrics and data sources.
Organize your dashboard tabs around business goals and data inputs for focused insights.

ADVICE

Rapid Database Schema Deployment

Use Gibson AI to generate your entire database schema from a simple high-level prompt.
Deploy instantly to cloud environments with production and development setups including full CRUD APIs.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

This is another episode from our AI PM series.

This time, we’re building an AI teammate that runs user research, writes product docs, and powers customer success end-to-end with GibsonAI founder, Harish Mukhami.

Brought to you by:

Amplitude: The market leader in product analytics

Linear: Plan and build products like the best

Maven: I’ve launched my own curation of their courses

Timestamps:

Preview – 00:00:00

Building AI Customer Success Agent (Tool Stack) – 00:01:46

Role of GibsonAI in Building Customer Success AI Agent – 00:07:29

Using Data from O3 Mini – 00:09:20

Ad (Amplitude) – 00:10:13

Ad (Linear) – 00:10:45

Directing GibsonAI – 00:11:45

Connecting GibsonAI via MCP – 00:17:38

Role of Cursor – 00:21:10

Python Script Inserting Data – 00:26:56

Understanding Cursor Modes – 00:29:00

Ad (Maven) – 00:30:38

Our Dashboard Is Ready – 00:31:01

AI Agent That Analyzes Data and Recommends Actions – 00:33:44

The Most Important Thing Agent Is Doing – 00:41:46

Aakash’s Reaction to Output – 00:50:51

Role of CrewAI – 00:52:01

Why He Built GibsonAI – 00:56:35

Final Thoughts – 01:00:15

Key Takeaways

1. Production Over Prototypes - Stop building prototypes and start shipping production-ready AI employees. Gibson AI, Cursor, and CrewAI let you go from concept to production in hours. Harish's agent was backed by a scalable database handling 10,000 users day one—no rebuilding required.

2. Amplify, Don't Replace - Your next 10x gain comes from making existing teams superhuman. AI agents analyze dashboards 24/7 and draft personalized outreach, while human CS agents focus on high-touch relationships and strategic decisions.

3. Three-Tier Implementation Strategy - Follow this roadmap: dashboard → human-approved recommendations → autonomous actions. Start with AI insights humans review, then AI recommendations humans approve, finally autonomous execution for low-risk tasks.

4. Human-Loop Insurance - Human-in-the-loop is customer relationship insurance. Harish built approval workflows because random AI emails "will only make the problem worse." AI should amplify human judgment, not bypass it.

5. Proactive Beats Reactive - Proactive churn prevention beats reactive win-back by orders of magnitude. AI agents monitor engagement patterns and usage metrics to address churn risks before customers consider leaving.

6. MCP Integration Magic - MCP makes AI tools actually talk to each other. Harish could query databases, update schemas, and deploy changes directly from Cursor—seamless integration without manual tool switching.

7. Information Processing Automation - Any role that "ingests information and sends out information" is automatable. SDRs, recruiters, executive assistants—if it involves processing data and taking action, AI handles the heavy lifting.

8. Specialized Model Selection - Different models excel at different tasks. Harish used O3 Mini for planning, Claude Sonnet for coding. Match your model choice to the specific job rather than defaulting to popularity.

9. Day-One Infrastructure - Production-grade infrastructure eliminates the prototype-to-production death valley. Starting with scalable database infrastructure means your demo can actually handle real user volumes when stakeholders want to scale.

10. Always Review Code - Read AI-generated code even when moving fast. Despite impressive capabilities, human oversight remains critical: "Make sure it is the code that you want." Speed matters, but understanding what you ship is non-negotiable.

Check it out on Apple, Spotify, or YouTube.

Where to Find Harish

LinkedIn: Harish Mukhami

Company: GibsonAI

Related Podcasts:

Tutorial of Top 5 AI Prototyping Tools

Complete Course: AI Product Management

We Built an AI Agent to Automate PM in 73 mins (ZERO CODING)

We Built an AI Product Manager in 58 mins (Claude, ChatGPT, Loom + Notion AI)

Up Next

I hope you enjoyed the last episode with Jeremy Epling (where we discussed the lessons he learned from working at Microsoft and now CPO, Vanta). Up next, we have episodes with:

Bret @DesignJoy - Running Solo $2M/yr Design Agency

Thomas Occhino - CPO, Vercel

Aman Khan - AI PM @ Arize AI, Spotify, Cruise

Finally, check out my latest deep dive if you haven’t yet: Career-Launching Companies: These are the Companies You Should Work For

If you want to advertise, email productgrowthppp at gmail.

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe