Skip to content
Aakash GuptaAakash Gupta

5 AI Agents Every PM Must Use in 2025 (Act Fast)

If you’ve ever said “I just wish I had an assistant who knew exactly how I think”... Lindy is that assistant. These agents aren’t demos. They’re real, customizable workflows anyone can build. No coding experience required. Flo Crivello (founder of Lindy and ex-Cruise/YC) joined us to show how his personal AI stack runs his entire workday: From triaging emails, summarizing meetings, blocking spam, managing contacts, and even sourcing candidates. We’re not talking theory here. You’ll see what’s possible today (no prompting skills, no code), just real agents doing real work when you give them instructions in plain English Language. Transcript: https://www.news.aakashg.com/p/flo-crivello-podcast Timestamps: Introduction: AI Agents vs Human Workers - 0:00 Are Lindy Agents Really 100x More Effective? - 1:34 Agent 1: Meeting Recording That Never Forgets - 3:28 Agent 2: Email Triage That Works While You Sleep - 10:48 Agent 3: CRM Agent That Manages Your Network - 13:25 Ad: Mobbin (Product Design Library) - 15:20 Ad: Jira Product Discovery - 16:23 Agent 4: Removing Twitter Spam Automatically - 18:04 Agent 5: Recruiting Software Engineers at Scale - 22:04 How to Measure and Improve Your AI Agents - 26:02 Secret: Auto-Posting from Twitter to LinkedIn - 28:03 Ad: AI PM Certification Course - 29:29 Top AI Agents Every Product Manager Needs - 31:06 Framework: When to Build an AI Agent - 35:55 ChatGPT vs Claude vs Lindy: Key Differences - 40:30 How Big Has Lindy Become? (5x Growth in 6 Months) - 44:50 Hiring the Most Famous Engineer (5-Job Scammer) - 48:29 From Product Manager to AI Founder Journey - 53:04 The One Key Insight That Changed Everything - 56:42 Should All PMs Become AI Founders? - 1:00:31 Hardest Moment: The Pivot Valley of Death - 1:04:35 AI Agent Agencies: The New Gold Rush Business - 1:07:38 Future: Will AI Agents Run Companies Autonomously? - 1:11:19 Conclusion: How to Get Started with AI Agents - 1:15:33 Thanks to our sponsors: 1. Mobbin: Discover real-world design inspiration - mobbin.com/aakash 2. Jira Product Discovery: Build the right thing - https://www.atlassian.com/software/jira/product-discovery 3. Product Faculty's #1 AI PM Certification with OpenAI's Product Lead (get $500 off) - https://maven.com/product-faculty/ai-product-management-certification?promoCode=AAKASH25 Takeaways: 1. You don’t need to be a “Founder” to act like one. Early in his career, Flo treated his work at Uber like it was his own company. That ownership mentality made him a better PM than most founders. 2. Write Like Your Career Depends on It. Clarity of thought = clarity of writing. He said the best PMs he’s worked with are excellent writers, not because it looks good, but because it reflects structured thinking. 3. Avoid Resume-Driven Decisions. Instead of chasing shiny brand names or job titles, ask: “Will this environment force me to grow?” For him, going from Uber to starting Lindy wasn’t a linear step up—it was a leap into discomfort. 4. Product Sense Is a Muscle. He builds product by imagining it from the user’s emotional POV. Not “What features should we ship?” but “What would delight the user in this moment?” 5. You Can't Delegate Taste. No matter how senior you are, if you're not involved in the details of product quality, you’ll lose the magic. He reviews designs himself, edits copy, and obsesses over UX—because product taste is not outsourceable. 6. Go where product is sacred. A PM’s growth is tied to the culture. He picked Uber because product rigor was high. At Lindy, he made product obsession part of the DNA. If your company doesn’t value product deeply, leave. 👨‍💻 Where to find Flo: LinkedIn: https://www.linkedin.com/in/florentcrivello/ X: https://x.com/altimor?lang=en Lindy: https://www.lindy.ai 👨‍💻 Where to find Aakash: Twitter: https://www.twitter.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aagupta/ Instagram: https://www.instagram.com/aakashg0/ #ai #aiagents #aiagent 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 180K listeners. Hosted by Aakash Gupta, who spent 16 years in PM, rising to VP of product, this 2x/ week show covers product and growth topics in depth. 🔔 Subscribe and like the video to support our content! And turn on the bell for notifications.

Aakash GuptahostFlo Crivelloguest
Aug 17, 20251h 16mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Five AI agents PMs should deploy now to scale work

  1. Flo Crivello argues many knowledge-work tasks are now 100× cheaper/faster with agents, framing the shift as everyone becoming an “orchestrator” rather than a doer.
  2. The episode demos high-ROI agent patterns—meeting recorder with automated Slack routing, Gmail email triage, CRM/contact manager, support automation, and recruiting/outreach using Agent Swarms.
  3. Lindy’s differentiators are extreme customization (flow editor + natural-language agent builder), broad integrations (~6,000), and “computer use” to automate sites without APIs (e.g., Twitter/LinkedIn).
  4. Risk management is handled via human-in-the-loop approvals, permission scoping, and emerging cost guardrails; model choice is positioned as a speed-vs-intelligence tradeoff.
  5. The conversation expands into founder/operator lessons: how Lindy emerged from customer requests and rapid iteration, how to run AI transformation inside companies, and cautions on hiring (job-hopper story).

IDEAS WORTH REMEMBERING

5 ideas

Start with agents that eliminate “coordination tax” first.

The meeting-recording agent that auto-summarizes and posts to the right Slack channel targets a universal PM pain: alignment and follow-through across many stakeholders.

Use natural-language “agent builder” for fast prototyping, then harden with flow controls.

Flo shows building Gmail triage from a single English prompt; the power comes when you later add conditions, loops, and routing logic in the flow editor.

Treat instructions as living policy docs, not static prompts.

A practical pattern is storing triage rules or review standards in a Google Doc that the agent consults each run, allowing non-builders to update behavior without editing the agent.

Mitigate hallucinations operationally, not philosophically.

Instead of debating LLM reliability, add one-click human confirmations on sensitive steps (e.g., sending messages, executing actions) and iterate as the agent learns from corrections.

Model selection should map to task economics: speed, IQ, and dollar value.

Use fast/cheap models for latency-sensitive tasks (e.g., phone calls via Gemini Flash) and premium reasoning models (e.g., o3 / Gemini Opus) when a task’s outcome is worth spending dollars in tokens.

WORDS WORTH SAVING

5 quotes

I think people should increasingly, with AI agents and with the rise of AI in general, they should increasingly think themselves as orchestrators and not as doers.

Flo Crivello

I just think with AI agents, it's like everybody just got a promotion to manager.

Flo Crivello

It's like AWS for labor, right? It's like you never have to worry about scaling again.

Flo Crivello

Don't do a grand plan. Like, the only thing I know about your grand plan is that it's wrong.

Flo Crivello

People way overthink this shit. Like, all the networking events and the dinners and the conferences and, like, frankly, the investor coffees, like, you can skip all of it. You should skip all of it.

Flo Crivello

Orchestrator mindset vs doer mindsetMeeting recording + project Slack auto-postingEmail triage with labels and external instructions (Google Doc)CRM/contact intelligence and proactive networking promptsComputer use to replace missing APIs (Twitter spam blocker, LinkedIn actions)Recruiting + outbound with Agent Swarms and campaign throttlingGovernance: human-in-loop, permissions, model/cost management, context limits

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome