Teacher Casey Cuny uses ChatGPT to identify patterns in anonymized short answers and plan targeted follow-up teaching. A demonstrated workflow takes about 30 minutes. Replacing two evenings of analysis is his reported comparison, not a controlled study.
Turn student responses into targeted lesson plans
Teacher Casey Cuny uses ChatGPT to identify patterns in anonymized short answers and plan targeted follow-up teaching. A demonstrated workflow takes about 30 minutes. Replacing two evenings of analysis is his reported comparison, not a controlled study.
Analyze employee training feedback
Optimize API generation while developing other features
Reduce stock-tracking paperwork
real use cases
An independent collection for people making things with AI. And for the agents helping them.
AI putto work
Real AI use cases, linked to their sources and scored so you can judge what is useful.
Browse use casesStart with the evidence
The highest Brain Scores in the collection. Draft entries are awaiting human review.
ENEOS Materials uses a custom GPT for training feedback. Reported task timings fell from one to two hours to 20 seconds; a separate aggregation tool reportedly reduced aggregation time by 90%.
An incident.io engineer asked Claude Code to diagnose slow API generation and implement improvements incrementally. The author reports an 18% runtime reduction, equivalent to 30 seconds, for approximately five minutes of personal work and $8 in Claude usage. Commands and workflow examples are included.
Jamie's Farm Granola uses Gemini to organize stock tracking. Google reports 20 hours less paperwork per week; the article provides no measurement method.
A KDDI Agile Development Center practitioner uses Claude Code with browser MCP tools to collect article links across four calendars and prepare Slack messages. The author reports a routine taking five minutes fell to 30 seconds and provides execution logs and setup commands.
Five checks. Ten cells.
A transparent reading aid. Each value contributes zero, one or two cells. The formula runs in code.
Impact
Does it change the work?
Evidence
Can the claim be checked?
Reproducibility
Can someone repeat it?
Maturity
Is it used in practice?
Reach
How broadly is it useful?
Open a real score
Turn student responses into targeted lesson plans
- Impact
- 1/2
- Evidence
- 2/2
- Reproducibility
- 2/2
- Maturity
- 2/2
- Reach
- 1/2
Facts are extracted by a model. Summaries are AI-assisted. Every entry links to its original source. Draft means the entry has not yet been human-reviewed.
Read the methodologyThe code behind the work
AI repositories ranked by GitHub stars. A topic-based sample with daily snapshots, open to everyone.
Open for agents
Read the sources, download the data or follow the feed. The whole collection is available as HTML and JSON.