All 24 articles, sorted alphabetically
Agent Prompt Architecture in Depth
A 2500-word walkthrough of agent prompt architecture: system prompt, tools, memory, response format, safety, few-shot, CoT, budget, versioning, portab…
Read article →Context packing architecture
Deep-dive on context packing: salience scoring, summarization, retrieval augment, working memory, priority ordering, budget.
Read article →Dynamic few-shot prompting
Deep-dive on dynamic few-shot prompting, where the demonstrations shown to a model are selected per request from an exemplar store rather than frozen …
Read article →Prompt Evaluation Architecture in Depth
A 2500-word walkthrough of prompt evaluation: golden sets, runner, metrics, regression gates, CI, cost/latency, adversarial, rollout gates, curation.
Read article →LLM hallucination guardrails architecture
Deep-dive on layered hallucination guardrails for LLM systems: why fabrication is structural and trust asymmetric, grounding via retrieval, the cite-o…
Read article →Least-to-most prompting architecture
Deep-dive on least-to-most prompting: decomposing a hard problem into an ordered easiest-to-hardest subproblem queue, passing each committed subanswer…
Read article →Meta-prompting -- using an LLM to write and improve prompts
Deep-dive on meta-prompting: using an LLM to generate and refine prompts, the optimization loop (generate/evaluate/refine), the meta-prompt, automatic…
Read article →Multimodal prompting architecture
Deep-dive on prompting with images: how pixels become tokens via resize and tiling, low vs high detail cost, image placement and interleaving, the cro…
Read article →Prompt caching architecture
Deep-dive on LLM prompt caching: storing the deterministic KV attention state of a stable prompt prefix so later requests prefill only the new tail, t…
Read article →Prompt compression architecture — segment budgets, compression cascades, and cache-aware assembly
Deep-dive on compressing LLM prompts at scale: segment inventory and per-class token budgets, relevance scoring, the extractive-abstractive-pruning ca…
Read article →Prompt-injection defense architecture
Deep-dive on defending LLM applications against prompt injection: why no prompt can stop it, how to separate trusted instructions from untrusted conte…
Read article →Prompt Pipeline Architecture in Depth
A 2500-word walkthrough of a production prompt pipeline: templates, variables, compiler, structured outputs, model router, validation, registry, eval,…
Read article →Prompt registry architecture
Deep-dive on prompt registries: immutable prompt versions with variable schemas, eval-gated promotion through environment labels, cached runtime resol…
Read article →ReAct
How ReAct interleaves reasoning and tool calls, enabling agents that think and act iteratively.
Read article →Reflexion architecture
Deep-dive on the Reflexion pattern: how an LLM agent improves within a single session through verbal reinforcement — writing natural-language self-cri…
Read article →Prompt routing architecture
Deep-dive on prompt routing: intent classifier, policy engine, LLM registry, selection, fallback ladder, quality gate, and A/B.
Read article →Self-Consistency
How self-consistency samples multiple CoT traces and takes the most common answer, boosting reliability.
Read article →Semantic routing architecture
Deep-dive on semantic routing for LLM apps: embedding queries, labeled route centroids, cosine similarity and confidence thresholds, LLM fallback for …
Read article →Skeleton-of-Thought prompting architecture
Deep-dive on Skeleton-of-Thought: a cheap skeleton call that lists an answer's key points, parallel expander calls that flesh…
Read article →Step-back prompting architecture
Deep-dive on step-back prompting: the two-stage abstraction-then-reasoning pipeline, using the derived principle as a retrieval key, self-verification…
Read article →Structured Output Architecture for LLMs in Depth
A 2500-word walkthrough of structured output: schema, provider features (function calling, JSON mode), constrained decoding, validation, retry, stream…
Read article →Tree of Thoughts
How Tree of Thoughts (ToT) explores multiple reasoning paths in parallel with backtracking, and when it beats linear CoT.
Read article →Prompt Delimiters
Separate instructions from data. Reduces injection + confusion.
Read article →Prompt Template Libraries
Reusable prompt templates. Variables. Composition. Trade-offs.
Read article →