Sign-In
Cart
Done Is a Function You Write: Eval-Driven Development for LLMs You Can Actually Trust
Paperback
Series: Build Agents You Can Trust
Publisher: Independently Published
Published: Jun 23 2026
Pages: 140
Weight: 0.43
Height: 0.30 Width: 6.00 Depth: 9.00
Language: English
The new unit test, for AI that thinks.
Your large language model crushed the benchmark. Then it shipped, and the support tickets started. Sound familiar? A nondeterministic system can be brilliant in the demo and wrong at scale, and you cannot regression-test it the way you test real code. The number you were steering by was measuring someone else's problem.
Done Is a Function You Write is the field manual for LLM evaluation, the discipline that quietly became the center of AI engineering. Its core move is a reframe: done is not a vibe or a leaderboard rank, it is a function you write. Once you can write that check, you can delegate to the machine everything that passes it.
Eval-driven development, from your first failing check to a suite that guards every deploy:
- Done as a function replaces the vibe check and the leaderboard rank with an executable definition of correct, treating evals as test-driven development for generative AI.
- Trace-first AI testing starts where the real failures live, your own production traces, so the suite measures your problem instead of a public benchmark's.
- LLM-as-judge alignment calibrates a machine grader against human labels and teaches you to spot and debug judge bias before it decides a release.
- Contamination defense shows why a verified score can drop thirty-five points overnight, and how to keep AI model evaluation honest when benchmarks leak into training data.
- Capability versus reliability separates what a model can do once from what it does every time, the distinction that decides what is safe to ship.
- The regression gate assembles a suite that blocks silent regressions on every deploy, the new unit test wired into your pipeline.
This is hands-on AI engineering, not theory. Read it and you will write the checks that decide what a thinking machine is allowed to do, delegate exactly as much as those checks prove safe, and ship AI you can stand behind. That is the scarce skill no model upgrade erases.
For engineers, data scientists, and applied-AI teams building with large language models and agentic AI, past can the model do it and stuck on can I trust it enough to ship. Part of the Build Agents You Can Trust series, in The Verifier's Library.
Also from
Vale, Ravi
It Doesn't Remember You: Why AI Forgets You, Invents Facts, and How to Finally Trust It
Vale, Ravi
Paperback
USB-C for Agents: AI Agent Tool Use, Function Calling, and MCP Servers Done Right
Vale, Ravi
Paperback
The Verifier's Advantage: How Leaders Verify AI Work and Turn Trust Into Advantage
Vale, Ravi
Paperback
The Context Window Is a Budget: Context Engineering for Reliable AI Agents and Long-Horizon Work
Vale, Ravi
Paperback
Agents You Can Leave Running: How to Engineer Agentic Loops You Can Trust Unattended
Vale, Ravi
Paperback
Claude Code: The Fleet: Long-Horizon Autonomy, Multi-Agent Systems, and Production Scale
Vale, Ravi
Paperback
Claude Code: The Reliability Playbook: Real Projects, Patterns, and Bounded Autonomy
Vale, Ravi
Paperback
Stop Prompting, Start Designing: Build No-Code AI Agents That Finish the Job Without You
Vale, Ravi
Paperback
The Second Opinion on AI: How to Catch the Confident-Wrong AI Answer in Medicine, Law, and Science
Vale, Ravi
Paperback
The 15x Problem: How AI Inference Cost Became 85% of the Bill, and the Controls That Tame It
Vale, Ravi
Paperback
The Inversion: First Principles for Building Software When Intelligence Is Cheap and Trust Is Not
Vale, Ravi
Paperback
The Verification Stack: Specs, Gates, Judges, and Escalation for AI Output That Has to Be Right
Vale, Ravi
Paperback
The Delegation Ladder: Engineering Human Oversight of Autonomous Work, from Ten Minutes to a Week
Vale, Ravi
Paperback
Also in
Programming
Interactive Theorem Proving and Program Development: Coq'art: The Calculus of Inductive Constructions
Castéran, Pierre
Bertot, Yves
Hardcover
Seven Databases in Seven Weeks: A Guide to Modern Databases and the Nosql Movement
Perkins, Luc
Redmond, Eric
Wilson, Jim
Paperback
The Legend of Zelda(tm) Tears of the Kingdom - The Complete Official Guide: Collector's Edition
Piggyback
Hardcover
Python Crash Course, 3rd Edition: A Hands-On, Project-Based Introduction to Programming
Matthes, Eric
Paperback
Crisis Engineering: Time-Tested Tools for Turning Chaos Into Clarity
Dickerson, Mikey
Nitze, Marina
Weaver, Matthew
Paperback
Vibe Coding: Building Production-Grade Software with Genai, Chat, Agents, and Beyond
Yegge, Steve
Kim, Gene
Paperback
Accelerate: The Science of Lean Software and DevOps: Building and Scaling High Performing Technology Organizations
Kim, Gene
Forsgren Phd, Nicole
Humble, Jez
Paperback
Embedded Systems with ARM Cortex-M Microcontrollers in Assembly Language and C: Fourth Edition
Zhu, Yifeng
Paperback
The Legend of Zelda(tm) Tears of the Kingdom - The Complete Official Guide: Standard Edition
Piggyback
Paperback
I Have an App Idea: The Essential Guide to Building an App Without Tech Skills
Spann, Amanda
Paperback
Fundamentals of Software Architecture: A Modern Engineering Approach
Richards, Mark
Ford, Neal
Paperback
AI Projects with Raspberry Pi: High-Performance Artificial Intelligence for Robotics, Security, Home Automation, and Vision
Jepson, Brian
Hattersley, Lucy
Paperback
The Manager's Path: A Guide for Tech Leaders Navigating Growth and Change
Fournier, Camille
Paperback
Make: Electronics: Learning by Discovery: A Hands-On Primer for the New Electronics Enthusiast
Platt, Charles
Paperback
The Devops Handbook, 2nd Edition: How to Create World-Class Agility, Reliability, & Security in Technology Organizations
Debois, Patrick
Kim, Gene
Humble, Jez
Paperback
Building Applications with AI Agents: Designing and Implementing Multiagent Systems
Albada, Michael
Paperback
The Developer's Guide to AI: A Field Guide for the Working Developer
Thompson, Danny
Orshalick, Jacob
Reghunadh, Jerry M.
Paperback
Cracking the Coding Interview: 189 Programming Questions and Solutions
McDowell, Gayle Laakmann
Paperback
The New AI Cold War: Liberty vs. Tyranny in the Age of Machine Empires
Maginnis, Ltc Robert L.
Paperback
Learning Web Design: A Beginner's Guide to Html, Css, Javascript, and Web Images
Robbins, Jennifer
Paperback
The Staff Engineer's Path: A Guide for Individual Contributors Navigating Growth and Change
Reilly, Tanya
Paperback
Software Architecture: The Hard Parts: Modern Trade-Off Analyses for Distributed Architectures
Sadalage, Pramod
Ford, Neal
Richards, Mark
Paperback
SQL QuickStart Guide: The Simplified Beginner's Guide to Managing, Analyzing, and Manipulating Data With SQL
Shields, Walter
Hardcover
Linux Basics for Hackers, 2nd Edition: Getting Started with Networking, Scripting, and Security in Kali
Occupytheweb
Paperback
The Official Raspberry Pi Handbook 2026: Astounding Projects with Raspberry Pi Computers
Makers of Raspberry Pi Official Magazine, The
Paperback
The Pragmatic Programmer: Your Journey to Mastery, 20th Anniversary Edition
Thomas, David
Hunt, Andrew
Hardcover
Generative AI Design Patterns: Solutions to Common Challenges When Building Genai Agents and Applications
Hapke, Hannes
Lakshmanan, Valliappa
Paperback
Forecasting: Principles and Practice, the Pythonic Way
Hyndman, Rob J.
Athanasopoulos, George
Paperback
Observability Engineering: Achieving Production Excellence
Fong-Jones, Liz
Miranda, George
Majors, Charity
Paperback
Head First Design Patterns: Building Extensible and Maintainable Object-Oriented Software
Robson, Elisabeth
Freeman, Eric
Paperback
Frictionless: 7 Steps to Remove Barriers, Unlock Value, and Outpace Your Competition in the AI Era
Forsgren, Nicole
Noda, Abi
Paperback
The Return on AI: From Promise to Profit in the Age of Intelligent Business
Mittal, Ashwin
Sawhney, Mohanbir
Paperback
Arduino Programming for Beginners: A Comprehensive Beginner's Guide to Learn the Realms of Arduino Programming from A-Z
Protosmith, Ada
Paperback
Building AI-Powered Products: The Essential Guide to AI and Genai Product Management
Nika, Marily
Paperback
Concrete Mathematics: A Foundation for Computer Science
Patashnik, Oren
Knuth, Donald
Graham, Ronald
Hardcover
Grokking Algorithms, Second Edition: An Illustrated Guide for Programmers and Other Curious People
Bhargava, Aditya Y.
Paperback
Debugging: The 9 Indispensable Rules for Finding Even the Most Elusive Software and Hardware Problems
Agans, David J.
Paperback
Learning Generative AI Tools for Excel: Speed Up Your Everyday Tasks with Microsoft Excel, Copilot, Chatgpt, and Beyond
Duca, Angelica Lo
Paperback
Learning Domain-Driven Design: Aligning Software Architecture and Business Strategy
Khononov, Vlad
Paperback
Computer Science from Scratch: Building Interpreters, Art, Emulators and ML in Python
Kopec, David
Paperback
The Software Architect Elevator: Redefining the Architect's Role in the Digital Enterprise
Hohpe, Gregor
Paperback
Python Programming for Young Coders: A Hands-On, Project-Based Introduction to Coding for Beginners, Kids, and Teens
Pandey, Anand
Paperback
Learning Php, MySQL & JavaScript: A Step-By-Step Guide to Creating Dynamic Websites
Nixon, Robin
Paperback
Software Engineering at Google: Lessons Learned from Programming Over Time
Manshreck, Tom
Wright, Hyrum
Winters, Titus
Paperback
Living a Jewish Life, Revised and Updated: Jewish Traditions, Customs, and Values for Today's Families
Cooper, Howard
Diamant, Anita
Paperback
Pro C# 10 with .Net 6: Foundational Principles and Practices in Programming
Troelsen, Andrew
Japikse, Phil
Paperback
Prompt Engineering for Llms: The Art and Science of Building Large Language Model-Based Applications
Ziegler, Albert
Berryman, John
Paperback
Articulating Design Decisions: Communicate with Stakeholders, Keep Your Sanity, and Deliver the Best User Experience
Greever, Tom
Paperback
Adobe Photoshop, 2nd Edition: A Complete Course and Compendium of Features
Laskevitch, Stephen
Paperback
Kubernetes in Action, Second Edition: Deploying and Managing Containers and Cloud-Native Applications
Luksa, Marko
Conner, Kevin
Paperback
Spies, Lies, and Algorithms: The History and Future of American Intelligence
Zegart, Amy B.
Paperback
Site Reliability Engineering: How Google Runs Production Systems
Murphy, Niall Richard
Jones, Chris
Beyer, Betsy
Paperback
Ruined by Design: How Designers Destroyed the World, and What We Can Do to Fix It
Monteiro, Mike
Paperback
Electronic Music and Sound Design - Theory and Practice with Max 9 - Volume 1 (Fifth Edition)
Maurizio, Giri
Cipriani, Alessandro
Paperback
Designing AI Interfaces: Design Principles for Creative and Autonomous AI
Macfadyen, Louise
Paperback