Watch modeSubscribed

Lenny's Podcast · 3 min · Feb 19, 2026

Plan mode can make Claude Code tasks more reliable

He recommends the strongest model, plan mode for most tasks, and trying different interfaces. Plan mode adds a single instruction not to code yet; after approving the plan, he lets the model execute.

Boris Cherny

Boris Cherny is creator and head of Claude Code at Anthropic.

  • Lenny Rachitsky, Host · Host, Lenny's Podcast

    Spent seven years at Airbnb; his product newsletter has over 1M subscribers.

About this segment

He recommends the strongest model, plan mode for most tasks, and trying different interfaces. Plan mode adds a single instruction not to code yet; after approving the plan, he lets the model execute.

From “Head of Claude Code: What happens after coding is solved | Boris Cherny”, Feb 19, 2026. Watch the full episode

“we inject one sentence into the model's prompt to say please don't write any code yet”
Boris Chernyat 1:09:54 · Lenny's Podcast1:09:54

Takeaways

  1. He recommends using the most capable model available.
  2. He starts about 80% of tasks in plan mode.
  3. The same agent works across terminal, desktop, mobile, and Slack.

In this episode

Full episode
  1. 23:55Give engineers tokens before optimizing costs4:06
  2. 47:20User workarounds reveal what product to build next4:44
  3. 1:03:15Build AI products around the model's expanding abilities5:28
  4. 8:41The terminal was the only interface that could keep pace4:55
  5. 21:07Claude Code coincided with a 200% rise in PRs per engineer2:59
  6. 32:06AI could make software creation as widespread as literacy4:00
  7. 54:21Agent safety needs real-world testing beyond labs and evals5:24
  8. 1:08:42Plan mode can make Claude Code tasks more reliable2:44

Up next · Lex Fridman PodcastSquatters sniped his accounts in seconds during the rename4:01

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 1:08:48

    What are a couple of pro tips that you could share? I will give a caveat, which is there's no one right way to use quad code. So I can share some tips, but honestly, this is a dev tool. Developers are all different. Developers have different preferences. They have different environments. So there's just so many ways to use these tools. There's no one right way. You sort of have to find your own path.

  2. 1:09:08

    Luckily, you can ask quad code. It's able to make recommendations. It can edit your settings. It kind of knows about itself. So it can help. It can help with that. A few tips that generally I find pretty useful. So number one is just use the most capable model. Currently, that's Opus 4.6. I have maximum effort enabled always. The thing that happens is sometimes people try to use a less expensive model like Sonnet or something like this, but because it's less intelligent, it actually takes more tokens in the end to do the same task.

  3. 1:09:35

    And so it's actually not obvious that it's cheaper if you use a less expensive model. Often it's actually cheaper and less token intensive if you use the most capable model because it can just do the same thing much faster with less correction, less handholding and so on. so that's the first step is just use the best model the second one is use plan mode i start almost all of my tasks in plan mode maybe like 80 percent and plan mode is actually really simple all it is is we inject one sentence into the model's prompt to say please don't write any code yet that's it like there's actually like nothing fancy going on it's just the simplest thing and so for people that are in the terminal it's just shift tab twice and that gets you into plan mode uh for people in the desktop app there's a little button on web there's a little button

  4. 1:10:19

    it's coming pretty soon to mobile also uh and we just launched it for the svak integration too uh so plan mode is the second one and uh essentially the model would just go back and forth with you once the plan looks good then you let the model execute i auto accept edits after that because if the plan looks good it's just going to one shot it it'll get it right the first time almost every time with opus 4.6 and then maybe the third tip is just play around with with different interfaces.

  5. 1:10:45

    I think a lot of people, when they think about Cloud Code, they think about a terminal. And of course we support every terminal. We support like Mac, Windows, like whatever terminal you might use that works perfectly. But we actually support a lot of other form factors too. Like we have like iOS and Android apps. We have a desktop app. There's the Slack integration. There's all sorts of things that we support.

  6. 1:11:04

    So I would just like play around with these. And again, it's like every engineer is different. Everyone that's building is different. Just find the thing that feels right to you and use that. You don't have to use a terminal. it's the same quad agent running everywhere. Amazing. Okay, just a couple more questions to round things out. What's your take on Codex?