AI-Wiki

Tag: observability

6 items with this tag.

  • Jun 26, 2026

    Langfuse

    • langfuse
    • agent-harness
    • observability
    • tracing
    • llm-tooling
    • open-source
    • evals
    • type/entity
    • kind/product
  • Jun 26, 2026

    LiteLLM

    • litellm
    • agent-harness
    • model-routing
    • observability
    • llm-tooling
    • open-source
    • type/entity
    • kind/library
  • Jun 26, 2026

    From Demo to Production: Why Agentic AI Systems Fail — and How to Fix Them

    • agent-harness
    • agentic-engineering
    • progressive-disclosure
    • skills
    • tool-search-tool
    • context-engineering
    • agent-orchestration
    • observability
    • mcp
    • langfuse
    • litellm
    • infoq
    • type/source
    • kind/video
  • Jun 22, 2026

    Harness engineering: leveraging Codex in an agent-first world

    • openai
    • codex
    • agent-harness
    • agentic-engineering
    • agents-md
    • progressive-disclosure
    • observability
    • doc-gardening
    • repository-as-system-of-record
    • agent-legibility
    • layered-architecture
    • ralph-wiggum-loop
    • type/source
    • kind/article
  • May 14, 2026

    Evals 101 — Doug Guthrie, Braintrust

    • evals
    • ai-evaluation
    • llm-as-judge
    • observability
    • agent-development-lifecycle
    • agent-harness
    • braintrust
    • ai-engineer-worlds-fair
    • flywheel-effect
    • human-in-the-loop
    • online-scoring
    • offline-evals
    • type/source
    • kind/video
  • May 14, 2026

    AI Evaluations Clearly Explained in 50 Minutes (Real Example) — Hamel Husain on Peter Yang's podcast

    • evals
    • ai-evaluation
    • llm-as-judge
    • observability
    • binary-pass-fail
    • agreement-metric
    • true-positive-rate
    • true-negative-rate
    • error-analysis
    • axial-coding
    • spreadsheet-evals
    • hamel-husain
    • peter-yang
    • agent-development-lifecycle
    • agent-harness
    • ai-product-management
    • type/source
    • kind/video

Created with Quartz v0.1.0 © 2026

187 sources · 135 entities · 39 concepts · 5 threads · 4 syntheses

  • GitHub