# ai-that-works/ai-that-works

🦄 ai that works - every tuesday 10 AM PST

Repository: https://github.com/ai-that-works/ai-that-works
Canonical: https://ross.abutalabs.com/products/ai-that-works
Homepage: https://www.boundaryml.com/podcast
Language: TypeScript
License Family: other
Last push: 2026-08-24T16:30:28+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 37
- inputs: {"age_days": 518, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1912, forks 141 (observed 2026-08-28T04:05:53.434289+00:00)

## What it is
A weekly live-streamed series (Tuesdays 10 AM PST) by the BAML and HumanLayer creators covering production AI engineering through live coding, Q&A, and episode demo code. The repository hosts code examples and harnesses from episodes on topics like model deprecation testing, agent scaling, and AI coding benchmarks.

## Use cases
- learn production AI engineering patterns
- how to handle LLM model deprecation safely
- evaluate new LLM models against regression budgets
- scale AI agents in parallel with A/B testing
- learn context engineering for coding agents
- find live coding sessions on building AI apps
- examples of eval harnesses for LLM apps

## When to choose
- you want to learn production AI engineering from experienced practitioners
- you need practical patterns for model swaps, evals, and agent infrastructure
- you enjoy live coding and community Q&A formats
- you use or are curious about BAML and agentic coding tools

## When to avoid
- you need a production-ready library rather than educational content
- you want a stable, documented API with a license
- you are not interested in AI/LLM engineering topics
- you cannot attend live sessions and prefer self-paced structured courses

## Facets
- artifact type: learning-resource
- maturity: active
- function: developer-tools, prompt-engineering, agent-framework, llm-inference, testing
- domain: large-language-models, developer-tools, tutorials, education
- platform: cross-platform, python
- tags: live-coding, webinar-series, context-engineering, ai-engineering, podcast, baml, production-ai, evals, ai-agents, typescript

## Member repositories
- ai-that-works/ai-that-works (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:53.434289+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:10:38.112675+00:00, confidence not recorded.
  - readme: https://github.com/ai-that-works/ai-that-works (fetched 2026-08-28T04:05:53.434289+00:00, sha 41685b1a9b58)
  - homepage: https://www.boundaryml.com/podcast (fetched 2026-08-29T10:50:16.734004+00:00, sha b4d57b2cbeca)
  - site_page: https://boundaryml.com/podcast/2026-08-25-software-factory-design-patterns (fetched 2026-08-29T10:50:16.749515+00:00, sha dec4b986a330)
  - site_page: https://boundaryml.com/podcast/2026-08-18-syncs-and-ab-testing-200-agents (fetched 2026-08-29T10:50:16.752713+00:00, sha ccb73386c291)
  - site_page: https://boundaryml.com/podcast/2026-08-11-unconference-recap (fetched 2026-08-29T10:50:16.756065+00:00, sha 63e149d1406f)
  - site_page: https://boundaryml.com/podcast/2026-08-04-slop-code-bench (fetched 2026-08-29T10:50:16.758931+00:00, sha 475c061005aa)
  - site_page: https://boundaryml.com/podcast/2026-07-28-your-model-is-already-obsolete (fetched 2026-08-29T10:50:16.761832+00:00, sha 8988d11e6233)
  - site_page: https://boundaryml.com/podcast/2026-07-21-no-vibes-july (fetched 2026-08-29T10:50:16.764815+00:00, sha 60a212f97dd2)
- Data as of 2026-08-30T08:39:29.467469+00:00.