Guides

Hands-on tutorials and explainers for working with AI: prompting, tools, workflows, APIs, and the concepts behind them, with working examples and honest trade-offs.

17 posts

Subscribe via RSS

Comparing AI agents vs workflows by asking who owns each runtime branch decision before any code is written.

Guides • Sep 24, 2026 •12 min read

AI Agents vs Workflows? Count Your Branches First

AI agents vs workflows: enumerate your branches, price each runtime decision point, and promote to an agent only when the branches can't be known ahead.

#ai-agents #ai-workflows +3

Entity deduplication collapses millions of near-duplicate supplier pairs into one trusted record per vendor.

Guides • Sep 20, 2026 •12 min read

Entity Deduplication From 50 Million Pairs to Thousands

Entity deduplication for builders: normalize, hash, and block before embeddings, calibrate thresholds without labels, and account for cost at every stage.

#entity-resolution #deduplication +4

Data center servers running large language model workloads, where LLM prompt caching cuts the cost of repeated input tokens.

Guides • Sep 16, 2026 •10 min read

LLM Prompt Caching Can Cut Input Costs Up to 90%

LLM prompt caching can cut agent loop input costs up to 90%. Compare OpenAI, Anthropic, Gemini, and Bedrock on TTLs, breakpoints, and real savings math.

#prompt-caching #llm-costs +3

AI text watermarking embeds a keyed statistical signal into machine-generated text so provenance can be verified later, the core technique this Python guide builds and stress-tests.

Guides • Sep 06, 2026 •12 min read

AI Text Watermarking in Python, Three Families Tested

Hands-on AI text watermarking in Python: how the three families work, what survives copy-paste, edits, and paraphrasing, and when to watermark or detect.

#text-watermarking #ai-detection +3

A prompt dependency graph maps prompts and their consuming components as coupled nodes so teams can see exactly what a prompt change touches before retesting.

Guides • Sep 03, 2026 •11 min read

Prompt Dependency Graphs That Shrink Your Retest Set

Build a prompt dependency graph to compute the blast radius of any prompt change and rerun only the evals your multi-prompt LLM system needs.

#llm-evaluation #prompt-engineering +3

NLP vs LLM vs RAG branches routed by task shape and cost, the decision framework that determines where document workloads land.

Guides • Aug 29, 2026 •12 min read

NLP vs LLM vs RAG, Routed by Task Shape and Cost

NLP vs LLM vs RAG is a routing decision set by task shape. Compare the cost math, failure modes, and an LLM-fallback pattern before picking a model.

#classical-nlp #rag +4

An AI text detector built on a locally fine-tuned language model scores writing samples to separate machine-generated text from human writing.

Guides • Aug 20, 2026 •11 min read

Build an AI Text Detector, Then Test If It Can Ship

Build an AI text detector with small local models, stress-test it on short and human-edited text, and use the error rates to decide if it ships.

#ai-text-detection #local-models +3

LLM context window management keeps a growing agent conversation within the limited space a model can actually read and reason over.

Guides • Aug 18, 2026 •11 min read

LLM Context Window Management With a Token Budget

Learn LLM context window management with a token budget ledger, a stepwise compression ladder, and the prompt cache trap that punishes trimming.

#context-windows #token-budget +4

Structured output enforcement with local LLMs balances JSON schema compliance against throughput and production reliability.

Guides • Aug 09, 2026 •12 min read

Structured Output Local LLM Tactics That Survive Production

Structured output local LLM enforcement means choosing JSON mode, grammar decoding, or tool-calling. Each trades latency, throughput, and reliability.

#structured-output #local-llm +4

Controlling reasoning effort in LLM APIs means setting explicit parameters that cap how many tokens a model spends on internal chain-of-thought before producing visible output.

Guides • Jul 28, 2026 •13 min read

Control Reasoning Effort LLM APIs in Production

Control reasoning effort LLM APIs across OpenAI, DeepSeek, and Anthropic. Practical routing rules to cut cost and latency without losing accuracy.

#llm-engineering #api-optimization +3

AI-driven browser agent performing web automation tasks on a computer screen, representing the production challenges of shipping LLM browser agents.

Guides • Jul 26, 2026 •12 min read

Shipping LLM Browser Agents Without Breaking Production

LLM browser agents look easy in demos. Shipping one means defaulting to APIs, containing prompt injection, and budgeting for unpredictable per-step costs.

#browser-agents #dom-automation +3

Apple Silicon Mac running large language model inference locally through the MLX framework and unified memory.

Guides • Jul 21, 2026 •13 min read

Run AI Models Locally on Mac With MLX and Nativ

Run AI models locally on Mac with MLX and Nativ. A trade-off framework for when on-device inference beats APIs on cost, privacy, and latency.

#mlx #apple-silicon +4