Tagged · Output Testing
Field notes,
Output Testing.
25 articles in this tag — part of the Jaypore Labs journal.
- 01Engineering
What makes an eval good
Apr 29, 20267 min read - 02Engineering
Trend evals vs. threshold evals
Apr 28, 20262 min read - 03Engineering
Pairwise judges: A/B agreement at scale
Apr 22, 20262 min read - 04Engineering
Eval CI: the pass/fail gate that's actually useful
Apr 21, 20262 min read - 05Engineering
Eval result storage and versioning
Apr 10, 20262 min read - 06Engineering
Eval anti-patterns: when evals make products worse
Apr 7, 20263 min read - 07Engineering
Eval-driven prompt iteration
Apr 6, 20262 min read - 08Engineering
Tool-use evals: right tool, right order
Apr 6, 20262 min read - 09Engineering
Building your first eval set from scratch
Mar 31, 20268 min read - 10Engineering
Evals for agents: trajectory + outcome
Mar 31, 20267 min read - 11Engineering
LLM-as-judge: when to trust it, when not
Mar 30, 20267 min read - 12Engineering
Human eval workflows: instructions that don't vary
Mar 26, 20262 min read - 13Engineering
Judging open-ended output without a rubric
Mar 26, 20262 min read - 14Engineering
Calibrating your judge: meta-evals
Mar 23, 20262 min read - 15Engineering
Eval taxonomy: golden, behavioural, drift, safety
Mar 18, 20263 min read - 16Engineering
Evals for retrieval: separating retrieval from synthesis
Mar 18, 20262 min read - 17Engineering
Evals that survive a model bump
Mar 12, 20263 min read - 18Engineering
The red set: adversarial cases you're allowed to fail
Mar 12, 20262 min read - 19Engineering
Per-feature evals vs. per-model evals
Mar 11, 20262 min read - 20Engineering
Sampling production traffic for eval
Mar 11, 20262 min read - 21Engineering
Authoring eval cases
Mar 5, 20262 min read - 22Engineering
Reading an eval dashboard
Mar 4, 20262 min read - 23Engineering
Eval ownership in an org: PM, eng, or QA?
Mar 3, 20262 min read - 24Engineering
Auto-generated eval cases from production logs
Mar 2, 20262 min read - 25Engineering
Eval cost management
Mar 2, 20262 min read