Tag: engineering

Showing 1-3 of 3

Jul 02, 20266 min readAgent PlaybookIntermediate

Why production agents fail at scale: guardrails, enterprise data, and resilient orchestration

Rafael Lopes argues scaling agents breaks on engineering, not LLM limits: build deterministic guardrails, connectors for unstructured enterprise data, and resilient orchestration.

agents scaling production-ai engineering orchestration

+3 more

TutorialsUnited States

Open

Apr 02, 20267 min readAgent PlaybookIntermediate240 min build

Why PostHog started with an MCP server before building a custom AI agent

Lessons from two years at PostHog: validate agent demand by exposing a narrow, authenticated MCP server (34% of AI-created dashboards used it) before building a full agent.

ai-agents product MCP server startup engineering

+1 more

validation

TutorialsUnited States

Open

Mar 03, 20269 min readAgent PlaybookIntermediate90 min build

Design patterns to address the Input Paradox, information asymmetry, and token costs in AI workflows

A concise guide to three AI-system failures—Input Paradox, Information Asymmetry, and token costs—and practical fixes: 3–5 field captures, progressive prompts, and token gates.

AI systems agents prompting engineering product

+2 more

costs operational-design