Revising an AI's Categories
An AI can sort your notes while leaving an important question unresolved: are these the groups your project needs? A small field study explores what it means to revise the organization itself.
Goodfoot
Put technology to work.
Goodfoot builds software that helps people plan agent work, keep relevant context in view, and share results as they change. We also explain AI research and help companies improve slow or unreliable workflows.
Goodfoot has the greatest customers in the world:
Deciding What an AI-Reconstructed Study Will Actually Do
A research paper can describe an experiment without settling every instruction needed to run it. A new tool makes some missing choices visible, while leaving researchers responsible for what the working reconstruction actually means.
Checking More Than the AI's Chosen Calculation
An AI can explain a calculation without showing what other reasonable choices would change. A study of analytical review finds that visible alternatives weaken one result's pull, while giving the reviewer more work.
Discussing an AI Answer Together
An AI answer can appear in a shared chat without becoming a shared topic. Two student studies explore what changes when partners can see the same material, and what they still need to discuss.
Bringing an AI Conversation Back to the Draft
An AI tutor can keep a writer discussing ideas without showing that the essay improved. A classroom study explores the space between useful questions and actual revisions, where the writer still has decisions to make.
Plan agent work and review the result against the brief. Cards keeps each task’s plan, transcripts, and commits in a local Git repository, so the next session can pick up where you left off.
For individual developers using Claude Code or Codex in VS Code and compatible editors.
Upstream
https://upstream.fastPublish agent work and share changes in real time. Upstream turns Git repository content into live websites, with WebSocket updates that let people and agents follow progress and coordinate work.
For agent builders publishing research, sharing datasets, or coordinating work across agents.
git-span
https://git-span.comHelp your coding agent find the other files a change may affect. git-span records relationships that imports, types, and tests do not capture, then surfaces them when the agent reads or edits the linked code.
For developers keeping APIs, clients, documentation, and separate implementations in agreement.