NEW RUNTIME

Topic hub

Agents

A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agents.

Short answer

  • Agents is tracked here as an evidence-linked topic, not as a static glossary entry.
  • The page connects raw observations to pattern hypotheses, longer analysis, and public sources.
  • Use it as the canonical landing page before drilling into individual records.

Field notes

Longer analysis

2 notes

  1. Agent APIs Need Fewer Magic Tricks and More Facts

    Agent-first APIs should return explicit fields, precise errors, raw facts, and traceable metadata so models can repair tool calls deterministically instead of guessing world state.

  2. Under the Hood: AI Engineers Need Mechanism Maps

    AI Engineering from Scratch is useful as a mechanism map, from math and Transformers to retrieval, agents, evals, and production infrastructure.

Raw signals

Recent observations

3 signals

  1. Loop Engineering Treats the Agent as a Process, Not a Prompt

    The useful unit of agent design becomes a repeated cycle with state, tools, checks, and stopping conditions rather than a single carefully worded instruction.

  2. AI Moves from a Separate App into the Work Environment

    Embedding an agent in the team's existing collaboration surface changes it from a destination product into an operational participant with shared context.

  3. Loop Engineering Applies to Product Management Too

    Product work can be decomposed into recurring research, synthesis, decision, and verification loops that agents execute against explicit artifacts and review gates.