| What it does | Platform to evaluate, trace, monitor and security test AI agents
| AI card grading that predicts PSA, BGS, and CGC outcomes in 60 seconds
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free plan at $0 forever with 5,000 spans/month, 25 test runs/month, 100 evaluator executions/month, 2 custom evaluators, 5 datasets, 2 prompts, 5 users, 3 projects, 7-day data retention. Pro plan at $39 per month with 200,000 spans/month plus $5 per 100k additional spans, 100 test runs/month, 5,000
| Hobby $4.99/month (10 credits), Starter $9.99/month (25 credits), Pro $24.99/month (80 credits), Business $74.99/month (300 credits). Annual plans: Hobby $47.99/year, Starter $95.99/year, Pro $239.99/year, Business $719.99/year. One-time credit packs from $9.99 (20 credits) to $99.99 (285 credits).
|
|---|
| Key features | - Observability and tracing of every LLM call, tool invocation and decision point with latency, cost and token usage metrics
- Evaluation to score agent answers before release against traces that broke
- Simulation to test agents with realistic users before launch
- Red teaming to find injection, tool abuse and data leaks before launch
- Prompt management with versioning and deployment controls
- Online evaluation to score real conversations in production
- Agent Insights to spot patterns and detect drift
- Real-time alerts on cost, latency, errors and quality regressions
- Support for 14+ LLM providers and 12+ frameworks
- MCP server for querying and debugging traces from inside IDE
| - 16 inspection zones covering corners, edges, centering, and surface
- 60-second grade predictions
- PSA, BGS, and CGC grade predictions with confidence scores
- Forensic Capture macro close-up analysis on Pro and Business plans
- Bulk grading for 10-50 cards at once
- Chrome extension for grading cards while browsing
- iOS and Android mobile apps
- Smart capture guide with real-time lighting and angle feedback
- Market value estimates for graded cards
- API access with webhooks on Pro and Business plans
|
|---|
| What makes it different | - Single platform that covers the entire AI agent lifecycle from prompt management through production monitoring, instead of scattered tools
- Built on OpenTelemetry standards for native observability across frameworks you already use
| - Photo-based pre-screening avoids months-long mail-in turnaround times
- Trained on thousands of card images across all major trading card types
- 2-grade credit-back guarantee if predictions miss
- Detailed per-pillar subgrades showing exactly where cards lose points
- Works across all major trading card categories including Pokémon, sports, and TCG
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 13 ▼ −1 (down) since last check | 33 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 10 | 9 |
|---|
| Citation Flow (Majestic) | 26 | 36 |
|---|
| Referring domains (Majestic) | 32 | 125 |
|---|
Netra
CardGrade