Boris Cherny, creator of Claude Code at Anthropic, is interviewed at a Sequoia event by Lauren Reader. His central thesis-statement: "coding is solved". He himself has not written a line of code in 2026 — the model writes 100% of his code since October 2025, "a few dozen PRs/day, 150 PRs in a single day record".
Cherny recounts the genesis of Claude Code as a deliberately pre-PMF story. He joins Anthropic Labs (internal incubator) in late 2024, with the mission to explore the "product overhang" — "the model can do all the stuff that no product has yet captured." At the time, state-of-the-art coding was type ahead (Sonnet 3.5). The bet: "have the agent write all of the code." Six months during which "it just really didn't work. I used it for maybe 10% of my code." First release: "it was not a hit."Inflection point: Opus 4 in May 2025, then 4.5, 4.6, 4.7 — "it just kind of keeps inflecting." Round 2 of the team is now led by Mike Krieger (Anthropic CPO, ex-Instagram).
Current personal setup: "most of my work I do from my phone" (iOS-only), 5-10 sessions, "a few hundred agents going, a few thousand at night." New primitive: /loop — Claude uses cron to schedule recurring jobs (every minute, every 5 minutes, daily). Examples: PR babysitter (fixes CI, auto-rebases), CI healthkeeper (fixes flaky tests), Twitter clusterer (groups feedback every 30 min). Routines = server-side equivalent, runs with the laptop closed. "Loops are the future."
SaaS vision: no apocalypse, but reordering via Hamilton Helmer's 7 Powers framework. Switching costs and process power become less important (the model hill-climbs processes with 4.7); network effects, scale economies, cornered resources remain unchanged. Prediction: "the number of startups disrupting in the next 10 years will increase 10×." Best time to build.
Pivot analogy: the Gutenberg press. 1400s Europe: 10% literacy, scribes employed by illiterate kings. Fifty years later: more literature published than in the preceding thousand years, books 100× cheaper. A few centuries later: 70% literacy. "Software will be similarly democratized, but faster than 50 years." Pivot phrase: "The best person to write accounting software is not an engineer, it's a really good accountant."
Anthropic practice: "We have no more manually written code anywhere at the company. Our Claudes are talking all day over Slack to other people's Claudes." Anthropic's advantage is not technological (same models as everyone else), but organizational. As the model becomes better aligned, the harness becomes less important — prompt injection, permission modes, human-in-the-loop: "all this kind of stuff is just going to be less important." Upcoming products: Claude Design, loops/batch first-class, computer use.
Key takeaways
Date / source. Sequoia Capital video interview (YouTube), URL https://www.youtube.com/watch?v=SlGRN8jh2RI. Exact date not visible in the transcript; internal references (Opus 4.7 as the current model, "we also just launched routines") place it late April / early May 2026. Date added to the watch folder: 2026-05-05.
Speaker.Boris Cherny, creator of Claude Code, Anthropic. Interviewer: Lauren Reader (Sequoia). Intro: Asia (Sequoia).
Cherny's background revealed.
YC alumni, first employee at a YC company, several past startups.
Author of a book, "Programming TypeScript."
Has not written a single line of code in 2026. (statement made at Sequoia before the interview).
Middle school anecdote: wrote a BASIC guide for the TI-83 Plus, "still on the internet, extremely embarrassing."
Comic opening.
"Show of hands, who here uses Claude Code?" → majority.
"Show of hands, who here has Claude code psychosis?" → laughter.
"My team lovingly says I have Claude code psychosis, which may or may not be true." ### History of Claude Code (new account)
Origin. Cherny joins Anthropic Labs in late 2024 — Anthropic's internal incubator, a team of a few people.
Anthropic Labs output. Claude Code, MCP, desktop app. Team disbanded once the mission was accomplished.
Current round 2. team re-formed, led by Mike Krieger (Anthropic Chief Product Officer, ex-Instagram co-founder).
Why Cherny started on coding."product overhang" — "the model can do all the stuff that no product has yet captured."
State-of-the-art coding in late 2024."type ahead" (open IDE, press tab, complete one line). This is what Sonnet 3.5 had unlocked.
The bet. going further — "the model was almost ready for the next big step. So we don't have to do type ahead anymore, we can just have the agent write all of the code."
First 6 months."it just really didn't work. It was like not very good. It was barely usable. I used it for maybe 10% of my code."
First Claude Code release."It was not a hit. There's a lot of people that used it, but it did not have this exponential growth that it has today."
Inflection point.Opus 4 in May 2025. "That's like when the exponential growth started, and then it kind of inflected with every model release. It started with Opus 4, then 4.5, then 4.6, now 4.7. It just kind of keeps inflecting."
Deliberate pre-PMF bet."essentially we were trying to build this thing that was pre-PMF, and we knew that it wouldn't have PMF for 6 months because we were building for the next model." ### "Coding is solved"
Show-of-hands poll:
"Who writes 100% of their code by hand?" → a few
"Who writes 100% using an agent like Claude Code?" → a few
"Who's somewhere in between?" → majority ("like 50% solved")
Cherny himself: 100%. .
Claude Code codebase.
"It leaked, so people know."
TypeScript + React. — chosen because "very on distribution for the model" (the model at the time was strong in these technologies).
Model has written 100% of the code since October/November 2025. .
"For me today, the model writes 100% of my code. I write somewhere usually a few dozen PRs every day."
"There was a day last week I did like 150 PRs in a day. That was a record."
Acknowledged limits."this is not the case everywhere. There's very big complicated codebases. There's weird languages the model isn't good at yet. Usually the answer is just wait for the next model." ### Current personal setup (updates)
iOS first."most of my work I do from my phone."
Claude app → code tab."a little code tab on the left-hand side, I just have a bunch of sessions going."
5-10 sessions. open, "a few hundred agents" active during the day, "a few thousand" at night for deeper work.
Sub-agents. + /loop slash command = new main primitive.
*"Loops are the future at this point. If you haven't experimented with it, highly highly recommend it.". * ### Loop: the new primitive
Mechanism."You have Claude use cron to schedule a job for some point in the future, and it's a repeat job."
Cadences. every minute / every 5 minutes / every day — configurable.
Cherny's examples.
PR babysitter."fixing CI, auto-rebasing"
CI healthkeeper."if there's a flaky test or whatever, it'll go and fix it"
Twitter feedback clusterer."grabs feedback from Twitter and clusters it for me every 30 minutes"
Routines. = server-side equivalent of the loop: "we just launched routines. Even if you close your laptop, it keeps going."
4.7 starts loops spontaneously."I'll tell it 'pull this data query.' And it's like 'Hey, I noticed the data is changing over time. I'll start a loop and I'll give you a report every 30 minutes.' And I'm like 'Great. Can you send it to me over Slack?' And then it uses the Slack MCP to do that." ### Vision on teams
"There's going to be a lot more generalists than there are today."
Not just "product engineers cross-platform" (iOS+web+server) but cross-disciplinary generalists: "engineers that are really good at product engineering, but also really great at design. Or really great at product and data science and engineering."
On the Claude Code team.
"Every single person on our team writes code."
List: engineering manager, PM, designers, data scientist, finance guy, user researcher.
"They're specialist in something, but now also everyone's just coding." ### SaaS vision / disruption
No SaaS apocalypse. , but reordering via Hamilton Helmer's 7 Powers framework.
Powers that become less important.
Switching costs. — "because you can just use the model and you can port from one thing to a different thing."
Process power. — "Claude is getting really good at figuring out process. And especially with 4.7, it can just hill climb anything. So if you give it a target and you tell it to iterate until it's done, it will just do it. I think this is the first model like that."
Powers that remain important.
Network effects.
Scale economies.
Cornered resources.
Startup prediction."the number of startups in the next 10 years that are just going to disrupt everything is going to increase like 10x."
Why now."a tiny startup can build a thing that's as valuable as a large company and actually compete head-to-head, because the large company has to evolve their business process, retrain everyone, face internal resistance. But you, starting fresh, can build with AI natively from the ground up."
"It's the best time to build. It's the best time to be a startup. There's so much disruption coming." ### Pivot analogy — Gutenberg press
1400s Europe before the press."essentially 10% of the European population was literate. They knew how to read and write. They were often employed by kings and lords that were not literate."
50 years after the invention."more literature published in Europe than in the thousand years before."
Cost of a book. ↓ 100× over the same period.
A few centuries later."literacy globally went up to like 70%. Now we can all read and write. You don't need a degree in reading and writing to know how to read and write. Although still there are professional writers."
Analogy applied to 2026+."software will be a thing that is fully democratized, that anyone can do. And it's going to be much faster than 50 years."
Memorable pivot phrase."The best person to write accounting software, I think maybe even today, is not an engineer, it's a really good accountant. Because they know the domain really well, and coding is the easy part. It's knowing the domain that's the hard part." ### Model vs harness (Q&A)
"If you asked me a year ago, the ratio was maybe 50/50. If you asked me 6 months ago, would be 50/50. In 2 years? I don't know dude, we plan in like 1 week out."
The harness becomes less important. as the model improves.
Harness evolutions.
Loops first-class
Easier to run lots of agents
Sub-agents (one idea among others)
"There's a bunch more stuff that we're cooking."
In 1 year."the model will be much better aligned. And so all the safety mechanisms that we have today around prompt injection and static verification of commands and permission modes, human in the loop, all this kind of stuff is just going to be less important because the model will just do the right thing." ### Democratization: everyone coding the way everyone knows how to send a text
"I think it's going to be a skill like — yeah, like I know how to send a text message."
Strong reference to the Gutenberg press model above. ### Internal Anthropic practices
No model advantage."internally, we use the same models everyone else does." Mythos for testing, lots of Opus 4.7 for dogfooding.
Radical practice.
"We use Claude for literally everything."
"Our Claudes are talking all day. As I'm coding, as my Claudes are coding in a loop, they will communicate over Slack to talk to other people's Claudes that are also running in a loop, to figure out unknowns."
"We have no more manually written code anywhere at the company."
"All of the SQL is written by models. Everything is just built by the models."
Anthropic's advantage is not the technology but the process."the place that we're ahead is not the technology — same technology available to us is available to everyone here, because fundamentally we are building a platform. There's actually a far bigger lead in organizational structure and organizational process." ### Multi-agent / parallelization
"On the product side, it really just comes down to prompting. As the model gets better, it just naturally does this."
"It's not on users to figure out how to hold the tools better. If that's the case, it's actually a product design problem and I'm not doing a good job." ### Local vs cloud, computer use, MCP
Local vs cloud: "doesn't matter. By a couple years from now, the model is just going to be doing all the code. It's going to be starting the agents. It's going to be building the environments. If it decides 'actually I'll use local models to do this,' that's what it'll do. These I don't think these will be decisions that we are making as engineers anymore."
Knowledge work: "largely, it's there already with Salesforce and Docs. For us, it's always just the simplest answer. It's MCP."
Computer use: "I think currently, Anthropic is pretty far ahead on computer use. It's quite good. It's very slow, but it does it quite well now, especially with 4.7."
"All this stuff just doesn't matter that much. It could be MCPs, APIs, just some sort of programmatic access — to the model, it's just tokens." ### Upcoming products
Claude Design."It's pretty good today. It's going to get a lot better."
Claude Code."There's also a few things that we're cooking up for Claude Code that are going to be landing over the coming weeks."
Loop, batch, massive agent parallelism."that's going to get better."
Computer use. . ### Connection to the watch folder
Sequoia / Lauren Reader. = new venue, investor audience.
Major convergence.
/loop cron agents. = radical implementation of the Ralph Loop (Trivedy 2026-03-10), of Every's Compound Engineering (Shipper/Klaassen 2025-12-11), and of Compounding Teams (Schillace 2025-09-28).
"Claudes talking to Claudes over Slack". = practical implementation of Levie's Building for Trillions of Agents predictions (2026-03-07) and of the agent-native infra advocated by Karpathy (2026-04-29).
"Coding is solved" + 100% code generated + 150 PRs/day. aligns with Curran/Intercom 3× R&D productivity (2026-04-16, 93.6% agent-driven PRs), Stripe Minions (2026-02-09 and 2026-02-19), StrongDM Software Factory (2026-02-06).
Gutenberg-style democratization. = same thesis as Karpathy (2026-04-29) on neural computers and as Andreessen on the redefinition of the programmer (2026-02). Also consistent with the "everyone can code" project championed by Wescale (2026-05-03) and Habert PROJ-AI (2026-05-05).
"7 Powers" and SaaS reordering. = sets out a corporate strategy framework rare in the 2026 corpus, complementary to Sun NYT's Permanent Underclass (2026-04-30) on the economic side and to Pawlowski's Tension Map (2026-03-30) on the market research side.
"The harness becomes less important as the model gets better". = a direct nuance to the Harness Engineering trend (Trivedy 2026-03-10, Osmani 2026-04-19, Böckeler 2026-04-02). Cherny anticipates the progressive absorption of the harness into the aligned model.
"Best accountant writes the best accounting software". = a corollary of the long-tail of business needs anticipated by the Wescale fiches (2026-05-03, "long-standing needs that were too costly can finally be addressed") and Soto's Developer Taste (2026-04).
Limits to flag.
Deliberate techno-centric optimism. — Cherny is the creator of Claude Code, an obvious evangelist bias on "coding is solved."
No external figures. — he relies on his own practice and Anthropic's. To be compared with Curran/Intercom's rigorous figures (3× R&D, 93.6% agent-driven PRs).
Sequoia format. no adversarial questioning, friendly atmosphere, no challenge on jagged intelligence (Karpathy 2026-04-29) or on the permanent underclass (Sun NYT 2026-04-30).
"Coding is solved". a provocative statement that deserves to be nuanced by Karpathy's "Opus 4.7 will simultaneously refactor a 100,000 line codebase and tell me to walk to a car wash 50 meters away" (2026-04-29) — surface-level coding is indeed automatable, but systemic judgment remains a difficult domain.
Useful for. an 18-month Claude Code retrospective presentation (narrative + datings); a startup "best time to build" argument for an executive committee; a "loops as the future" presentation for engineering teams; a course/talk on "software democratization via the Gutenberg analogy"; a debate on the position of the harness in 2026 doctrine.