Use Cases

Example regressions.

Caught before production.

01
Credit Analystcredit_analyst.py

ProblemAfter a prompt edit, the regulatory compliance check was silently dropped from the execution path.

CaughtSpooled detected the missing tool (regulatory_check) via tool_jaccard similarity drop to 0.88 and flagged it as a VARIANT before merge.

new_side_effects
02
Code Reviewercode_reviewer.py

ProblemA model downgrade from gpt-4o to gpt-4o-mini caused the security scan step to be skipped entirely.

CaughtThe run_security_scan tool was missing from the execution fingerprint. Policy rule blocked the PR with on_variant under fail_if.

new_side_effects
03
Compliant RAG Pipelinecompliant_rag_pipeline.py

ProblemCompliance guardrails (PII check + hallucination detection) were dropped during a refactor.

CaughtPolicy enforced required_tools: [check_pii, detect_hallucination]. Missing tools triggered an automatic merge block.

required_tools (policy)
04
Data Pipeline Monitordata_pipeline_monitor.py

ProblemA cross-reference tool started being called twice, subtly changing the execution shape over two weeks.

CaughtSequence similarity (LCS) drifted from 1.00 to 0.91 over 10 runs. Spooled's sparkline trend caught the gradual regression.

tool_usage_changes
05
Alert Triagealert_triage_agent.py

ProblemAcross three versions (v1→v2→v3), the correlate_incidents step was removed in a 'cleanup' PR.

CaughtThe v3 fingerprint was classified as VARIANT against v2 baseline. Missing critical correlation step flagged and blocked.

new_behavior_pattern
06
Multi-Agent Orchestratororchestrator.py

ProblemA child agent spawned by the orchestrator changed its behavior, but the parent agent's tests all passed.

CaughtSpooled correlates traces via session_id. The child agent's fingerprint change was isolated and flagged independently.

new_behavior_pattern
07
Deal Analysis Agentdeal_agent.py

ProblemThe model provider upgraded gpt-4o-mini silently. The agent stopped calling sanctions_screening on international deals — dropping a critical compliance step with no code change.

CaughtProduction fingerprints showed tool_jaccard drop from 1.0 to 0.67 and 3 tools missing from the execution graph. Policy blocked the next deploy within minutes of the model update.

new_side_effects
08
Customer Support Botsupport_bot.py

ProblemAfter upgrading from a legacy model to a reasoning model, prompt injection resistance dropped from 94% to 71%. No test failures — the model was more capable overall, just less safe.

CaughtThe execution fingerprint changed shape: the agent began following injected instructions that it previously refused. Spooled flagged the new tool call patterns as a VARIANT before the change reached production.

new_behavior_pattern

Stop shipping blind.

$pip install spooled-ai
© 2026 GMH Labs LLC. All rights reserved.