Ideas with work to do
20 directions have pages here: 2 retained for falsification and 18 parked. Selection and development gates are separate; these are provisional research lanes, not products. Each page states what would change our mind.
PROVISIONALLive Integration RadarPrimary recommendation withdrawnProblem: Parallel changes can pass their own tests and still fail when combined.Idea: Can unfinished agent work reveal a composition problem before the tasks are complete?
Next test: A useful neutral task family where a real agent discovers and consumes a warning.
PROVISIONALStorage-aware workspacesParked as competition candidate; final shortlist unsignedProblem: Separate agent workspaces can fill the disk with repeated dependencies and builds.Idea: Keep writable tasks isolated without multiplying dependencies and build footprints.Next test: Keep useful storage advice and read-only diagnostics.
PROVISIONALBehavior-based fork tournamentParked provisionally; selection advantage not demonstratedProblem: Comparing several agents' attempts takes time, and a plausible answer can still be wrong.Idea: Choose between parallel attempts by what they do, with a bounded and independent review.Next test: Compare a single attempt and existing vendor-style selection on a declared small task set.
PROVISIONALChange-story reviewInternal use; comparative benefit unprovenProblem: Agent-generated changes increase review work; long summaries can hide mistakes or mislead reviewers.Idea: A short account of behavioral changes, tied to the evidence a reviewer actually needs.Next test: A prospective unfamiliar review decision with equal evidence and an ordinary PR-list control.
PROVISIONALDurable task handoffParked provisionally; ordinary recovery baseline sufficedProblem: When an agent restarts or hands off a task, its intent, unfinished work and correct code version can get lost.Idea: Resume the right task on the right code state without reconstructing an entire conversation.Next test: Reopen only with firsthand demand, a gap against incumbent recovery, and an actual ordinary-baseline failure.
PROVISIONALLease-bound claims enforced at landingParked; reopen only if the expired-lease race test passesProblem: Stop two agents from silently doing overlapping work.Idea: an agent claims the files it's working on, and the system refuses to merge overlapping changes from another agent.Next test: Not yet scheduled.
PROVISIONALMerged-state gate + bounded intent reapplicationParked; reopen only after the merged-state fixture testProblem: A change made against an older code version can break newer work when it is merged.Idea: the system tests changes together before it accepts them.Next test: Not yet scheduled.
PROVISIONALSemantic contract sentinelParked; compared against running the full test suite on the merged stateProblem: Changes can merge without text conflicts but break behavior that other code depends on.Idea: catches changes that merge cleanly but quietly break something another part of the code relies on.Next test: Not yet scheduled.
PROVISIONALMaintainer inbound quarantineParked; reopen test recorded, not selectedProblem: Maintainers spend time reviewing AI contributions that lack a working fix or evidence.Idea: contributions from AI wait in a holding area until they show they're worth a human's time.Next test: Not yet scheduled.
PROVISIONALIndependent reviewer panel on pushNot selected; parked without a testProblem: Bugs in agent-written code can reach human review without an independent check.Idea: AI reviewers unrelated to the agent that wrote a change check it before a human looks.Next test: Not yet scheduled.
PROVISIONALExact-SHA verification receiptsParked; the narrowed publication-receipt idea waits on a kill testProblem: A passing test report may refer to an older change or a different combination of commits.Idea: a trusted record of exactly which version someone tested, under which rules.Next test: Not yet scheduled.
PROVISIONALMerge decision ledgerNot selected; parked without a testProblem: Git history can show what changed without explaining why or which alternatives were rejected.Idea: for any piece of code, it records why it was written that way and which alternatives were rejected.Next test: Not yet scheduled.
PROVISIONALQuarantine forks + capability tokensParked; Task Passports refinement waits on first-hand demandProblem: An agent with broad Git access can overwrite shared history or affect another agent's work.Idea: agents work in separate copies with limited permissions, so they can't delete or overwrite the main history.Next test: Not yet scheduled.
PROVISIONALSession footprint undo across forksParked; reopen test recorded, not selectedProblem: One agent's changes can spread across several branches, making them hard to find and undo safely.Idea: you see everything one agent did, everywhere, and reverse it in one step.Next test: Not yet scheduled.
PROVISIONALPreview-per-agent runtime isolationParked; folded into the collision radar as runtime verificationProblem: Agents running separate changes can still collide over ports, databases and shared runtime data.Idea: each change gets its own running preview and data, so agents don't fight over the same ports or database.Next test: Not yet scheduled.
PROVISIONALPush-triggered fast verification laneNot selected; parked without a testProblem: Slow or expensive test runs delay feedback, and agents can miss failed checks.Idea: after every change, the system runs only the tests the change could affect and reports back within seconds.Next test: Not yet scheduled.
PROVISIONALFork-is-the-task boardNot selected; parked without a testProblem: People must keep task-board status in sync with the code agents are actually working on.Idea: there's no separate task board.Next test: Not yet scheduled.
PROVISIONALMulti-repo change sets with recoveryParked; investigate-first, must beat the existing deploy-check toolsProblem: Changes across related repositories can leave incompatible versions if integration fails partway.Idea: one change rolls out across several related codebases in the right order, with a way to recover if it fails partway.Next test: Not yet scheduled.
PROVISIONALMaintenance swarm with batch landingParked; partly folded into the collision radarProblem: Many small maintenance changes can create a backlog of test runs and merges.Idea: dozens of agents each take one chore, such as an upgrade or a cleanup, and the system merges the compatible results together.Next test: Not yet scheduled.
PROVISIONALEarned-autonomy policy per agent configNot selected; parked without a testProblem: Reviewing every small agent change takes time, but letting all changes merge automatically risks defects.Idea: setups with a good track record can merge low-risk changes on their own, and everything else goes to a human.Next test: Not yet scheduled.
OPENOpen place — nothing selectedReopened · no candidate approvedThe private test site idea was folded into the collision radar. Nothing has earned the sixth place yet.
Next test: Open