00 / Indexbardak.ai

Ivan Bardak

Evidence-based notes on AI agents, enterprise architecture and AI transformation.

Read the posts About

Agents GraphRAG Architecture AI transformation

Agents and platforms
MCP tools, delegated access, reliability in production
GraphRAG and retrieval
When graphs beat vectors, and what they cost
AI transformation
What the studies, surveys and real cases show
Read the latest field notes

01 / Start hereThree reading paths

Start here

Agents and platforms

Getting AI agents into production: tools, identity, reliability.

GraphRAG and retrieval

When knowledge graphs beat vector search, and what they cost.

AI transformation

What studies, surveys and real cases say about the effect of AI.

More notes

View all

Oct 29, 202613 min read

Agentic AI from demo to production: what the evidence says about the architecture

Most agent pilots stall on the architecture around the model, not the model. What surveys, published incidents and reliability benchmarks show about tools, identity, retrieval, reversibility and measurement, and the six questions I ask before anything ships.

Ivan Bardak

Oct 29, 20266 min read

GraphRAG vs RAG: what the evidence actually says

GraphRAG wins on multi-hop and whole-corpus questions and loses on plain lookups, at a higher cost. What three studies show, how much weight each deserves, and a decision rule you can use.

Ivan Bardak

Oct 29, 20266 min read

Five questions before you build a knowledge graph for RAG

A knowledge graph can make RAG better at connecting facts, or just slower and more expensive. Five questions, each tied to published evidence, that tell you which one you are about to get.

Ivan Bardak

Oct 29, 20266 min read

A GraphRAG business case, done the evidence-based way

Most GraphRAG business cases are a vendor benchmark and a hopeful percentage. A structure that survives a CFO's questions: six steps of evidence-based management, a cost model from measured token counts, and a value range instead of one number.

Ivan Bardak

Oct 29, 20267 min read

AI code migrations: what Airbnb, Google and Amazon actually reported

The headline numbers travel well: 1.5 years in 6 weeks, 50% less time, 4,500 developer-years saved. What each company actually measured, how much weight it deserves, and a decision rule for your next migration.

Ivan Bardak

Oct 29, 20266 min read

Does AI make developers faster? What the controlled studies say

55% faster, 21% faster, 19% slower, roughly even: the controlled studies disagree for good reasons. What each one measured, how much weight it deserves, and what to put in an AI transformation plan instead of a single number.

Ivan Bardak