<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI Product Engineer Wiki</title><description>Free, visual guide to becoming an AI product engineer: product discovery, LLM trade-offs, AI UX, prototyping, evals, shipping, safety and unit economics.</description><link>https://ai-product-engineer-wiki.netlify.app/</link><language>en</language><item><title>Project: AI writing assistant inside an existing app</title><link>https://ai-product-engineer-wiki.netlify.app/projects/ai-writing-assistant/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects/ai-writing-assistant/</guid><description>Add an AI writing assistant to an existing app with editable suggestions, accept and reject controls, and tracking of what users keep.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>projects</category><category>beginner</category></item><item><title>Project: Smart catalog search with RAG and citations</title><link>https://ai-product-engineer-wiki.netlify.app/projects/catalog-search-with-rag/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects/catalog-search-with-rag/</guid><description>Build natural-language search over a product catalog with retrieval, cited answers and a relevance eval set that proves it beats keyword search.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>projects</category><category>intermediate</category></item><item><title>Project: AI onboarding agent with approvals</title><link>https://ai-product-engineer-wiki.netlify.app/projects/onboarding-agent-with-approvals/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects/onboarding-agent-with-approvals/</guid><description>Build an agent that sets up a new account through tools, asks for approval before risky actions, and logs every step it takes.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>projects</category><category>intermediate</category></item><item><title>Project: Feedback-driven feature: mine edits, improve prompts</title><link>https://ai-product-engineer-wiki.netlify.app/projects/feedback-driven-prompt-improvement/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects/feedback-driven-prompt-improvement/</guid><description>Capture how users edit AI output, mine the edits for patterns, improve the prompt, and measure the lift with evals and product metrics.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>projects</category><category>advanced</category></item><item><title>Project: A/B-tested AI feature with a cost-per-success dashboard</title><link>https://ai-product-engineer-wiki.netlify.app/projects/ab-tested-ai-feature/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects/ab-tested-ai-feature/</guid><description>Ship an AI feature behind flags, A/B test two variants with analytics events, and build a dashboard of cost per successful task.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>projects</category><category>advanced</category></item><item><title>Project: Capstone: a paid AI SaaS feature end to end</title><link>https://ai-product-engineer-wiki.netlify.app/projects/capstone-paid-ai-saas-feature/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects/capstone-paid-ai-saas-feature/</guid><description>Take a paid AI feature from spec to launch with UX, evals, staged rollout, pricing, a metrics review and a written case study.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>projects</category><category>expert</category></item><item><title>What is an AI product engineer?</title><link>https://ai-product-engineer-wiki.netlify.app/start-here/what-is-an-ai-product-engineer/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/start-here/what-is-an-ai-product-engineer/</guid><description>An AI product engineer owns an AI feature end to end, from the user problem and UX to evals, launch metrics and cost. What the role covers and why it exists.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>start-here</category><category>beginner</category></item><item><title>AI product engineer vs AI, ML, product and full-stack roles</title><link>https://ai-product-engineer-wiki.netlify.app/start-here/ai-product-engineer-vs-other-roles/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/start-here/ai-product-engineer-vs-other-roles/</guid><description>How the AI product engineer differs from AI engineers, ML engineers, product managers and full-stack engineers, and the path into the role from each.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>start-here</category><category>beginner</category></item><item><title>The AI product lifecycle, from problem to iteration</title><link>https://ai-product-engineer-wiki.netlify.app/start-here/the-ai-product-lifecycle/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/start-here/the-ai-product-lifecycle/</guid><description>The six-step loop every AI feature goes through, from user problem to shipping and learning, with the artifact and exit criterion for each step.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>start-here</category><category>beginner</category></item><item><title>Choose your path: 3, 6 or 12-month plans</title><link>https://ai-product-engineer-wiki.netlify.app/start-here/choose-your-path/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/start-here/choose-your-path/</guid><description>Pick a 3, 6 or 12-month plan to become an AI product engineer, check the prerequisites, and set up a weekly routine you can keep.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>start-here</category><category>beginner</category></item><item><title>Problem discovery for AI features</title><link>https://ai-product-engineer-wiki.netlify.app/product-foundations/problem-discovery-for-ai-features/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/product-foundations/problem-discovery-for-ai-features/</guid><description>Find AI feature ideas worth building by starting from frequent, painful user jobs instead of model capabilities, using data you already have.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>product-foundations</category><category>beginner</category></item><item><title>User interviews for engineers</title><link>https://ai-product-engineer-wiki.netlify.app/product-foundations/user-interviews-for-engineers/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/product-foundations/user-interviews-for-engineers/</guid><description>Run short, useful user interviews as an engineer, from recruiting to asking about real behavior, avoiding leading questions and turning notes into decisions.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>product-foundations</category><category>beginner</category></item><item><title>Jobs-to-be-done for AI products</title><link>https://ai-product-engineer-wiki.netlify.app/product-foundations/jobs-to-be-done-for-ai-products/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/product-foundations/jobs-to-be-done-for-ai-products/</guid><description>Use jobs-to-be-done to frame AI features around the progress users want to make, write job statements, and spot where AI changes the job.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>product-foundations</category><category>beginner</category></item><item><title>Writing a one-page AI feature spec</title><link>https://ai-product-engineer-wiki.netlify.app/product-foundations/writing-a-one-page-ai-feature-spec/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/product-foundations/writing-a-one-page-ai-feature-spec/</guid><description>Write a one-page spec for an AI feature covering the user and job, success metric, quality bar, failure states, cost estimate and the non-AI alternative.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>product-foundations</category><category>beginner</category></item><item><title>Defining success metrics before you build</title><link>https://ai-product-engineer-wiki.netlify.app/product-foundations/defining-success-metrics/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/product-foundations/defining-success-metrics/</guid><description>Choose success metrics for an AI feature before you build it, from task success and adoption to guardrails and cost per success, with code to compute them.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>product-foundations</category><category>beginner</category></item><item><title>When not to use AI</title><link>https://ai-product-engineer-wiki.netlify.app/product-foundations/when-not-to-use-ai/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/product-foundations/when-not-to-use-ai/</guid><description>Recognize problems where AI is the wrong tool, where rules, search, templates or better UX solve it more cheaply, reliably and safely than a model.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>product-foundations</category><category>beginner</category></item><item><title>What LLMs are good and bad at</title><link>https://ai-product-engineer-wiki.netlify.app/llm-capabilities/what-llms-are-good-and-bad-at/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/llm-capabilities/what-llms-are-good-and-bad-at/</guid><description>A product-focused map of LLM strengths and weaknesses, from language tasks to tool use, and where models still fail, so you scope features realistically.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>llm-capabilities</category><category>intermediate</category></item><item><title>Latency budgets and perceived speed</title><link>https://ai-product-engineer-wiki.netlify.app/llm-capabilities/latency-budgets-and-perceived-speed/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/llm-capabilities/latency-budgets-and-perceived-speed/</guid><description>Set latency budgets for AI features, measure time to first token and total time, and use streaming and UX to make responses feel fast.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>llm-capabilities</category><category>intermediate</category></item><item><title>Estimating cost per task</title><link>https://ai-product-engineer-wiki.netlify.app/llm-capabilities/estimating-cost-per-task/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/llm-capabilities/estimating-cost-per-task/</guid><description>Estimate what an AI feature costs per task and per successful task, from token counts and model prices to retries and caching, with a reusable cost calculator.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>llm-capabilities</category><category>intermediate</category></item><item><title>Context windows, retrieval and memory trade-offs</title><link>https://ai-product-engineer-wiki.netlify.app/llm-capabilities/context-windows-retrieval-and-memory/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/llm-capabilities/context-windows-retrieval-and-memory/</guid><description>Decide what goes into the model&apos;s context, from long context versus retrieval to conversation memory, and the cost, latency and quality trade-offs of each.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>llm-capabilities</category><category>intermediate</category></item><item><title>Choosing a model: a decision framework</title><link>https://ai-product-engineer-wiki.netlify.app/llm-capabilities/choosing-a-model/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/llm-capabilities/choosing-a-model/</guid><description>Choose the right model for each AI feature with a repeatable framework that weighs quality on your evals, latency, cost per success, limits and effort settings.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>llm-capabilities</category><category>intermediate</category></item><item><title>Build, buy or fine-tune</title><link>https://ai-product-engineer-wiki.netlify.app/llm-capabilities/build-buy-or-fine-tune/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/llm-capabilities/build-buy-or-fine-tune/</guid><description>Decide whether to build on a model API, buy an existing AI product, or fine-tune a model, with the costs, risks and evidence each option needs.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>llm-capabilities</category><category>intermediate</category></item><item><title>Streaming and loading states</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/streaming-and-loading-states/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/streaming-and-loading-states/</guid><description>Design streaming responses and loading states for AI features, from when to stream to skeletons, progress, stop buttons and handling a stream that ends early.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Editable outputs and undo</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/editable-outputs-and-undo/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/editable-outputs-and-undo/</guid><description>Make AI output editable and reversible with inline editing, accept and reject controls, version history and undo, so users stay in control of the result.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Citations and showing sources</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/citations-and-showing-sources/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/citations-and-showing-sources/</guid><description>Show where AI answers come from with citations, quoted passages and source links that let users verify claims, built with the Claude citations feature.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Communicating confidence and uncertainty</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/communicating-confidence-and-uncertainty/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/communicating-confidence-and-uncertainty/</guid><description>Communicate uncertainty in AI features honestly: when to hedge, when to abstain, and why raw confidence scores usually confuse users more than they help.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Human-in-the-loop and approval flows</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/human-in-the-loop-and-approval-flows/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/human-in-the-loop-and-approval-flows/</guid><description>Design approval flows for AI actions, deciding which actions need a human, how to present a proposed action clearly, and how to keep approvals fast.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Error, refusal and empty states</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/error-refusal-and-empty-states/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/error-refusal-and-empty-states/</guid><description>Design the unhappy paths of AI features, from API errors and refusals to truncated answers, empty results and timeouts, with copy and recovery for each.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Onboarding and setting expectations</title><link>https://ai-product-engineer-wiki.netlify.app/ai-ux/onboarding-and-setting-expectations/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/ai-ux/onboarding-and-setting-expectations/</guid><description>Introduce AI features so users know what they can do, where they fall short and how to get good results, without long tutorials.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>ai-ux</category><category>intermediate</category></item><item><title>Prompt-first prototyping</title><link>https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/prompt-first-prototyping/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/prompt-first-prototyping/</guid><description>Prototype an AI feature with nothing but prompts and real inputs before writing app code, and learn whether the core idea works in an afternoon.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>rapid-prototyping</category><category>intermediate</category></item><item><title>Wizard-of-Oz tests for AI features</title><link>https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/wizard-of-oz-tests/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/wizard-of-oz-tests/</guid><description>Test an AI feature with real users before building it by having a human play the AI, and learn what people actually need from the experience.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>rapid-prototyping</category><category>intermediate</category></item><item><title>A day-one demo in Next.js</title><link>https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/day-one-demo-in-nextjs/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/day-one-demo-in-nextjs/</guid><description>Build a working AI feature demo in one day with Next.js and the Anthropic SDK, with a server route, streaming UI and handling for every stop reason.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>rapid-prototyping</category><category>intermediate</category></item><item><title>Structured outputs and tool calls in prototypes</title><link>https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/structured-outputs-and-tool-calls/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/structured-outputs-and-tool-calls/</guid><description>Get reliable JSON and actions from a model in prototypes, with schema-based structured outputs, simple tool calls and validation of what the model returns.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>rapid-prototyping</category><category>intermediate</category></item><item><title>Turning a prototype into a spec</title><link>https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/turning-a-prototype-into-a-spec/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/rapid-prototyping/turning-a-prototype-into-a-spec/</guid><description>Turn what a prototype taught you into a buildable spec, with findings, decisions, the first eval cases and the open risks before engineering starts.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>rapid-prototyping</category><category>intermediate</category></item><item><title>Why evals are product metrics</title><link>https://ai-product-engineer-wiki.netlify.app/evals/why-evals-are-product-metrics/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/evals/why-evals-are-product-metrics/</guid><description>Evals measure how often an AI feature is good enough for users. Learn why they belong with product metrics, not only in an ML notebook.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>evals</category><category>advanced</category></item><item><title>Building golden datasets from real user tasks</title><link>https://ai-product-engineer-wiki.netlify.app/evals/golden-datasets-from-real-user-tasks/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/evals/golden-datasets-from-real-user-tasks/</guid><description>Build a golden dataset from real user tasks, covering sampling, coverage of hard cases, writing reference answers, privacy, and keeping the set fresh.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>evals</category><category>advanced</category></item><item><title>Rubrics and human grading</title><link>https://ai-product-engineer-wiki.netlify.app/evals/rubrics-and-human-grading/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/evals/rubrics-and-human-grading/</guid><description>Write rubrics that make AI output gradeable, run human grading sessions, and measure agreement between graders before trusting the scores.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>evals</category><category>advanced</category></item><item><title>LLM-as-judge: design and calibration</title><link>https://ai-product-engineer-wiki.netlify.app/evals/llm-as-judge/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/evals/llm-as-judge/</guid><description>Use a model to grade AI output at scale, with judge prompts, rubrics, calibration against human grades, and the biases to guard against.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>evals</category><category>advanced</category></item><item><title>Regression eval suites in CI</title><link>https://ai-product-engineer-wiki.netlify.app/evals/regression-eval-suites-in-ci/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/evals/regression-eval-suites-in-ci/</guid><description>Run evals in CI so prompt and model changes can&apos;t silently make an AI feature worse, with thresholds, flakiness handling, cost control and reporting.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>evals</category><category>advanced</category></item><item><title>Linking eval scores to business KPIs</title><link>https://ai-product-engineer-wiki.netlify.app/evals/linking-eval-scores-to-business-kpis/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/evals/linking-eval-scores-to-business-kpis/</guid><description>Connect offline eval scores to the business metrics they should move, check that the link holds, and report AI quality in terms leadership understands.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>evals</category><category>advanced</category></item><item><title>Feature flags and staged rollouts for AI</title><link>https://ai-product-engineer-wiki.netlify.app/shipping/feature-flags-and-staged-rollouts/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/shipping/feature-flags-and-staged-rollouts/</guid><description>Ship AI features gradually with feature flags, covering staged exposure, kill switches, flagging prompts and models, and rollback plans that work in minutes.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>shipping</category><category>advanced</category></item><item><title>A/B testing AI features</title><link>https://ai-product-engineer-wiki.netlify.app/shipping/ab-testing-ai-features/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/shipping/ab-testing-ai-features/</guid><description>Run A/B tests on AI features, from choosing metrics and sample sizes to novelty effects, cost as a metric, and reading results when output quality varies.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>shipping</category><category>advanced</category></item><item><title>Product analytics events for AI features</title><link>https://ai-product-engineer-wiki.netlify.app/shipping/product-analytics-events-for-ai/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/shipping/product-analytics-events-for-ai/</guid><description>Instrument AI features with product analytics, with an event schema for requests, outcomes, edits and costs, and the questions it lets you answer.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>shipping</category><category>advanced</category></item><item><title>Capturing feedback: thumbs, edits and retries</title><link>https://ai-product-engineer-wiki.netlify.app/shipping/capturing-feedback/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/shipping/capturing-feedback/</guid><description>Collect useful feedback on AI output, from explicit ratings to implicit signals in edits and retries, and turn both into improvements.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>shipping</category><category>advanced</category></item><item><title>Tracing and observability for LLM calls</title><link>https://ai-product-engineer-wiki.netlify.app/shipping/tracing-and-observability/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/shipping/tracing-and-observability/</guid><description>Trace every LLM call in production, from what to record to linking traces with users and outcomes, reviewing traces, and monitoring cost and latency.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>shipping</category><category>advanced</category></item><item><title>The iteration loop: from feedback to prompt changes</title><link>https://ai-product-engineer-wiki.netlify.app/shipping/the-iteration-loop/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/shipping/the-iteration-loop/</guid><description>Turn production feedback into measured improvements by finding failure patterns, changing prompts or design, verifying with evals and shipping safely.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>shipping</category><category>advanced</category></item><item><title>Prompt injection and tool-use risks</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/prompt-injection-and-tool-use-risks/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/prompt-injection-and-tool-use-risks/</guid><description>Understand prompt injection and the risks of giving AI features tools, including attack paths, realistic threat models and defenses that limit the damage.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Data privacy and retention</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/data-privacy-and-retention/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/data-privacy-and-retention/</guid><description>Handle user data responsibly in AI features, including what you send to model providers, retention, consent, regulated data and telling users plainly.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Abuse, misuse and rate limiting</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/abuse-misuse-and-rate-limiting/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/abuse-misuse-and-rate-limiting/</guid><description>Protect AI features from abuse with rate limits, quotas, misuse detection and cost-attack defenses, and handle users who push a feature beyond its purpose.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Guardrails for inputs, outputs and actions</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/guardrails-for-inputs-outputs-and-actions/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/guardrails-for-inputs-outputs-and-actions/</guid><description>Add guardrails around AI features with input checks, output validation, action limits and refusal handling, and keep them from blocking real users.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Unit economics of AI features</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/unit-economics-of-ai-features/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/unit-economics-of-ai-features/</guid><description>Work out the unit economics of an AI feature, from cost per successful task and value per user to margins by plan and the levers that improve them.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Pricing AI features</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/pricing-ai-features/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/pricing-ai-features/</guid><description>Price AI features with bundling, usage-based pricing, credits and tiers, protecting margins from heavy users and communicating limits fairly.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Cost dashboards and budgets</title><link>https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/cost-dashboards-and-budgets/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/trust-safety-economics/cost-dashboards-and-budgets/</guid><description>Track and control AI spend with cost dashboards by feature, model and customer, budgets and alerts, and spend reviewed as a product metric.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>trust-safety-economics</category><category>expert</category></item><item><title>Building an AI product portfolio</title><link>https://ai-product-engineer-wiki.netlify.app/projects-and-career/building-an-ai-product-portfolio/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects-and-career/building-an-ai-product-portfolio/</guid><description>Build a portfolio that shows AI product engineering skill, choosing projects, showing evidence, and presenting outcomes rather than just code.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>projects-and-career</category><category>expert</category></item><item><title>Writing a product case study</title><link>https://ai-product-engineer-wiki.netlify.app/projects-and-career/writing-a-product-case-study/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects-and-career/writing-a-product-case-study/</guid><description>Write a case study of an AI feature that shows how you think, covering context, problem, decisions and trade-offs, evals, results and what you would change.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>projects-and-career</category><category>expert</category></item><item><title>Passing AI product sense interviews</title><link>https://ai-product-engineer-wiki.netlify.app/projects-and-career/ai-product-sense-interviews/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects-and-career/ai-product-sense-interviews/</guid><description>Prepare for AI product sense interviews with a framework for open-ended questions, evaluating AI features, trade-off questions and practice prompts.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>projects-and-career</category><category>expert</category></item><item><title>Career paths and leveling</title><link>https://ai-product-engineer-wiki.netlify.app/projects-and-career/career-paths-and-leveling/</link><guid isPermaLink="true">https://ai-product-engineer-wiki.netlify.app/projects-and-career/career-paths-and-leveling/</guid><description>Plan your career as an AI product engineer, including what changes from mid-level to senior and staff, adjacent paths, and how to grow scope and impact.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>projects-and-career</category><category>expert</category></item></channel></rss>