Spotify Engineering ✓

@SpotifyEng · Anywhere · joined 29 Oct 2014

The official account for Spotify Engineering

47 417Followers

107Following

1 520Posts total

16.5KViews on collected posts

Ultimi post

Spotify Engineering ✓@SpotifyEng11 Sep

Here's a quick look at this week's Xirp releases: → CLI tool — `xirp` command for importing, listing, and messaging sessions from your terminal → Browser panel annotations — highlight elements, comment, send to your agent in one go → Cost alerts — set a daily spend threshold, 1.6K views · 10 likes · 0 reposts · 2 replies Open on X →

Spotify Engineering ✓@SpotifyEng10 Sep

@SpotifyEng How do you decide which organizational context is durable enough to preload, versus better fetched on demand? 98 views · 0 likes · 0 reposts · 1 replies Open on X →

Spotify Engineering ✓@SpotifyEng9 Sep

Every AI agent session starts from scratch scanning, guessing, relearning things your org already knows. You're paying for that orientation loop every single time. We measured the hidden tax at Spotify and then we fixed it. Here's how https://t.co/VFeR8cNtPP 5.5K views · 67 likes · 6 reposts · 1 replies Open on X →

Spotify Engineering ✓@SpotifyEng8 Sep

One prompt. The agent pulls Portal context before it touches the codebase 🎯 🔗 Service ownership. Dependencies. Architecture. All there before the first response. No exploring. No guessing. The context came to the agent. 🚀 Portal workspace → Xirp session → grounded 2.6K views · 10 likes · 3 reposts · 0 replies Open on X →

Spotify Engineering ✓@SpotifyEng6 Sep

@SpotifyEng Spotify Engineering just cut Claude Code token usage by 90%. No infra changes. Just smarter model routing. This is what AI-native development looks like in 2026. As a dev — I'm taking notes. 📝 The playbook big teams use today is what we ship tomorrow. #AI #SaaS 68 views · 0 likes · 0 reposts · 1 replies Open on X →

Spotify Engineering ✓@SpotifyEng4 Sep

We've had 7 Xirp releases this week. Here's a quick look at a few: → Passage-level review — select parts of an agent's response, comment, send it back → Bulk worktree cleanup — find stale worktrees, see what's merged, remove in one click → Visual refresh — new header, menus, 2K views · 12 likes · 2 reposts · 1 replies Open on X →

Spotify Engineering ✓@SpotifyEng4 Sep

@SpotifyEng Routing bulk reads to a cheaper model is a solid pattern. Curious how you handle eval drift when the cheaper model occasionally misroutes or returns lower quality—do you log and review those cases? 23 views · 0 likes · 0 reposts · 0 replies Open on X →

Spotify Engineering ✓@SpotifyEng4 Sep

@SpotifyEng the routing rule is the product here. “bulk reads” and “real problems” need definitions the system can actually test, otherwise the expensive model slowly becomes the default again. the savings are real when the boundary is inspectable 40 views · 0 likes · 0 reposts · 0 replies Open on X →

Spotify Engineering ✓@SpotifyEng4 Sep

A Claude Code plugin + two declarative agents on Portal by Spotify. Bulk reads and boilerplate route to a cheaper model. Frontier model stays on real problems. 90% token savings, zero infra changes. https://t.co/Ef167UKW1u 4.7K views · 46 likes · 7 reposts · 3 replies Open on X →

Rispetto ad account della stessa dimensione

9 post degli ultimi 90 giorni, accanto alla fascia di 10K–100K follower. copertura nella norma per la sua dimensione, reazione più debole della media.

Visualizzazioni mediane1 561questo account924mediana per 10K–100K

Copertura, %3.29%questo account3.62%mediana per 10K–100K

Interazione, %0.77%questo account1.52%mediana per 10K–100K

Metrica	Questo account	Mediana per 10K–100K	Rapporto
Visualizzazioni mediane per post	1 561	924	1.69×
Copertura (visualizzazioni ÷ follower)	3.29%	3.62%	0.91×
Tasso di interazione	0.77%	1.52%	0.51×

Altri account di questa fascia → Confronta con un altro account → Come sono costruiti questi parametri →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

4.7K4 Sep

686 Sep

2.6K8 Sep

5.5K9 Sep

9810 Sep

1.6K11 Sep

Last 9 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.20%4 Sep

0.00%

0.76%

1.47%6 Sep

0.50%8 Sep

1.36%9 Sep

1.02%10 Sep

0.77%11 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes48.5%145 in total

Reposts6.0%18 in total

Replies3.0%9 in total

Bookmarks42.5%127 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Ultimi post

Rispetto ad account della stessa dimensione

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Account simili