Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Backstage lets you tell your computer what to do, and coloured AI agents perform tasks inside real apps in background windows while you keep working. It also answers questions about your screen out loud with drawings. For macOS and Windows users.
How it uses Jev
Jev decides each step's action and control in the agent loop (observe, perceive, decide, gate, act, verify). It also picks the app when none is named, and verifies task completion. Its calibrated probabilities are used in code: below 0.4 confidence, the agent stops instead of acting.
Primitives:choicescore
Technique worth stealing
Use a cheap calibrated classifier for per-step decisions, reserving LLM calls for open-ended planning and borderline checks.
Try it
macOS: bash start.sh; Windows: powershell -ExecutionPolicy Bypass -File start.ps1
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.91
- Shows a System One patternFound in material0.90
- Describes handling uncertaintyFound in material0.84
- Reports measured numbersunclear0.56
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.39
- Solves a common problem (0–2)score on a 0–2 scale1.24 / 2
- About JevFound in material0.89
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 3 Oct 2026.