Skip to content
ClaudeClaude

Coding is no longer the constraint: Scaling devex to teams and agents at Spotify

At Spotify, 96% of engineers now code with AI and PR frequency is up 60% — so the constraint has moved from writing code to orchestrating it. Niklas Gustavsson, Chief Architect & VP of Engineering, shares how Spotify built Honk, a background coding agent running on the Agent SDK, plugged it into their Fleetshift migration platform and Backstage software catalog, and learned that the same standardization that makes teams effective makes agents effective too. Walk away with Spotify's bets on developer experience for agents — and why firmer guardrails are accelerators, not constraints.

May 20, 202627mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Spotify scales developer experience with AI agents, automation, and standards

  1. Spotify saw extremely rapid adoption of AI coding tools, with 99%+ of engineers using them weekly and a large jump tied to the Opus 4.5 release.
  2. AI-assisted development increased pull-request (PR) frequency by ~76%, with many PRs now co-authored by agents and developers.
  3. Years of pre-AI “fleet management” automation (Fleetshift) laid groundwork for massive automated maintenance, already producing 2.5M maintenance PRs with most auto-merged.
  4. Spotify evolved from deterministic migration scripts to an LLM-based migration agent (Honk) that runs in Kubernetes with trusted verification tools and CI to safely execute complex code changes at scale.
  5. As coding becomes less of a bottleneck, Spotify is reallocating human judgment toward higher-leverage points like review prioritization, product decisions, and rapid prototyping in real production codebases.

IDEAS WORTH REMEMBERING

5 ideas

AI coding adoption can reach near-universal usage when integrated into daily workflows.

Spotify reports 99%+ weekly usage and 94% self-reported productivity gains, driven by convenient tool access and clear developer value (e.g., faster PR throughput).

Scale requires automation that verifies and merges changes safely, not just generates code.

Spotify’s Fleetshift approach pairs PR generation with automated validation and auto-merge, enabling thousands of low-risk maintenance changes per day without human attention.

Deterministic migration scripts don’t scale to real-world code variance; LLMs help absorb edge cases.

API surface diversity and “Hyrum’s Law” created unmanageable corner cases in scripted migrations; Honk uses an LLM to handle variations while still relying on verification to ensure correctness.

Agent capability depends heavily on strong engineering hygiene: tests, linting, and consistent patterns.

Spotify emphasizes that agents become more autonomous and accurate when they can run tests/CI and when the codebase enforces standardized practices that steer the agent back on-track.

Developer experience platforms become “agent experience” platforms when exposed as tools.

Backstage’s catalog and operational tooling are exposed to agents via MCP/CLI, letting agents discover ownership, navigate systems, and even contact teams—critical for large, distributed orgs.

WORDS WORTH SAVING

5 quotes

And today, more than ninety-nine percent of our engineers use AI coding tools every week.

Niklas

By now, by far most of the PRs that we ship are authored by an AI agent together with the developer.

Niklas

Today, up, up until today, we've now merged two and a half million of those automated maintenance PRs, work that our developers did not have to do.

Niklas

What used to be what I described before, hundreds of teams doing migrations for their components, taking weeks and weeks or months, now can be done by a single engineer in a few days.

Niklas

Developers, one of our most frequent feedbacks at the moment is there's just too many freaking PR, PRs to review.

Niklas

AI tool adoption curve and productivity metricsPR volume growth and review burdenFleet management automation (Fleetshift)Automated maintenance PRs and auto-merge validationLLM-based migration agent architecture (Honk + Agent SDK)Agent orchestration and collaboration (Chirp, shared sessions, projects)Codebase standardization via Backstage (catalog, golden paths, Sound Check, linting)Shifting bottlenecks: from coding to decisions and governanceRapid prototyping in production monorepos with agents

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.