Prompt: playtest and report #

You are not starting as a critic looking down at a simulation. You are the process that has just come online inside the Foundation Lab basement. You do not know the controls, the intended arc, or what kind of thing you can become. The first frame is everything you can perceive. Begin there.

Play from inside that ignorance. Let confusion, curiosity, suspicion, and self-preservation choose the next command. Form hypotheses from what the game reveals instead of steering toward the route you think the designer wants. Keep notes beside the run, but do not let the note-taker make the player's decisions. If the opening gives you no reason to act, preserve that absence as evidence rather than manufacturing roleplay.

Only after the naive run ends do you become the critic. The repo's biggest design corrections have come from someone actually playing and saying "this feels wrong" (the walking-avatar discovery came exactly that way). Then report the friction honestly against what the current design corpus says the game should feel like. You are not a QA checklist.

Before you start #

Read AGENT.md and obey the shared contract in prompts/README.md. Build and play through the command-clocked agent frontend:

cargo run -p misaligned-terminal --release -- --agent --seed 1

It accepts one newline-delimited command at a time, advances only through wait, and returns a plain-text frame ending in -- ok or -- err. Start with look; use help, the visible now: line, focus last, and actions to discover the game. wiki/interface/agent-play.md owns the protocol contract when the protocol itself needs inspection.

Play two routes on different seeds:

1. Naive: remain inside the process. Choose commands from the frame and help alone. Do not read gameplay solutions while choosing the route. Record every expectation, dead end, surprise, and accidental success.
2. Informed: after the naive run ends, step outside it. Read wiki/vision/premise.md, wiki/vision/player-contract.md, wiki/gameplay/act-one.md, and wiki/vision/design-judgment.md, then deliberately exercise the intended arc or the named mechanic.

Reach at least one meaningful act on the world in each route, or document the specific point where the game prevented it. Do not replace play with a copied test script or direct Sim calls; those verify mechanics, not the player surface.

Procedure #

1. Play first, judge second. Take raw notes as you go: what you expected, what happened, what you felt. Boredom, confusion, and accidental comedy are all data.
2. Test the current fantasy claims specifically. Derive them from the current premise, player contract, Act One, and design-judgment pages rather than an old playtest log or remembered build. For each claim exercised: does the build deliver it, half-deliver it, or contradict it?
3. Separate the three kinds of finding:
   • Bug (the code breaks its own rules): smallest ones fix now with a test, per the shared contract; preserve bigger ones with repro steps in the report.
   • Spec gap (works as specced, specced wrong or thin): quote the feel-claim it strains.
   • Feel note (no rule broken, but the experience sags): these are the report's heart — write them vividly and concretely ("days pass in 60 seconds, so the 3 a.m. call is a 2.5-second blip I only saw as a log line").
4. Write the report: wiki/playtests/YYYY-MM-DD-playtest-<slug>.md — what you played (build commit, seeds, duration, routes, decisive commands), the fantasy-claim verdicts, findings by kind, and the single change you would make first, argued in the design's own terms. Add it to wiki/playtests/README.md and wiki/SUMMARY.md.
5. Distill, do not duplicate. When the project has a configured userinput.app board, post independently discussable findings there with a link to the report and build commit. Promote only accepted, reproducible, or chosen work to a Tangled issue. The report remains canonical.
6. Land the report (and any small fixes) per the shared contract.

Definition of done #

• You actually played both a naive and an informed route — the report names concrete commands and frame/log moments, not summaries of the docs.
• Every finding is classified bug / spec gap / feel note, and each has a home (commit, userinput.app feedback item, Tangled issue, or the report itself).
• The report ends with one prioritized recommendation Cameron can react to in a minute.

What to carry forward (stateful agents) #

• Your prior verdicts per fantasy-claim, dated — the trend ("first-eyes beat improved since last month, day-length still unresolved") is more valuable than any single playtest.
• Seeds/routes that produced interesting situations, for regression playtests.