Daily Bytes of
AI Engineering

Bite-sized insights for building production AI systems. Expert guides, real-world patterns, and practical engineering wisdom.

AI Bytes

Practical insights for production AI systems

LLM Engineering

Query anonymization for RAG bias mitigation

How to strip names, roles, and demographics from queries before retrieval to reduce RAG bias. The redaction pipeline and the 3 leakage traps to avoid.

RAG Guardrails Data Processing+2 more

Read Article

9 min

AI Engineering in Practice

pip vs uv vs poetry for Python AI services

Which Python dependency manager should you use for production agent services in 2026? The install speed, lockfile story, and Docker build times compared.

Python AI Agents Production AI+2 more

Read Article

9 min

AI Engineering in Practice

Retry patterns for LLM API errors in production

How to build retry logic that handles rate limits, timeouts, and transient failures without burning money. The backoff rules and the 3 errors you must not retry.

AI Agents Error Handling Resilience+2 more

Read Article

8 min

LLM Engineering

Choosing the LLM judge for evaluation pipelines

How to pick the LLM that grades your LLM. The cost-quality tradeoffs, the calibration check, and why a weaker judge is sometimes the right call.

Evaluation LLM Metrics+2 more

Read Article

8 min

LLM Engineering

Ground truth vs relevancy in RAG evaluation

Why ground truth and relevancy measure different things in RAG evals. When to use each, how to build both datasets, and the 2 metrics that matter most.

RAG Evaluation Metrics+2 more

Read Article

9 min

LLM Engineering

Pydantic output structuring for RAG agent plans

How to use Pydantic models to force your RAG planner LLM to return structured steps. The schema, the retry loop, and why plain JSON prompts break in production.

RAG Pydantic Structured Output+2 more

Read Article

8 min

LLM Engineering

Hallucination testing for RAG pipelines

How to test a RAG pipeline for hallucinations systematically. Adversarial prompts, the out-of-scope set, and the metric that catches confabulation.

RAG Evaluation LLM+2 more

Read Article

8 min

LLM Engineering

Testing and evaluating RAG pipelines end to end

How to test a RAG pipeline like real software. Unit, integration, and eval tests that catch regressions before they ship. The 3-layer test strategy.

RAG Evaluation Production AI+2 more

Read Article

8 min

LLM Engineering

Fact-checking RAG answers: grounding with verification

How to fact-check RAG answers with a second LLM pass that verifies every claim against the retrieved context. The prompt, the rejection rule, and the loop.

RAG LLM Evaluation+2 more

Read Article

8 min

Previous 1 2...15 Next →

Your Instructor

Built by Param Harrison

Cofounder of AEOsome.com and Chief Mentor at learnwithparam.com with 15+ years building production systems. I've trained 100+ engineers on AI engineering - these programs distill what actually works into structured paths you can follow at your own pace.

@learnwithparam GitHub LinkedIn

Ready to go deeper?

Go beyond articles. Build production AI systems with hands-on workshops and our intensive AI Bootcamp.

Explore AI Bootcamp Browse Workshops

FAQ

Frequently asked questions

Cadence, authors, topics, and how to follow along.

What does the learnwithparam blog cover?

The blog covers production AI engineering, with a tilt toward RAG, agentic systems, and the operational layer that turns demos into services. New posts ship roughly daily and lean on patterns the mentors actually use at work, not the framework-of-the-week. Every post includes a working code snippet, a mermaid diagram, and a Monday-morning checklist you can act on.

Browse all posts

How often are new posts published?

A new post lands roughly every day. The cadence is intentional: small, high-signal posts that solve one specific production problem each, instead of an occasional 5000-word omnibus. If you want every post in your inbox, the newsletter signup is at the bottom of every post page.

Who writes the blog posts?

Three mentors. Param Harrison (chief mentor) writes core AI engineering and RAG fundamentals. Ahmed Aleryani writes complex agentic systems and production infrastructure. Asep Bagja Priandana writes polyglot programming and tooling. Each post links to its author. They all share a tight engineer-to-engineer voice with no fluff and no AI slop.

About Param About Ahmed About Asep

How do I follow new posts?

Subscribe to the newsletter (signup form on every post page) to get new posts in your inbox. The blog also publishes an RSS feed at /rss.xml. For social, follow Param on Twitter and LinkedIn. Posts are tagged by category so you can filter for RAG, agents, tooling, or whichever topic matters to you.

Daily Bytes of
AI Engineering

Bite-sized insights for building production AI systems. Expert guides, real-world patterns, and practical engineering wisdom.

AI Bytes

Practical insights for production AI systems

LLM Engineering

Query anonymization for RAG bias mitigation

How to strip names, roles, and demographics from queries before retrieval to reduce RAG bias. The redaction pipeline and the 3 leakage traps to avoid.

RAG Guardrails Data Processing+2 more

Read Article

9 min

AI Engineering in Practice

pip vs uv vs poetry for Python AI services

Which Python dependency manager should you use for production agent services in 2026? The install speed, lockfile story, and Docker build times compared.

Python AI Agents Production AI+2 more

Read Article

9 min

AI Engineering in Practice

Retry patterns for LLM API errors in production

How to build retry logic that handles rate limits, timeouts, and transient failures without burning money. The backoff rules and the 3 errors you must not retry.

AI Agents Error Handling Resilience+2 more

Read Article

8 min

LLM Engineering

Choosing the LLM judge for evaluation pipelines

How to pick the LLM that grades your LLM. The cost-quality tradeoffs, the calibration check, and why a weaker judge is sometimes the right call.

Evaluation LLM Metrics+2 more

Read Article

8 min

LLM Engineering

Ground truth vs relevancy in RAG evaluation

Why ground truth and relevancy measure different things in RAG evals. When to use each, how to build both datasets, and the 2 metrics that matter most.

RAG Evaluation Metrics+2 more

Read Article

9 min

LLM Engineering

Pydantic output structuring for RAG agent plans

How to use Pydantic models to force your RAG planner LLM to return structured steps. The schema, the retry loop, and why plain JSON prompts break in production.

RAG Pydantic Structured Output+2 more

Read Article

8 min

LLM Engineering

Hallucination testing for RAG pipelines

How to test a RAG pipeline for hallucinations systematically. Adversarial prompts, the out-of-scope set, and the metric that catches confabulation.

RAG Evaluation LLM+2 more

Read Article

8 min

LLM Engineering

Testing and evaluating RAG pipelines end to end

How to test a RAG pipeline like real software. Unit, integration, and eval tests that catch regressions before they ship. The 3-layer test strategy.

RAG Evaluation Production AI+2 more

Read Article

8 min

LLM Engineering

Fact-checking RAG answers: grounding with verification

How to fact-check RAG answers with a second LLM pass that verifies every claim against the retrieved context. The prompt, the rejection rule, and the loop.

RAG LLM Evaluation+2 more

Read Article

8 min

Previous 1 2...15 Next →

Your Instructor

Built by Param Harrison

@learnwithparam GitHub LinkedIn

Ready to go deeper?

Go beyond articles. Build production AI systems with hands-on workshops and our intensive AI Bootcamp.

Explore AI Bootcamp Browse Workshops

FAQ

Frequently asked questions

Cadence, authors, topics, and how to follow along.

What does the learnwithparam blog cover?

Browse all posts

How often are new posts published?

Who writes the blog posts?

About Param About Ahmed About Asep

How do I follow new posts?

Daily Bytes ofAI Engineering

AI Bytes

Query anonymization for RAG bias mitigation

pip vs uv vs poetry for Python AI services

Retry patterns for LLM API errors in production

Choosing the LLM judge for evaluation pipelines

Ground truth vs relevancy in RAG evaluation

Pydantic output structuring for RAG agent plans

Hallucination testing for RAG pipelines

Testing and evaluating RAG pipelines end to end

Fact-checking RAG answers: grounding with verification

Weekly Bytes of AI

Built by Param Harrison

Ready to go deeper?

Frequently asked questions

Daily Bytes ofAI Engineering

AI Bytes

Query anonymization for RAG bias mitigation

pip vs uv vs poetry for Python AI services

Retry patterns for LLM API errors in production

Choosing the LLM judge for evaluation pipelines

Ground truth vs relevancy in RAG evaluation

Pydantic output structuring for RAG agent plans

Hallucination testing for RAG pipelines

Testing and evaluating RAG pipelines end to end

Fact-checking RAG answers: grounding with verification

Weekly Bytes of AI

Built by Param Harrison

Ready to go deeper?

Frequently asked questions

Daily Bytes of
AI Engineering

Daily Bytes of
AI Engineering