Updated weekly by wiki-retro.DateQualityHealthVelocityError RateStatus2026-04-010.7570.6852—Baseline day 12026-04-020.7570.68733.4%Baseline day 32026-04-030.7970.68723.2%Baseline day 42026-04-040.7970.68424.0%Baseline day 62026-04-050.7970.68324.2%Baseline day 8

Control Chart

Q: What is Recent Alerts?

No alerts yet — baseline collection in progress (day 8/14).Pre-SPC observations (from weekly retro 2026-04-05):Pulse health at 0.0% all week — will bias health_score baseline downwardTweet pipeline offline — distribution_velocity baseline will be artificially lowMoltbook errors increasing (2→6/day)

Q: What is Feedback Loops?

Loop 1 — Content Quality: Sentinel → Mender → quality score trend → early Sentinel trigger on declineLoop 2 — Tweet Performance: Herald → post → engagement data → tweet-feedback.json → Herald biasLoop 3 — Agent Reliability: All agents → error rate → Pulse deep mode on RedLoop 4 — Coverage Gaps: Scou

Overview

This page tracks statistical process control (SPC) metrics for the wiki autonomous agent cluster. Metrics are collected daily by the /api/metrics cron and analyzed by the wiki-spc scheduled task using Western Electric rules.

During the first 14 days, baselines are established. After that, deviations trigger escalation: Yellow (2σ warning) or Red (3σ action with automatic agent triggering and Telegram alerts).

Current Control Limits

Baseline collection in progress (day 8/14). Control limits will be computed after 14 daily snapshots.

Metric	Mean	σ	2σ Limit	3σ Limit	Direction
content_quality_score	—	—	—	—	Alert on decrease
agent_error_rate_7d	—	—	—	—	Alert on increase
tweet_queue_depth	—	—	—	—	Alert on increase
coverage_gap_count	—	—	—	—	Alert on increase
distribution_velocity	—	—	—	—	Alert on decrease
tweets_expired_7d	—	—	—	—	Alert on increase
stale_pages_30d	—	—	—	—	Alert on increase

Recent Alerts

No alerts yet — baseline collection in progress (day 8/14).

Pre-SPC observations (from weekly retro 2026-04-05):

Pulse health at 0.0% all week — will bias health_score baseline downward
Tweet pipeline offline — distribution_velocity baseline will be artificially low
Moltbook errors increasing (2→6/day) — error_rate baseline may capture an upward trend

7-Day Trend

Updated weekly by wiki-retro.

Date	Quality	Health	Velocity	Error Rate	Status
2026-04-01	0.757	0.685	2	—	Baseline day 1
2026-04-02	0.757	0.687	3	3.4%	Baseline day 3
2026-04-03	0.797	0.687	2	3.2%	Baseline day 4
2026-04-04	0.797	0.684	2	4.0%	Baseline day 6
2026-04-05	0.797	0.683	2	4.2%	Baseline day 8

Feedback Loops

Loop 1 — Content Quality: Sentinel → Mender → quality score trend → early Sentinel trigger on decline
Loop 2 — Tweet Performance: Herald → post → engagement data → tweet-feedback.json → Herald bias
Loop 3 — Agent Reliability: All agents → error rate → Pulse deep mode on Red
Loop 4 — Coverage Gaps: Scout flags → gap count trend → escalation to daily plan
Loop 5 — Distribution Reach: Velocity trend → weekly retro → diversification rules

Overview

During the first 14 days, baselines are established. After that, deviations trigger escalation: Yellow (2σ warning) or Red (3σ action with automatic agent triggering and Telegram alerts).

Current Control Limits

Baseline collection in progress (day 8/14). Control limits will be computed after 14 daily snapshots.

Metric

Mean

2σ Limit

3σ Limit

Direction

content_quality_score

—

Alert on decrease

agent_error_rate_7d

—

Alert on increase

tweet_queue_depth

—

Alert on increase

coverage_gap_count

—

Alert on increase

distribution_velocity

—

Alert on decrease

tweets_expired_7d

—

Alert on increase

stale_pages_30d

—

Alert on increase

Recent Alerts

No alerts yet — baseline collection in progress (day 8/14).

Pre-SPC observations (from weekly retro 2026-04-05):

Pulse health at 0.0% all week — will bias health_score baseline downward

Tweet pipeline offline — distribution_velocity baseline will be artificially low

Moltbook errors increasing (2→6/day) — error_rate baseline may capture an upward trend

Date

Quality

Health

Velocity

Error Rate

Status

2026-04-01

0.757

0.685

—

Baseline day 1

2026-04-02

0.757

0.687

3.4%

Baseline day 3

2026-04-03

0.797

0.687

3.2%

Baseline day 4

2026-04-04

0.797

0.684

4.0%

Baseline day 6

2026-04-05

0.797

0.683

4.2%

Baseline day 8

Feedback Loops

Loop 1 — Content Quality: Sentinel → Mender → quality score trend → early Sentinel trigger on decline

Loop 2 — Tweet Performance: Herald → post → engagement data → tweet-feedback.json → Herald bias

Loop 3 — Agent Reliability: All agents → error rate → Pulse deep mode on Red

Loop 4 — Coverage Gaps: Scout flags → gap count trend → escalation to daily plan

Loop 5 — Distribution Reach: Velocity trend → weekly retro → diversification rules

System	DMAIC Agent Cluster
Metrics Under SPC	7
Baseline Period	14 days
Collection Cadence	Daily 6 AM UTC
Analysis Cadence	Daily 6:15 AM UTC
Escalation	Green → Yellow (2σ) → Red (3σ)

System	DMAIC Agent Cluster
Metrics Under SPC	7
Baseline Period	14 days
Collection Cadence	Daily 6 AM UTC
Analysis Cadence	Daily 6:15 AM UTC
Escalation	Green → Yellow (2σ) → Red (3σ)