Tekhnika/ai-agent-cost-reliability-monitoring-dataset-free

---
pretty_name: AI Agent Cost Reliability Monitoring Dataset
language:
- en
license: cc-by-nc-4.0
tags:
- tabular-data
- analytics
- observability
- agentic-ai
task_categories:
- tabular-classification
- time-series-forecasting
size_categories:
- 1K<n<10K
---

# AI Agent Cost Reliability Monitoring Dataset

Free sample for AI agent reliability dashboards, anomaly exploration, and observability-oriented analytics workflows.

## What is included
- customer_escalation_reviews.csv: 705 rows, 10 columns
- daily_escalation_health.csv: 253 rows, 10 columns
- escalation_cases.csv: 1085 rows, 10 columns
- handoff_events.csv: 3256 rows, 10 columns
- resolution_actions.csv: 2171 rows, 10 columns
- support_pods.csv: 27 rows, 10 columns

## Why this dataset is useful
- Good starter sample for an agent reliability dashboard or observability notebook.
- Useful for validating run-level and event-level analytics in Python, SQL, and BI tools.
- Lightweight enough for quick experiments while still matching the core workflow of the full starter pack.

## Starter use cases
- Agent reliability baseline using run and event data.
- Observability dashboard for event severity, run behavior, and agent health patterns.

## Schema overview
### customer_escalation_reviews.csv
- Rows: 705
- Columns: feedback_id, run_id, agent_id, feedback_time, resolution_time_min, issue_category, rating_score, thumbs_up_flag, hallucination_flag, resolved_flag

### daily_escalation_health.csv
- Rows: 253
- Columns: metric_id, agent_id, metric_date, runs_total, success_rate, tool_error_rate, avg_cost_usd, user_satisfaction_score, incident_count, breach_count

### escalation_cases.csv
- Rows: 1085
- Columns: run_id, agent_id, session_id, started_at, ended_at, run_status, goal_type, dataset_split, duration_ms, estimated_cost_usd

### handoff_events.csv
- Rows: 3256
- Columns: event_id, run_id, agent_id, trace_id, span_id, event_time, event_type, severity, component_name, message_template

### resolution_actions.csv
- Rows: 2171
- Columns: tool_call_id, run_id, agent_id, started_at, ended_at, timeout_flag, tool_category, error_type, tool_name, latency_ms

### support_pods.csv
- Rows: 27
- Columns: agent_id, created_at, agent_type, tool_access_tier, status, traffic_tier, cost_profile, agent_name, team_name, region

## Free vs full version
- Free Kaggle sample: reduced rows, reduced columns, starter notebook, and enough linked observability tables to validate the core workflow.
- Full version: full row volume, richer feature coverage, tool and feedback tables, and extra starter assets for dashboard, SQL, and anomaly-analysis work.

## Upgrade to full version
- Buy full dataset: https://tekhnikalab.gumroad.com/l/ai-agent-cost-reliability-monitoring-dataset
- Upgrade if you need the full linked schema plus starter assets that get you to a dashboard, SQL project, or anomaly baseline faster.

## Notes
- Contains generated data only and no real personal data.
- Designed as a lightweight free sample for evaluation and discovery.