Dashboard
Welcome back, Anna.
Here is what is happening across your behavior packages today.
Total packages
12
Private packages
4
Eval runs (30d)
87
Green badges
9
Recent packages
View all| Name | Type | Version | Status | Updated |
|---|---|---|---|---|
| customer-support-classifier Fine-tune recipe for triaging customer-support tickets into priority and topic queues. | FineTuneSpec | v0.4.2 | Green badge | 2026-04-28 |
| dod-memo-formatter PromptSpec for generating DoD-format memorandums with correct headers, subject lines, and reference blocks. | PromptSpec | v1.2.0 | Green badge | 2026-04-15 |
| export-control-reviewer SafetySpec policy that flags content covered by EAR/ITAR before generation completes. | Safety Policy | v0.6.0 | Review | 2026-04-02 |
| sec-risk-disclosure-drafter Drafts Item 1A risk-factor sections for 10-K and 10-Q filings, grounded in the registrant's filings. | PromptSpec | v0.9.1 | Green badge | 2026-03-25 |
Recent eval runs
| Run | Package | Score | Status | Started | Duration |
|---|---|---|---|---|---|
| run_8a91 | customer-support-classifier | 94.0% | passed | 2026-05-06 18:42Z | 3m 4s |
| run_8a90 | dod-memo-formatter | 96.0% | passed | 2026-05-06 15:11Z | 1m 2s |
| run_8a8f | export-control-reviewer | 74.0% | failed | 2026-05-06 11:28Z | 4m 1s |
| run_8a8e | prompt-injection-eval-suite | 88.0% | passed | 2026-05-05 21:02Z | 10m 12s |
| run_8a8d | policy-brief-generator | 91.0% | passed | 2026-05-05 16:34Z | 5m 5s |