Skip to main content
The nightly loop is TENET’s autonomous improvement engine. It runs while you sleep, making focused code changes, measuring results, and keeping only what improves.

​
How It Works

Every night at 2 AM (configurable):
  1. Mine tuples — Extract training data from today’s journal entries
  2. Synthesize context — Generate product context summary for agents
  3. Strategic reasoning — Stratus decides which agents to run based on ROI
  4. Run agents — 5 rounds per agent, ~1 hour total
  5. Retrain policy head — If 50+ new tuples since last training
  6. Pick up backlog — Grab GitHub/Linear issues for autonomous PRs

​
Setup

If you have OpenClaw running, add a cron job: 
{
  "name": "nightly-loop",
  "schedule": { "kind": "cron", "expr": "0 2 * * *", "tz": "America/Denver" },
  "payload": {
    "kind": "agentTurn",
    "message": "cd ~/CascadeProjects/my-project && jfl peter daily >> .jfl/nightly.log 2>&1",
    "timeoutSeconds": 3600
  }
}

​
System Cron

# crontab -e
0 2 * * * cd /path/to/project && jfl peter daily >> .jfl/nightly.log 2>&1

​
Manual Run

jfl peter daily

​
What to Expect

First run output: 
  Peter Parker - Daily RL Agent Loop

  Found 5 RL agent(s):
    • test-coverage (coverage_percent, maximize)
    • code-quality (quality_score, maximize)
    • cli-speed (p90_ms, minimize)
    • telemetry-rl (product_health, maximize)
    • onboarding-success (success_rate, maximize)

  Pre-flight: Mining tuples from journals...
    Mined 12 tuples, 8 new → buffer total: 2772

  Pre-flight: Synthesizing product context...
    ✓ Product context updated

  Layer 3: Strategic reasoning...
    Run: ["test-coverage", "code-quality"]
    Skip: ["cli-speed"] — near optimal
    Reasoning: test-coverage has highest gradient (87% headroom)

  Hub health: ✓ (12ms)

  ── test-coverage ──────────────────────────────
    Baseline: 0.1276
    Round 1: +0.0031 KEPT
    Round 2: -0.0002 REVERTED
    Round 3: +0.0018 KEPT
    Round 4: +0.0012 KEPT
    Round 5: -0.0001 REVERTED

  ── code-quality ───────────────────────────────
    Baseline: 0.6836
    Round 1: +0.0045 KEPT
    ...

  Daily loop complete.

​
Monitoring

​
Check Last Night’s Results

# View the log
tail -100 .jfl/nightly.log

# Run the scorecard
bash eval/nightly-scorecard.sh

​
Scorecard Output

╔════════════════════════════════════════════╗
║           JFL Nightly Scorecard            ║
╚════════════════════════════════════════════╝

┌──────────────────┬──────┬──────┬──────────┐
│ Agent            │ Runs │ Kept │ Signal?  │
├──────────────────┼──────┼──────┼──────────┤
│ test-coverage    │   15 │    8 │    ✓     │
│ code-quality     │   10 │    4 │    ✓     │
│ cli-speed        │  174 │   16 │    ✓     │
└──────────────────┴──────┴──────┴──────────┘

  Keep rate: 28/199 (14.1%)

​
Tuning

​
Rounds Per Agent

Default is 5. Increase for agents with high gradient: 
# .jfl/agents/test-coverage.toml
rounds = 20  # More rounds = more improvement per night

​
Strategic Reasoning

PP uses recent agent performance to decide who runs. If an agent has plateaued (0 improvements in last 10 runs), it gets skipped automatically.

​
Cost Control

Each round costs ~0.50−1.00inAPItokens(dependsonmodel).5agents×5rounds= 0.50-1.00 in API tokens (depends on model). 5 agents × 5 rounds = ~15/night. Use --budget to cap costs: 
jfl peter daily --budget 10  # Stop at $10