LLM Digest
Subscribe

Agent Builder Foundations

Mechanisms, math intuition, evidence, and application

View as JSON

Agent Builder Foundations

Mechanisms behind reliable agents

Durable explanations for builders who want to understand why a prompt, retrieval setup, tool call, memory system, or eval behaves the way it does. Each page separates paper-backed mechanisms, benchmark results, field reports, and LLM Digest synthesis.

13 concepts·7 clusters·evidence-tiered

Prompting and instruction following

Retrieval and grounding

Tool use and agents

Memory and context

  • Why does adding more context sometimes hurt an agent?

    Most production agent failures trace back to unmanaged context, not weak reasoning — treating context as a lifecycle to architect, ingest, scope, anticipate, and compact (not a log to truncate when it gets too big) is…

    5 evidence tiers
  • Can you trust what your agent remembers?

    Persistent agent memory is a write-once, replay-many attack surface — 2026 benchmarks show attackers can forge an agent's own reasoning history or plant poisoned facts through routine content like email, both with high…

    4 evidence tiers

Evals and reliability

  • Does a high benchmark score predict production reliability?

    A benchmark pass rate measures one round of scoring against a fixed task set — 2026 evidence shows agent-optimization gains that look real on that single round can fail to transfer or even regress once the agent is…

    9 evidence tiers
  • Can you trust an LLM-as-judge score?

    An LLM judge is a measurement instrument with its own biases, not ground truth — validate it the same way you validate the agent it grades, and for agent trajectories with checkable evidence, consider a deterministic…

    6 evidence tiers

Cost, latency, and operations

  • How does speculative decoding speed up LLM inference?

    Speculative decoding drafts several tokens cheaply, then verifies them in one parallel pass through the target model — cutting decode latency without changing the output distribution, as long as the draft's guesses are…

    6 evidence tiers

Safety and control