Build a checked film production office in Claude Cowork
Use Claude Cowork to draft a source-checked film office, then deliver approved TXT and CSV copies through private project knowledge and verify every recipient file.
Explore by topic
AI Models & Tools
Explore BIG CHANGE reporting on AI Models & Tools: what changed, how it works and why it matters.
Practical guides
181 stories
Set up a four-role AI marketing team and review one campaign
Configure a Paperclip CEO, researcher, marketer and designer around one owned campaign, approve research before creative work, and check the task and run records before using the result.
Install and verify a Journey kit, then share your own workflow
Inspect and install an exact Journey kit release, check its first use, then package a workflow you have already tested and verify that a teammate can install your release.
Upscale a 720p AI video to a checked 1440p file with Magnific
Take one rights-cleared 720p AI clip through Magnific Creative, then inspect the downloaded 1440p file for dimensions, detail, motion and audio.
Build a three-function go-to-market tool with Replit Agent
Build a restricted Replit GTM workbench that uses one approved brief for concurrent competitor analysis, marketing drafts and landing-page copy, then reviews every result before export.
Create and check an editable SVG logo and icon set in Recraft
Use Recraft V4 Vector to draft a mark and matching icons, refine and export each SVG, then check actual files, target sizes and rights before use.
Schedule a checked Claude Code repository review on Linux
A bounded Python runner pins tracked Git files, saves a private Claude Code review receipt, and gives maintainers a manual and first scheduled run check.
Pilot Claude's Opus adviser with Sonnet or Haiku and check quality and cost
Run an approved real task with the same Claude executor alone and with an Opus adviser, verify both answers, and compare complete usage and billed cost.
Build one artifact with a Claude Code builder and separate validator
Set up a Claude Code builder and read-only validator for one authorized artifact, run the real checks, allow one scoped repair, and make a documented human accept-or-hold decision.
Use Claude Code's Opus plan and Sonnet execution route, then check the work and usage
Use Claude Code's opusplan route on a bounded repository issue, review the plan and code change, and compare whole-session usage only when the baseline and result qualify.
Direct a local Cursor Agent from iPhone and verify the result
Hand a local Cursor Agent session to iPhone Remote Control, inspect its permissions, then check the local diff and tests before a commit or PR decision.
Build and check a vertical-launch simulation in Google AI Studio
Build a full vertical-launch simulation in AI Studio, inspect its generated code, verify exact math and controls, then share or release a checked revision.
Create and check a HeyGen Avatar V from a short recording
Record motion footage and separate consent, check Avatar V and paid export access, then render one approved test and inspect the downloaded file and charge.
Build a full-stack TypeScript web app with checked access
Build a private TypeScript reading queue with shared Zod contracts, an Express API, Supabase Auth and owner-only rows, then check the real app and release.
Connect Perplexity to your financial account and check one answer
Check the Plaid consent, connect one authorized financial account to Perplexity, reconcile one answer with your institution, and review access and prior data.
Write a software specification an AI coding agent can build and an owner can check
Turn real product requirements into an owner-approved software specification with a full template, bounded AI critique, acceptance cases and an exact implementation handoff.
Deploy an existing web app on Render and verify its live release
Inspect an owned working app, freeze its approved revision, configure data and sign-in before Render's first deploy, then check the live release and recovery path.
Build a paid SaaS app with an AI coding agent, from real problem to checked launch
Validate a customer job, scope and build a useful paid SaaS v1 with an AI coding agent, test tenant and payment boundaries, then approve and operate its release.