Table of Contents

The Agentic Programming Language

A Programmer's Guide to the New Paradigm — how the concepts, patterns, and principles of classical software engineering translate into the age of LLM-powered agents.

17 chapters · 7 parts
Intro
A Translation Guide for Software Engineers Entering the Agentic Paradigm

Maps classical software engineering concepts to their agentic equivalents, giving developers a mental framework to cross the paradigm boundary without losing their footing.

6 sections
Part I The New Syntax
Ch 1
When Natural Language Became Code

Traces the moment natural language crossed from documentation into executable code, and what that shift demands from programmers who learned to think in types and functions.

7 sections
Ch 2
Model, Prompt, and Context as a Complete System

Explores model, prompt, and context as an inseparable system — change any one element and the behavior of the whole changes with it.

7 sections
Part II The New Memory
Ch 3
RAM, Attention, and the Token Budget

Treats the context window as working memory: finite, precious, and the primary resource an agentic programmer must learn to allocate deliberately.

7 sections
Ch 4
When Memory Becomes Noise

Diagnoses the slow degradation of context quality — how stale history, contradictory instructions, and accumulated noise silently erode agent reliability over time.

7 sections
Part III The New Control Flow
Ch 5
The if/else That Understands Intent

Replaces hard-coded conditionals with meaning-aware routing that dispatches tasks based on intent, turning ambiguous natural-language input into deterministic execution paths.

8 sections
Ch 6
The for Loop That Applies Judgment

Decomposes a task into concurrent workstreams where each sub-agent applies independent judgment, then synthesizes the results into a coherent whole.

9 sections
Ch 7
The while Loop That Knows When to Stop

Dissects the plan–act–observe cycle that drives autonomous agents, and identifies the stopping conditions that separate reliable agents from runaway loops.

7 sections
Part IV The New Architecture
Ch 8
From God Prompt to Composable Architecture

Refactors the monolithic god-prompt into injected, composable components — separating persona, tools, memory, and task specification into clean, testable interfaces.

7 sections
Ch 9
Why Fifty-Year-Old Rules Still Apply

Applies SRP, OCP, LSP, ISP, and DIP to agent system design, showing these fifty-year-old rules are more relevant, not less, when working at the semantic layer.

8 sections
Ch 10
Gang of Four Meets the LLM Runtime

Translates Observer, Strategy, Chain-of-Responsibility, and other classic patterns into multi-agent workflow architectures — familiar structures in a new medium.

7 sections
Part V The New Engineering Practices
Ch 11
Eval-Driven Development and the New Test Suite

Adapts test-driven development to the probabilistic domain, writing evals before prompts to define what good output looks like before the first token is generated.

5 sections
Ch 12
Behavior as the Contract, Scenarios as the Specification

Uses Gherkin-style Given/When/Then scenarios as executable agent specifications, making behavior testable, auditable, and readable by non-engineers.

7 sections
Ch 13
Debug the Prompt, Not the Model

Reframes debugging for non-deterministic systems, tracing agent failures back to ambiguous instructions, missing context, and misaligned goals rather than code bugs.

7 sections
Part VI The New Security and Observability
Ch 14
Structural Separation Between Instructions and Data

Treats user-supplied data as an untrusted attack surface and builds structural barriers that prevent injected instructions from hijacking agent behavior.

6 sections
Ch 15
You Cannot Debug What You Cannot See

Instruments agent systems with traces, spans, and structured logs so that reasoning chains become inspectable and failures become diagnosable before they reach production.

6 sections
Part VII The Future
Ch 16
The Theoretical Foundation of the Prompt as Program

Examines whether the prompt–tool–loop system is Turing complete, and what theoretical guarantees — and hard limits — that confers on programs written in natural language.

5 sections
Ch 17
The 2026 Programmer's Job Description

Defines the emerging role of the programmer as orchestrator: someone who composes, evaluates, and governs a team of specialized AI agents toward a shared goal.

6 sections + Appendix A