Skip to content
Work

Engagement patterns, documented in full

Newbieget Labs is an early-stage firm, so we publish the shape of our programs rather than borrowed logos. Volumes below are illustrative. Named client studies publish once engagements clear for publication.

Start a pilotQuality framework
Agent trajectoryGraded step by step, not pass or fail

A run that ends green can still be wrong in the middle. Scoring the trajectory is what separates an agent benchmark from a unit test.

01Model Evaluation6 weeks · pilot to recurringPattern

A 1,000-item coding evaluation, delivered a day early with the audit attached

The standard six-week play: pilot scoped against the client’s own acceptance bar, pod calibrated to an agreement gate before production, batch delivered with full QA evidence, converted to a dedicated pod inside two weeks.

Read the pattern
Acceptance
96.8%
Client spot-check, against a 95% bar
Schedule
−1 day
Delivered ahead of committed date
Rework
48h
Two Cat-A defects, at our cost
Expansion
3 months
Dedicated pod signed within two weeks
02Agent Benchmarking10 weeks · programPattern

Terminal-agent benchmark built end to end, from task taxonomy to grading pipeline

Agentic evaluation is where crowd models break. Task authoring, Dockerised environment engineering, verified gold solutions and step-level trajectory grading, run as one accountable workstream.

Read the pattern
Reproducibility
100%
Gold solution passes from clean container
Grader agreement
κ ≥ 0.7
Tracked per rubric dimension
Shortcut audit
Every task
Adversarially reviewed before inclusion
Handover
Full
Harness runs in your CI, not ours