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 18, 20251h 16mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 3:16

    Why AI agents can be 100× cheaper and better than humans (and why adoption is still low)

    Aakash introduces Lindy and CEO Flo Crivello, framing AI agents as a near-term way to replace certain team roles. Flo argues this is a natural continuation of automation, yet most working PMs still haven’t built an agent—creating an opportunity for early adopters.

    • AI agents as replacements for specific roles, not just assistants
    • Flo’s claim: 100× effectiveness/cost for certain tasks
    • Tech bubble vs real-world adoption gap (only ~8% in PM community)
    • Positioning 2025 as a major monetization window for agent builders
  2. 3:16 – 6:57

    Agent #1: Meeting recording as a ‘second brain’ with automated follow-ups

    Flo demos his meeting-recording agent that stores searchable meeting history and answers questions later (e.g., commitments made in a call). The differentiator versus note-taking apps is deep customization—like auto-posting summaries to the right Slack project channel.

    • Meeting recorder as durable memory: query any past meeting
    • Auto-generating and distributing action items/summaries
    • Conditional routing: detect project meetings and post to matching Slack channels
    • Customization is the key advantage over simple note-takers
  3. 6:57 – 8:54

    Reliability & brand safety: hallucinations, human-in-the-loop approvals, and learning from edits

    Aakash presses on LLM unreliability and misrouting risk. Flo argues models have improved rapidly and can be governed using human-in-the-loop confirmation steps that let users approve sensitive actions and (eventually) teach the agent from corrections.

    • LLM ‘hallucination’ reputation is partly legacy from early GPT-3.5 era
    • Agents are non-deterministic but comparable to humans in error rate for many tasks
    • One-click human approval before executing actions (e.g., Slack posting)
    • Future: agents learn from user edits to reduce repeat mistakes
  4. 8:54 – 10:32

    Choosing the right model: speed vs intelligence vs cost (plus token ‘burn’ for high-stakes tasks)

    Flo explains model selection heuristics: default is fine most of the time, but use fast models for low-latency needs and smartest models for complex reasoning. He shares an example of an agent that researches and places bets, intentionally spending more tokens to improve decision quality.

    • Most users should stick with the platform default model
    • Fast models for phone/real-time scenarios; smarter models for deep reasoning
    • High-stakes tasks justify higher token spend
    • Two main axes: latency and ‘IQ’ (capability)
  5. 10:32 – 13:26

    Agent builder walkthrough: creating an email triage agent in plain English (and ‘agents building agents’)

    Flo builds an email labeling agent from scratch using natural language prompts. The platform turns the prompt into a trigger + analysis step + action, illustrating how agent-builder tooling reduces the need for manual flow construction.

    • Start-from-scratch agent creation via plain-English instructions
    • Email triage labels (urgent/FYI/archive/investor) as a simple starter
    • Flow editor enables personalization/context engineering
    • ‘Agent prompting an agent’: builder generates the underlying logic
  6. 13:26 – 17:25

    Agent #2–#3: CRM manager agent + 6,000 integrations (and using docs as living instructions)

    Flo describes a CRM agent that remembers contacts, proactively surfaces who to meet when traveling, and prompts weekly cleanup by cross-checking calendar vs CRM. He also explains how instructions can live in a Google Doc for continuous updates and highlights Lindy’s broad integration coverage.

    • CRM agent: add/retrieve contacts, proactive relationship reminders
    • Weekly reconciliation: detect people met who aren’t in CRM and prompt additions
    • Use a Google Doc as the updatable policy/instructions source
    • Integration breadth (6,000+) reduces setup friction
  7. 17:25 – 20:42

    Computer Use: bypassing missing APIs (Twitter spam blocking) and surprising cost dynamics

    Flo introduces ‘computer use’—agents operating a cloud browser/desktop to do anything a human can, even without APIs. He demos a Twitter-mentions spam blocker and explains why computer-use tasks can be cheaper due to constrained context (e.g., only recent screenshots).

    • Computer use enables automation where APIs don’t exist (Twitter/LinkedIn patterns)
    • Example: wake every 3 hours, scan mentions, block spam accounts
    • Cost mechanics: fewer tokens via screenshot-based context vs full API context
    • Practical takeaway: ‘no integration’ stops being a bottleneck
  8. 20:42 – 24:46

    Business agents that replace real headcount: support automation, elastic scaling, and recruiting at scale

    Flo argues support is the most obvious ROI: instant 24/7 responses and elastic scaling (e.g., Black Friday spikes) like ‘AWS for labor.’ He then demos recruiting: sourcing candidates and running parallelized outreach workflows using Agent Swarm to avoid bulk-task degradation.

    • Support agents: 30-second responses, 24/7/365, elastic to demand spikes
    • ‘AWS for labor’ analogy: pay only for usage, scale instantly
    • Recruiting agent: find candidates (e.g., engineers from Zapier) with real links
    • Agent Swarm: parallel outreach to prevent slowdown/errors in long bulk runs
  9. 24:46 – 26:54

    Operational guardrails & evaluation: avoiding Gmail bans, activity logging, and weekly digests

    Aakash asks how to prevent failures and improve over time. Flo shares practical safeguards like tracking outreach campaigns in spreadsheets to avoid Gmail lockouts, and using logs/digests (including a weekly meeting digest email) to monitor performance and iterate.

    • Risk management example: outreach pacing to avoid Gmail deactivation/spam
    • Campaign tracking in spreadsheets and queueing outreach when limits are hit
    • Evaluation via task review, logs, and automated reporting
    • Weekly digest from meeting notes as executive reflection tool
  10. 26:54 – 31:06

    More ‘replacement-grade’ agents: sales prospecting, LinkedIn outreach, and cross-post marketing automation

    Flo outlines sales as a massive agent category—especially now that computer use enables DMs, forms, and scheduling without APIs. He also shares a marketing agent that selects appropriate tweets to cross-post to LinkedIn, with human approval to maintain platform-appropriate tone.

    • Sales outreach via contact forms, LinkedIn DMs, Calendly booking
    • Computer use unlocks channels traditionally blocked by missing APIs
    • Marketing agent filters tweets for LinkedIn-appropriate cross-posting
    • Human review step ensures brand/tone safety before posting
  11. 31:06 – 35:52

    PM-specific agent stack: voice-of-customer digests, virtual users, and a ‘mini-PM’ decision agent

    Asked what he’d build as a PM, Flo prioritizes meeting capture and distribution, plus daily voice-of-customer summaries from support tickets. He introduces a ‘virtual user’ knowledge base and an internal ‘mini-PM’ agent trained on a PM’s principles that answers engineers and escalates uncertain cases to the real PM.

    • Meeting notes routed to stakeholders reduce misalignment and dropped balls
    • Daily VOC digest: top issues/confusions posted to Slack
    • Virtual user agent: searchable internal expert on users/features/competitors
    • Mini-PM agent: codifies decision principles, escalates edge cases, self-improves
  12. 35:52 – 40:14

    Frameworks for when to build agents: repetitive work, dislike-to-do tasks, and safety via permissions

    Aakash and Flo generalize when agents make sense: repetitive/manual work, tasks you could train a VA to do, or anything you don’t enjoy. They cover safety basics—agents can only act within granted permissions—and the mindset shift to ‘orchestrator’ with human approvals for critical steps.

    • Heuristic: never do the same thing twice—automate repeat patterns
    • Automate what you dislike and what scales across the company
    • Permission scoping limits damage; approvals for risky actions
    • Role shift: from doer to orchestrator managing an ‘empire’ of agents
  13. 40:14 – 44:01

    Agent platforms vs chatbots: orchestration, permissions, performance, and cost management

    Flo contrasts ChatGPT/Claude as single-agent tools with Lindy-style platforms for orchestrating many collaborating agents. He defines three management dimensions—performance, permissions, and cost—and previews cost guardrails like alerting when tasks exceed a threshold.

    • Chatbots = single-agent personal tools; platforms = multi-agent work systems
    • Orchestration pillars: performance management, permission management, cost management
    • Cost scales with tokens/context; guardrails can request approval above thresholds
    • Granular controls differentiate agent platforms from general LLM interfaces
  14. 44:01 – 52:59

    Competition & company building: Lindy vs Make/Zapier, lean teams with agents, and the Soham hiring story

    Flo positions Lindy as more AI-native and easier than developer-oriented automation tools, and distinct from workflow-first tools like Zapier. He shares how Lindy runs lean with internal agents (code review, postmortems) and recounts hiring then quickly firing Soham Parekh, extracting hiring-process lessons.

    • Differentiation: AI employees vs workflow automations; ease-of-use emphasis
    • Lean execution: internal agents for code review and postmortem learning loops
    • Hiring cautionary tale: Soham Parekh ‘multi-job’ scam and rapid offboarding
    • Advice: trust your gut, avoid job-hopper patterns, do backchannel references
  15. 52:59 – 1:07:41

    Founding Lindy early, pivot lessons, and why ‘strategy is emergent’

    Flo explains his long-standing AGI interest and how GPT-3.5’s API plus a struggling prior startup led to the pivot. He emphasizes action over planning: start building, let strategy emerge, and pivot faster than feels comfortable to overcome status quo bias.

    • From TeamFlow to Lindy: meeting recorder → CRM updates → generalized agent platform
    • Key unlock: LLMs can ‘do’ via API calls, not just generate text
    • Advice: grand plans are wrong; action produces information
    • Pivot heuristics: follow what pulls you, counter status quo bias, move sooner
  16. 1:07:41 – 1:16:42

    AI agent agencies & enterprise transformation: AI ‘czars’, centers of excellence, and the road to autonomous companies

    Flo validates ‘AI agent agency’ businesses as lucrative, comparing today to past digital transformation waves. He suggests successful adoption often requires a dedicated full-time internal leader, and discusses remaining gaps—model coherence over long horizons and effective use of large context/memory.

    • High demand for AI transformation services; early-adopter arbitrage window
    • Pattern: appoint a full-time internal AI lead (not a halftime role)
    • Roadmap gaps: long-horizon coherence, memory, and effective context utilization
    • Workarounds today: context-clearing steps and extracted summaries; optimism on near-term breakthroughs

Get more out of YouTube videos.

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