Airflow

500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIn

Sep 9, 2026 · 20:25

Ajay Prakash, senior staff software engineer at LinkedIn, explains how Contextual Agent Playbooks make coding agents reliable at enterprise scale, turning an on-call alert into a mitigated incident in minutes. Early vibe coding failed: agents trained on open source hallucinated across LinkedIn's 1,000 internal repos. An internal MCP server with code search, docs, and Jira fell short: tribal knowledge sat in stale wikis, context overloaded, and sessions started from scratch. Playbooks, instructions published as tools, work when self-contained and split into small referenced pieces, and agents open PRs to refresh stale ones. Since MCP degrades past 30 or 40 tools, everything surfaces behind three meta tools: search, get schema, execute, now 1,300 tools, 600 playbooks, 8,000 daily users.

12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer

Jul 3, 2025 · 17:06

Dex Horthy, founder of HumanLayer, presents the 12-Factor Agents framework for building reliable LLM-powered applications, arguing that production-grade agents are primarily deterministic software with targeted LLM steps rather than fully autonomous loops. He distills patterns: own prompts and context windows, treat tools as JSON and code, use small focused agents with three to ten steps, contact humans via tool calls. Horthy emphasizes context engineering—LLMs are pure functions—and shows how to compact errors, unify state, and add pause/resume via APIs. He shares a DevOps agent that became a bash script, and advocates for outer-loop agents. The framework, which gained 4,000 GitHub stars in two months, treats agents as stateless reducers that meet users on any channel, with engineers controlling the inner loop of token and control flow.

How agents broke app-level infrastructure - Evan Boyle

Jun 3, 2025 · 13:32

Evan Boyle, founder of GenSX, argues that LLM-powered agents have broken assumptions about app-level infrastructure, as p1 latency jumps from milliseconds to seconds and workflows run minutes to hours. He explains that traditional serverless providers timeout after 5 minutes, lack native streaming, and force brittle Rube Goldberg machines on top of queues like SQS or tools like Airflow. Boyle presents an open-source library that separates API and compute layers using Redis streams for resumability, enabling users to refresh pages or navigate away without losing progress. He demonstrates components with built-in retries, caching, and tracing, and a workflow that automates Hacker News analysis. Key architectural lessons include starting simple but planning for long-running agents, keeping compute and API planes separate, and leaning on Redis for resumability.