Skip to content
Index / $11

Production GenAI Series

Complete series index: engineering LLM platforms that survive production — agent tool discovery at scale, grounded citations, eval-driven model selection, fine-tuned classifiers under extreme imbalance, and trustworthy AI front ends

Date
Jul 6, 2026
Runtime
3 min · 650 words
Tags
genai, llm, ai-agents
Slot
$11
Contents

Start Here

This series documents the engineering patterns behind production GenAI systems I've built in enterprise consulting work — technique-first and generalized, the way a conference talk would teach them. The through-line: an LLM feature becomes a platform the moment someone else's workflow depends on it, and the patterns that get you there (tool discovery, grounding, evals, human-in-the-loop) are the actual engineering.

Context: multi-provider LLM platform work (Anthropic, OpenAI/Azure, Google/Vertex, AWS Bedrock), agent tooling over the Model Context Protocol, applied transformer fine-tuning, and the front ends that make it client-ready. All examples are generic and representative; no client or proprietary detail.

Prerequisites: comfort with APIs and Python/TypeScript; no prior LLM platform experience assumed.


Reading Order

1. How Do You Give an AI Agent 75 Tools Without Wrecking Its Judgment?

What: Tool-selection collapse is real: dump 75+ tools into a context window and the agent's judgment degrades. The fix is a tool-RAG discovery surface — list → search → describe → call — plus a sandboxed code-composition mode, with the reliability layer (idempotency, confirm-guards, error envelopes, circuit breakers) that makes agent actions safe to retry.

Why it matters: every serious agent deployment hits this wall; the discovery-surface pattern is the difference between a demo and a platform.

Read →


2. How Do You Make an LLM Cite Its Sources — and Prove It?

What: Provider-native citation grounding: model output tied to page-anchored source quotes rendered as click-to-source footnotes, an evidence-first pipeline (gather → prompt → validate → score), knowledge-graph validation via JSON-LD/RDF + W3C SHACL, and the honest "no evidence" state instead of fabricated citations.

Why it matters: trust is the product. A wrong answer with a checkable source beats a right answer with none.

Read →


3. How Do You Pick Which Model to Ship?

What: The offline eval harness — frontier vs. baseline models measured on latency, token cost, and output quality with automated hallucination scoring — and how a ship/no-ship decision actually gets structured, including the LLM-as-judge pitfalls.

Why it matters: model selection by vibes is how teams ship regressions; eval infrastructure is what the strongest AI teams hire for.

Read →


4. How Do You Lift a Classifier's Hardest Level From 4% to 77%?

What: A hierarchical DeBERTa/RoBERTa classifier over a 4-level, 137-path taxonomy — one fine-tuned model per branch, parents constraining children — and the class-imbalance toolkit (class weights, focal loss, branch oversampling) that lifted deepest-level accuracy from ~4% to 77%+. Plus the MLOps loop: CI-triggered SageMaker fine-tuning, ECS serving, symlink-rollout model artifacts.

Why it matters: the fine-tuning-under-imbalance playbook transfers to any deep-taxonomy problem, and the equation everyone cites (FL(pt)=αt(1pt)γlogptFL(p_t) = -\alpha_t(1-p_t)^\gamma \log p_t) finally gets a plain-English treatment.

Read →


5. What Does a Trustworthy AI Analyst UI Actually Look Like?

What: The client-ready React 19/TypeScript front end: SSE streaming chat with inline charts, click-to-source citation markers, constrained tool-calling with stable chart ids (editing beats regenerating), web-search-grounded autofill with human accept/reject review, and export gates with human-in-the-loop approval.

Why it matters: AI UIs fail on trust, not on polish — the streaming state machine and the provenance contract are the hard parts.

Read →


Series Status

PostTopicStatus
1. Agent tool discoveryMCP · tool-RAG · reliability patterns✅ Published
2. Grounded citationsGateway · XAI · SHACL validation✅ Published
3. Eval harnessModel selection · hallucination scoring✅ Published
4. Hierarchical classifierFine-tuning · imbalance · MLOps✅ Published
5. Trustworthy AI UIReact 19 · streaming · HITL✅ Published

Related: the applied-ML research side of this portfolio lives in The Memorial Bot: The Complete Story — behavioral cloning and style-constrained RL on a single machine.

EOF · $11 · 650 words · Daniel Plas Rivera
Share[X][LinkedIn]