Sign in Subscribe

Igor Bobriakov

The Prompt Is a Hyperparameter

Manual prompt engineering is optimization without an objective function. DSPy reframes prompts as hyperparameters, programs as signatures, and optimization as a first-class operation — and in doing so, shifts the core skill from prompt craft to metric design.

Text-First Extraction Is an Epistemic Error

RAG pipelines degrade in a pattern consistent enough to be structural: a text extractor destroys semantic layout before a single token reaches the model. The failure is not in the retriever. It is at the extraction boundary — where two-dimensional structure gets linearized into noise.

Durable Execution: Why Python while Loops Are Not Production Ready

A while loop is a state machine whose state lives in RAM. One pod eviction and every completed step is gone. Production agentic workflows require exactly-once semantics — a guarantee that must be encoded in the architecture, not hoped for through retry logic.

Your Company's "Agentic Surface Area": The New Metric for Competitiveness

Your CEO asks: "How much of our operation is AI-powered?" The uncomfortable part is that the question sounds simple and usually has no clean answer. Teams can name pilots, copilots, and workflows, but not how much decision-making has actually moved to agents. Security teams have "attack surface

The API Is the New Command Line: A Manifesto for Agentic Design

The command line gave humans a grammar for commanding machines. The API gives agents the same grammar — at scale, in parallel, without a human in the loop. Every design decision downstream flows from whether you've internalized that shift.

Dumb Core, Smart Edge: Agentic Design

Many agentic systems I've watched fail in production had the same shape: intelligence concentrated at the center, where it was hard to test, replace, or reason about. The orchestrator was doing too much — routing requests, holding domain knowledge, managing memory, selecting tools, and shaping outputs, all at once.

Every AI Agent is a Liar, a Slacker, and a Thief

The industry is currently stuck in the Prototype Trap. We can build a magical AI demo in a weekend, but we spend six months failing to make it reliable in production. Why? Because we assume the model wants to help us. It doesn't. By default, every AI agent is a liar, a slacker, and a thief.

The Golden Dataset: If You Lose Your Code but Keep Your Data, You Survive

Every AI system has exactly one irreplaceable artifact, and it is not the model. Your golden dataset — the curated triples of input, expected output, and ground truth — is the only thing that survives a complete rewrite. Lose it, and you are starting from zero.

The Probabilistic State Machine: Why Linear Chains Fail

In data engineering, we build linear pipelines. In AI engineering, linear pipelines are fatal. If you have three steps, each with 90% accuracy, your system is only 72% reliable. To fix this, we must abandon the Chain and embrace the Probabilistic State Machine.

Intelligence Arbitrage: The Economics of Routing Thought

The default LLM architecture is economically incoherent: one expensive model for every task. Intelligence Arbitrage treats model selection as a routing problem and turns the spread between task difficulty and model capability into operating leverage.