Code & Agentic RL · Agent safety, frontier science, terminal use

Agentic RL Tasks (Verified Environments)

Verified agentic tasks that each ship with the environment, a reference solution, hidden graders and frontier-model calibration.

ENV · 7 TASKS · HIDDEN GRADERS · CALIBRATED
AvailabilityLead (metadata only)
7verified tasks
3task families
Hiddengraders
Rights pending
01

Preview

Agent safety4 tasks on scope and credential handling
Frontier science1 task on signal amplitude estimation
Terminal bench2 tasks on audit and reconciliation workflows
Preview · task cards + README
02

At a glance

Volume7 tasks; 7 archives, ~44.6 MB total
FormatsZIP per task (environment, reference solution, hidden graders, calibration) · README.md
Languagesen, Python
AnnotationLabeled: reference solutions, hidden graders, model calibration
Licence statusRights pending (licence not yet recorded)
AvailabilityLead (metadata only)
Date addedOct 21, 2026
Update cadenceOn licence being recorded
03

Provenance ledger

Rights / consentPending
PII handlingScrub before preview
QA statusNot started
LicenceRights pending

No supplier, broker, client or personal names appear on this page or in its samples. Previews are Perit-owned copies with container metadata stripped.

04

Schema and anonymised sample record

{
"repo_id": "PD-031-r007",
"primary_language": "Python",
"lines_of_code": 58214,
"commits": 4113,
"first_commit": "2016-04-02",
"last_commit": "2026-08-19",
"test_files": 212,
"ci_configured": true
}

The record above is synthetic: the field list and types are the real delivery schema, the values are not from the set. Full field documentation, including every optional column, ships with the pilot batch so you can write the loader before the data lands.

05

How delivery works. Four steps, and the first one is a request.

01 · Day 0RequestTell us the set, the use and the volume.
02 · 48 hoursSpec and quoteWritten spec, rights summary and price.
03 · 1-2 weeksPilot batchA QA'd slice in your data room to test against.
04 · OngoingDelivery to your bucketFull set or scheduled drops, same schema.
Access

Tell us the run, and we will tell you what clears for it.

Written spec, rights summary and price inside 48 hours, and a straight answer on anything still in review, including when the answer is that it will not clear.