✓ ShippedByAgents
Practitioner (own blog/paper) Migration

Google migrates production YouTube models from TensorFlow to JAX with a planner, orchestrator and coder agent system, 6.4x to 8x faster than by hand

Google's AI and Infrastructure team found single-agent setups failed on production TensorFlow models spanning many files. It built a multi-agent system: a planner using compiler-based static analysis to order work from leaf layers up, an orchestrator that chunks steps and recovers from failed builds, and a coder agent in internal IDE tools that runs a build and test-and-fix loop. Playbooks of golden examples from manual migrations steer it. Each unit is checked numerically with gradient ascent to find the maximum error between TF and JAX layers, and a blind LLM judge scores architecture.

The numbers (as reported)

Speedup6.4x to 8x over manual migration
TimeSeveral SWE-months reduced to a few weeks of AI-assisted generation plus expert review
Models migratedReal-world YouTube models with thousands of lines of code and hundreds of layers

Facts

Company / subject
Google (AI and Infrastructure)
Tools
Unstated
Codebase
brownfield
Work type
Migration
Stack
TensorFlow, JAX, Python
Published
2026-05-06
Last checked
2026-11-03

What the source claims Practitioner (own blog/paper)

Claimed by the builder, writing about their own work. Not checked independently.

  • Model migration 6.4x to 8x faster than doing it manually 6.4x to 8x
    “the multi-agent system achieved a 6.4x to 8x speedup over performing the migration manually”
  • Several SWE-months of work reduced to a few weeks plus expert review several SWE-months to a few weeks

Caveats

Google writing about its own system; it also sells AI products. The post does not name the coding model or say how many models were migrated. Speedup is from their evaluations; a technical paper is referenced but not linked here.

More stories by tool: Unstated

Related topics: MigrationsBrownfield codebases

Source

Google Cloud Blog (Jamie Rogers, Parthasarathy Ranganathan)

One email a week: what actually shipped

New sourced stories, the numbers behind them, and what didn't work. No hype.

We'll only use this to send the newsletter. See the privacy page.