Route agent tasks by case features and audit accepted work
Build a deterministic per-case Agents SDK model route from owner-approved features, then compare every attempt and human-accepted task with a fixed baseline.
The BIG CHANGE archive
News, analysis and practical guides.
Explore our reporting on how AI and robotics change work, business and the world.
Explore the stories
270 stories
Chain Claude Code skills into one reviewed GitHub issue
Use three Claude Code project skills to prepare an evidence-linked GitHub issue, secure exact human approval, then create and reconcile one issue with a checked readback.
Carry a reviewed Stitch DESIGN.md into two checked Claude Code components
Export a real Stitch DESIGN.md, approve its exact revision, import it into Claude Code and check two components against the same design.
Run a Claude Code evidence brief through three reviewed specialists
Build a source-grounded Claude Code brief with three fresh specialists, sealed handoffs and owner-reviewed rule trials. Includes the complete copyable workflow.
Use Claude Dispatch from your phone to check a Windows Notepad action
Send one bounded Notepad request from an eligible Claude Dispatch account, then inspect the exact local result and recover safely if the route or outcome differs.
Share one brand.md across two Claude Code skills
Create one approved brand.md, point two distinct Claude Code skills to it, then check a rule change against four fresh task runs.
How to dictate and review a Claude Code prompt before sending it
Prepare an authorized request, verify its captured words, and review the agent's result.
Take a software milestone through GSD Core phases and acceptance
Use current GSD Core commands to carry an owned software milestone from requirements and phase plans through fresh-context execution, handoff, project tests and human acceptance.
Evaluate an AI agent product across three decision axes
Map one agent product’s runtime and data paths, orchestration and oversight, and interface contract against your own mandatory requirements with a copyable decision worksheet.
Put a complete process diagram in a Claude Code skill and check it
Map your owned procedure into a Claude Code skill with a Mermaid flowchart, check every branch in fresh sessions, and compare exact instruction tokens if API access permits.
Turn Claude Code session results into reviewed project learnings
Export a finished Claude Code conversation, check the evidence, review a bounded Learnings.md change, and test one lesson in a fresh session.
Check TextEdit with Claude Code computer use on Mac
Set up one Claude Code TextEdit check on Mac: enter a fixed line through the visible interface and compare the document with the session’s actions.
Connect Claude Code to iMessage and check a reply from your phone
Set up Claude Code’s official iMessage channel on a Mac, send one self-message about an existing project file, and verify the same-thread reply against the file.
Create a Suno song with your own verified voice and check the result
Record and verify your own vocal in Suno Voices, select it for a song, then compare the generated singer with your source recording while checking access, credits and rights.
Measure six ways to cut a scraping agent’s HTML input without losing card fields
Compare six local controls on three permitted HTML listing pages, count serialized input with a pinned tokenizer, and check every extracted card against an independent reference.
Diagnose six agent failure patterns from a real run
Use an owned Python Agents SDK trace and pre-run requirement to investigate six failure patterns, identify the first proven divergence, and verify a bounded repair.
Create and check a daily news brief in Claude Cowork Projects
Save a personalized Cowork Project profile, check a current source-linked brief, then schedule one daily task with complete instructions and verify its first result.
Organize two ongoing tasks with Claude Cowork Projects
Set up two Claude Cowork Projects for separate ongoing tasks, then check each project's instructions, references, account-memory choice and first output.