Circleback CEO Ali Haghani: Why Your Company Should Be Recording More Meetings

Y Combinator · 2026-08-11 · 15 分鐘
https://www.youtube.com/watch?v=4YWO4sSRrTE影片總結
CircleBack CEO Ali Haghani champions recording every meeting as AI agents reshape software engineering
CircleBack co-founder Ali Haghani argues that companies should record nearly every conversation because AI agents need shared context to work effectively. CircleBack transcribes meetings, creates notes and action items, connects with CRM, Slack and issue trackers, and lets teams query their collective “company brain.” Haghani uses it as an applicant-tracking system, to prepare for interviews, and to follow up on customer feedback. He spends 10–20% of his day with OpenClaw, relies on agents to write and review code, and uses evals to prevent noisy notes—for example, banning the word “discussed.” However, agents may never send emails independently, publish production copy, or architect security-sensitive systems. Haghani believes falling software costs shift the advantage from coding speed to deciding what to build and designing systems that work together.
章節
- 0:00Ali's hardware setup + gadgets: Topre keyboard, Temu vehicle, and AirPods Max
- 2:51Unexpected ways of using Circleback: ATS, YC relationship tracking, and interview preparation
- 5:48Different agents made in Telegram: finance, customers, people ops, and Slack workflows
- 7:42Time spent in terminal vs everything else: Thursday shipping days and AI code review
- 9:36Testing and writing prompts: evals for action items and natural notes
- 10:48Tokenmaxxing?: unlimited AI use, automated ops, and strict agent boundaries
- 12:59Why should companies start recording more meetings?: AI context, sharing controls, and privacy
- 14:04Where is software engineering headed?: imagination, system composition, and startup builders
這是 Tier 1 公開摘要
每章重點、段落總結、心智圖由分享者控制是否公開。想看完整分析?自己提交一支。
同頻道的其他分析
Jeff Dean: The 1% Rule for Building in AIY CombinatorJeff Dean links Google Search, TPUs, Gemini agents, and founder strategy to 1,000x energy gaps and 0%-success niches.
Patrick Collison: Is AI Breaking the Lean Startup Playbook?Y CombinatorPatrick Collison says Stripe took two years to launch, while Stripe data shows AI-era startups nearly doubled year over year.
Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The WorkY CombinatorWaymo’s demo took 18 months, its product 15 years, now reaching 17× human safety across 220 million autonomous miles.
Garry Tan: Own Your IntelligenceY CombinatorGarry Tan argues personal AGI, G Brain, and Markdown skills let one founder achieve 400x leverage while owning their intelligence.
Max Hodak: Average Is Not Good EnoughY CombinatorMax Hodak explains how Science’s Helix infrastructure, hiring system, and retinal implant work turn speed into startup advantage.
相關主題的分析
Rebuilding Git for AI Agents and The Future of Developer Tools | Deep Dives with a16za16z Deep DivesGitButler rethinks Git for AI agents with parallel branches, agent-ready CLIs, and patch-based code review
Pyramid of Work and The Future of Enterprise Automation | The a16z Showa16z Deep DivesHappy Robot scales voice agents from logistics to DHL, using Twin and context-sharing to automate enterprise execution.
How Exa is Building the Perfect Search Engine | Deep Dives with a16za16z Deep DivesExa CEO Will Bryk argues agentic search will surpass Google by 2030, with 10,000-result retrieval and 20x lower costs
Peter Steinberger: "Fun Is Velocity"Y CombinatorOpenClaw grew from a WhatsApp relay into a 4.7-million-download open-source storm—and taught Peter Steinberger that fun drives velocity.
How Microsoft is Adapting to the AI Eraa16z Deep DivesMicrosoft’s Aaron Zollman explains securing OpenClaw agents, AI-driven patching, and the CISO’s shift from blocker to enabler.