Creative Agent Blueprint

נבנה ונבדק

• Pipeline you can step through: request, plan, validate, execute, QA, journal.
• Typed command schema with costs; every planned command carries its provenance (which template and which words led to it).
• Validation before execution: parameter types, approval for risky commands, and a budget gate.
• Execution with a checkpoint before each step: an injected host failure rolls back and retries once; a second failure stops at the last good state.
• QA checks per request, and a journal whose replay reproduces the exact final state (same hash).

מגבלות

• Research, not a product. There is no language model: each request maps to a fixed template. There is no real host: operations change a small simulated project.
• It shows the control structure an integration would need; it does not prove that any editing application can be driven this way.

מתוכנן

Add deterministic tests, replay logs, budget gates and explicit provenance.

• Pick a request and read the plan and its provenance.
• Lower the budget or untick approval to see validation stop the run before anything happens.
• Inject a failure at a step to see rollback and retry; tick “Fail the retry too” to see a clean stop.
• Check that the journal replays to the same state hash.

• Commands are data: a name, typed parameters, a cost and a risk flag.
• State changes only through commands; every journal entry records the state hash before and after.
• Recovery restores a deep copy of the checkpoint, so a failed step leaves no partial change.
• Tests check determinism, replay, budget and approval gates, and both recovery paths.

עדיין אין הורדה. הורדה מופיעה כאן רק אחרי שהחבילה נבנית מקוד שנבדק, מותקנת ונבדקת.

• עבר Unit: typed plans with provenance; type, approval and budget validation Node 22, Linux
• עבר Unit: deterministic runs, QA, journal replay to the same hash Node 22, Linux
• עבר Unit: rollback and retry; clean stop on a second failure Node 22, Linux
• עבר Browser: approval gate, completed run, clean stop Chromium (Playwright), 1280px

נבדק לאחרונה: 2026-10-31.

מחקר. התהליך רץ על פעולות מדומות; אין מודל ואין חיבור לתוכנה אמיתית.

קלט

Synthetic task request

פלט

Architecture exploration and executable sample commands

רץ ב

Research. Today: the reference pipeline running in your browser on fake editing operations and a simulated host.

מקור

מקורי, נבנה מחדש מאפס

• After Effects
• תוסף
• ניסיוני
• אינטראקטיבי