High Agency Pydantic > VC Backed Frameworks, with Jason Liu
The Instructor creator on why validation beats vibes for reliability.
Open latent.space →
Building & Product
Podcast
Guide
Article
Article
Article
Guide
Article
Article
Article
Article
Article
Article
Article
Article
Tool
Tool
Tool
How do I stop my AI feature from making things up in front of customers?
Models hallucinate because they are trained to always answer; your job is to constrain them, not to hope. The biggest wins in order: ground answers in your own retrieved data with citations (RAG), force structured outputs so responses are validated before display, let the model say "I don't know", and add guardrails plus human review on high-stakes actions. Air Canada and Cursor both learned publicly that you own whatever your bot says, so treat reliability as a launch requirement, not a polish item.
Go deeper
17 resources.
LLM Hallucinations: Understand and Tackle AI's Most Persistent Quirk
The clearest end-to-end explainer of why hallucinations happen and the layered defences that work.
Open lakera.ai →How to Reduce LLM Hallucinations
Separates factuality from faithfulness errors and matches each to its fix.
Open getzep.com →How to Reduce LLM Hallucinations: 7 Proven Strategies
A prioritized playbook: grounding and abstention first, verification where errors are expensive.
Open futureagi.com →8 Ways to Prevent LLM Hallucinations in Production
Production-focused checklist including the stat that layered guardrails cut hallucination rates 71-89%.
Open airbyte.com →Structured model outputs (OpenAI docs)
Schema-guaranteed responses kill an entire category of made-up fields and invalid values.
Open developers.openai.com →The guide to structured outputs and function calling with LLMs
Connects structured output techniques across providers in one practical reference.
Open agenta.ai →Guardrails AI and NVIDIA NeMo Guardrails: A Comprehensive Approach to AI Safety
How the two main open-source guardrail approaches compose into one defence stack.
Open guardrailsai.com →Moffatt v. Air Canada: A Misrepresentation by an AI Chatbot
The legal analysis of the ruling, in plain enough language for a founder.
Open mccarthy.ca →Cursor AI support bot hallucinated its own company policy
A hot AI startup's own bot invented a policy and triggered cancellations; the cautionary tale of 2025.
Open theregister.com →A customer support AI went rogue, and it's a warning for every company
The business-impact view of the Cursor incident, including the labelling fix that followed.
Open fortune.com →AI Incident Database: Cursor support bot invents login policy
A neutral incident record, and a database worth browsing before you ship anything customer-facing.
Open incidentdatabase.ai →Case Study of Air Canada's Chatbot Misleading on Bereavement Fares
Breaks the failure into design decisions you can audit your own bot against.
Open envive.ai →Air Canada Held Responsible for Chatbot's Hallucinations
Short, shareable summary for convincing your team that reliability is a legal issue too.
Open aibusiness.com →Instructor: structured outputs for LLMs
Validate and auto-retry model outputs against a schema; 6M downloads a month for a reason.
Open github.com →NeMo Guardrails
Open-source programmable rails: topic control, fact-checking, and jailbreak detection.
Open github.com →Guardrails AI
A hub of pre-built validators that intercept bad inputs and outputs before users see them.
Open github.com →More in AI in Your Product
- Should my startup add AI features, and which ones actually matter to users? 20 →
- How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)? 19 →
- How much does it cost to run AI features, and how do I keep costs sane? 19 →
- Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in? 17 →
- How do I test whether my AI feature actually works before launch (evals, in plain terms)? 18 →
- Prompt engineering, RAG, or fine-tuning: which one does my product actually need? 18 →
- How do I design AI features people trust (chat vs buttons, streaming, showing the work)? 18 →
- What is my moat if I'm building on someone else's model? 19 →
- Should I put an AI agent in my product, or is a simple workflow enough? 18 →
- Is it safe to send customer data to AI APIs, and what about privacy laws like India's DPDP Act? 18 →
- How should I price AI features: per seat, per use, or per outcome? 17 →
- My AI feature is live. How do I monitor it and make it better with real usage? 18 →
Also in Starting Up
The same ground, over in Build the product, our Starting Up track.
eChai Partner Brands
