back_office_ops · media · workflow
Spotify's Honk background coding agent automates 240 dataset migration PRs, saving an estimated 10 engineering weeks
Spotify needed to migrate approximately 1,800 direct downstream data pipelines off deprecated user datasets in only six months across three pipeline frameworks — a task estimated at 10 engineering weeks of manual effort.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Dataset deprecation triggers migration
Deprecating two heavily-used user datasets created the need to migrate approximately 1,800 direct downstream data pipelines.
Tools used
HonkBackstageCodesearchFleet ManagementClaude CodeBigQuery RunnerdbtScioGitHub Enterprise
Outcome
Spotify successfully rolled out 240 automated migration PRs using Fleetshift, saving an estimated 10 engineering weeks of manual effort.
What failed first
All-in-one prompts for Scio pipelines were abandoned because Scio's lack of standardisation made comprehensive prompts unworkable; initial context files generated from human migration guides were too vague, causing Honk to make incorrect field mapping assumptions.
Results
Time saved10 engineering weeks
Volume240
Source
https://engineering.atspotify.com/2026/4/background-coding-agents-dataset-migrations-honk-part-4
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowai agentcode generationcode diff prfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedmediasoftwareemployee productivitythroughput increasetime savedtechnical build writeupback office opsagentic task execution