Amp

Amp is the coding agent and development environment that runs anywhere and everywhere.

[Amp @AmpCode]

Think you get it, but you’re at a 200+ person company where most people don’t?

@thorstenball and @sqs’s advice: “Kill the gossip channel.”

[Amp @AmpCode]

21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.

@sqs and @thorstenball on how the Amp team works:

[Amp @AmpCode]

Issue resolved. Amp should work again now. We're monitoring.

[Amp @AmpCode]

We're experiencing infrastructure issues.

Investigating.

You can see the current status here: https://t.co/5nxhNhg66Z

[Amp @AmpCode]

@tobimori We wish. We'd have Lamborghinis instead of an outage.

[Amp @AmpCode]

Amp is built by a team of 21, with revenue the size of competitors that have 30, 40 or 50 times the staff.

“This is what a lot of other companies in the future will look like.” — @sqs

[Amp @AmpCode]

21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.

@sqs and @thorstenball on how the Amp team works:

[Amp @AmpCode]

“But the code review process is what creates the risk.”

@thorstenball and @sqs on 4,000-line PRs on a Friday, branches nobody remembers, and what continuous integration actually means.

[Amp @AmpCode]

21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.

@sqs and @thorstenball on how the Amp team works:

[Amp @AmpCode]

On graduation day, a Navy aircraft mechanic checks the jet alone. No senior mechanic. Not even the pilot.

@sqs on why skin in the game makes people better, and what that means for code review.

[Amp @AmpCode]

21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.

@sqs and @thorstenball on how the Amp team works:

[Amp @AmpCode]

“You defined those teams based on the capabilities of humans in 2019.”

When agents let every engineer reach 10× further, the old team boundaries start to collide. @thorstenball and @sqs on bigger fish in the same pond.

[Amp @AmpCode]

21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.

@sqs and @thorstenball on how the Amp team works:

[Amp @AmpCode]

You can also watch it on YouTube: https://t.co/tkb0rsfVZX

Or listen to it on Spotify: https://t.co/hC6cKMau4r

If you want to listen to all of them: https://t.co/NxaedG7D6o

[Amp @AmpCode]

21 people, a single meeting a week, no quarterly goals, no pull requests, no mandatory code review, no titles (except one dictator), a hundred releases a day, bugs fixed in minutes, famous for killing features.

@sqs and @thorstenball on how the Amp team works:

[Thorsten Ball @thorstenball]

You can now share your Amp runner's desktop

https://t.co/Nls5bsfBZi

[Quinn Slack @sqs]

You can use your Claude plan in Amp now. Free and open to everyone.

(By very very very very popular request.)

https://t.co/ndFj5NbNbI

[Thorsten Ball @thorstenball]

Who wants macOS orbs?

https://t.co/YyygMFt7Di

[Amp @AmpCode]

“Planning is dead. Or it's going to change 99.99%.”

The hot take @sqs would add to @thorstenball’s list.

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?

[Amp @AmpCode]

Imagine the collective hours lost to reading AI-generated Slack messages, PRDs, and slide decks.

@thorstenball and @sqs discuss how AI can meaningfully accelerate product development -- just not by bolting it onto old rituals and processes.

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?

[Amp @AmpCode]

Only care about writing the code?

@thorstenball: “that game is over.”

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?

[Amp @AmpCode]

Is your agent still just the thing that writes code?

@thorstenball says the latest models let you aim much higher:

“Previously the agents went fully vertical in the stack… But now I think it's time to go horizontal, meaning the whole lifecycle.”

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?

[Amp @AmpCode]

Don't wait for your agent. Let it wait for you.

@thorstenball on why he never watches agents work: let them take as long as they need to comprehensively test changes in orbs, and focus on something else.

They don’t take up resources, or cost anything while they wait. We get back to them once we’re ready.

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?

[Amp @AmpCode]

“I thought you guys were all about non-local dev, so why do you have the runners?”

@thorstenball on runners, which run Amp agents on machines you own: a Raspberry Pi at home, a lab of test hardware, GPU boxes, a macOS build machine.

“I think runners on different machines are non-local too, you know?”

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?

[Amp @AmpCode]

“Code review in so many companies, it's a farce now. Nobody can review the volume of code, and they're not even the best at reviewing it.”

@sqs and @thorstenball on rethinking the old rules for working with agents:

“I wish I could do this, but we don't have a monorepo… then get a monorepo.”

[Amp @AmpCode]

Would you prefer to save money with dial-up when your competitors are using fiber?

Recorded on Hot Take Thursday, @sqs and @thorstenball are back with a new Raising An Agent. In this episode they discuss how cheaper models end up costing more, why they do not not wait for agents, running evals in Orbs, and the hot takes Thorsten left out of his X post last week.

00:00 Intro: Engineers who forget the history of technology
01:55 Hot Take Thursday & a €50-a-week token budget
05:14 Why cheap models cost more than frontier models
08:11 Token budgets & who gets priced out
14:06 Disrupt yourself with small teams & unlimited tokens
16:38 Agents go horizontal across the software lifecycle
20:56 Rollouts, bug reports & "I'm feeling Pucky"
23:53 Code review, monorepos & other walls around the agent
25:30 How to show a cautious company what agents can do
29:48 Why most people haven't seen what agents can do
31:57 Don't wait for your agent
33:38 Simple evals & agents testing agents in Orbs
38:27 Why Amp has runners too
40:47 Follow your energy & stay aligned
46:33 The hot take Thorsten left out
54:14 Do languages & frameworks still matter?