Write the problem hypothesis
For [user], the agent loses or retrieves [information] incorrectly across [scope], causing [wrong action or repeated work].
You can name one user, one situation and one measurable consequence without proposing a feature.This page is preserved so old links and saved research still work. Verify the original GitHub Issue before taking action, or choose a current signal from Opportunity Radar.
Browse current opportunities →/add-context writes to global path instead of project-local by default
Evidence observed in darrenhinde/OpenAgentsControl, a Coding project.
2 comments4 positive reactions114 days openProject Radar 85
Browse current opportunitiesArchived brief · verify the original Issue
SOURCE EVIDENCE
Read original GitHub Issue ↗Start with what users actually said
Reporter context: Description Ran expecting project intelligence to land in the project repo, but files were written to instead. The flag made no difference since both paths resolve to the same location. Steps to Reproduce Run in any project Complete the wizard Check where files were created: Run — files go to the same directory What I…Excerpted from the public Issue. Read the complete thread before interpreting it.
Interview five affected users
- Which information must persist?
- For how long and within what scope?
- Show the last wrong or missing recall.
- What data must never cross boundaries?
- How do you correct memory today?
Run the smallest experiment
Test one constrained memory scope with a small real dataset and a written expected-recall benchmark.
The system retrieves the right evidence across repeated sessions without leaking or inventing context.Make a build decision
- Build: repeated pain and active commitment
- Narrow: pain is real but the audience or job differs
- Stop: weak frequency or no behavioral proof
Why this brief exists
Information has value only when it changes action. This page turns one public signal into a bounded validation exercise. It is a research aid, not proof of demand, investment advice or a product recommendation.