Asking Whether the Work Is Done
Checking on a computing job seems harmless. But someone has to answer each request, and new observations at Harvard show why an AI agent's appetite for updates deserves a more careful look.
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:
Reading Past the Feedback Summary
A quick AI summary can help you prepare to discuss employee feedback. But which comments shaped its headings, and what might you miss if those headings become the whole agenda for the conversation?
When the Customer Changes the Test
A simulated customer volunteers information, and an AI support agent completes the task. That helpful exchange raises a harder question: how much can a success score tell us when the customer changes the test?
Secrets in an Ordinary Summary
How can a summary of public facts reveal a secret? In a simulated security exercise, AI agents learned to send messages that passed inspection but meant something more to a receiver that remembered earlier exchanges.
Before You Fix the Bug
An AI agent finds a failing test, but does the software need fixing or is the test asking for the wrong thing? Two bug reports show why that question matters before writing a patch.
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.