Ideas worth your time

Explore intelligence

Discover ideas, people, and practical knowledge worth exploring.

8,296 results · Most relevant

For creators · Explore System ideas →

Explore

Worth exploring

Every insight the pipeline has cleared, with its creator and the analysis it came from.

WHY · 8075 cleared results from 164 sources on record

Principle · Money

Fix data quality first, then prompting, then model, then hyperparameters

Iteration hierarchy: fix data quality first (wrong sources or stale knowledge defeat any prompt iteration), invest in prompting second (few-shot examples, explicit instructions, constraints — often highest ROI), model selection third (more capable models solve what prompting can't but cost more and are slower), and hyperparameter tuning last.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Claim from Laurie Voss

View full analysis →Watch the original ↗

Principle · Money

Traces reveal every decision the agent made

Without traces all you see is 'I gave it a prompt and I got a report'; with traces you see every step and where exactly it went wrong. SDKs like Claude Agent SDK and OpenAI's already emit LLM and tool call spans, and OpenTelemetry/OpenInference means you don't write custom instrumentation per SDK.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Claim from Laurie Voss

View full analysis →Watch the original ↗

Creator perspective · Money

Rubric criteria must be specific and observable, derived from error analysis

Don't say 'a good response' in your rubric because that is an aspiration, not a criterion. Instead, list exactly what makes a report actionable and not actionable. Every criterion should be specific and observable — something a human looking at the report could say yes or no to. Each rubric criterion should match something you observed going wrong in your trace analysis; your error analysis is what tells you what criteria to write. Don't come up with rubric criteria from whole cloth; get them from reading your traces and noting the specific wrong things your agent did. Specific criteria produce consistent judgments, while vague criteria produce coin flips.

AI Engineer · From Vibes to Production: Evaluating and Shipping AI Agents That Work 101 — Laurie Voss, Arize AI

Claim from Laurie Voss

View full analysis →Watch the original ↗

Creator perspective · Money

When transcript and audio disagree, trust the audio

The source advises that when a voice agent's transcript and audio disagree, trust the audio, and that when a transcript shows a successful confirmation, play the audio to verify the confirmation actually occurred.

AI Engineer · The Transcript Looked Fine. The Call Wasn't. — Debugging Voice Agents, Arize

Claim from AI Engineer

View full analysis →Watch the original ↗

Principle · Money

Rubric guiding principles

Grade only what was asked and not any extraneous criterion; keep criteria isolated so errors don't cascade from one to another; always look at the ground truth screenshots because agents often overconfidently claim they did something they didn't; and separate what the agent could control from what it could not, since the browser is an environment the agent doesn't always control.

AI Engineer · Your LLM Judge Is a Confident Liar: Building Better Verifiers — Browserbase

Claim from Miguel Pagano

View full analysis →Watch the original ↗

Creator perspective · Money

Loops: repeat a task until told to stop or a timer expires

A loop repeats a task nonstop until you cancel it or a timer you set expires — more creative and adaptable than goals. Examples: run tests every minute, check the deploy and ping when healthy (or check every five minutes and act, e.g., run an additional script), tell me when my favorite video game is available and text me, go through Slack filing customer complaints as Linear tickets, babysit a PR and fix comments until there are none. Loops are incredibly reusable; you could split a complex workflow into two loops; regular reports fit schedule better.