Method

Guardrails

Input/output safety and policy filters, PII masking, prompt-injection defense.

33 cases from 28 companies apply Guardrails. 6 were checked in an online A/B test; 11 report results in production.

Typical tasks: Build an assistant over internal docs, Evaluate models, Answer questions over data, Build a data platform and 17 more. Companies: LY Corporation, Avito, DoorDash, LinkedIn, Grab, Khan Academy and 22 more. Often combined with: RAG, LLM-as-a-judge, Human in the loop, Few-shot prompting, Multi-agent system and 80 more.

How much should we delegate to an LLM? Automating advertising analytics reports with an AI agentadtech2026-10
Inside LinkedIn's data context layer: curating trustworthy context for humans and agentssocial2026-10
Building Jarvis Pro: Route first, answer laterfood-delivery2026-08
Near Real-Time Media Analytics with Lakeflow Spark Declarative Pipelinesmedia-streaming2026-06
AI Agents for the Frontline: 7-Eleven's GenAI Maintenance Assistantretail2026-06
Reliance Jio Customer Churn Radar and next best actiontelecom2026-06
Sponsored by: Pogo | You're Overthinking It: What Analyzing $500B in Consumer Spend Taught Us About Building AI Agentsretail2026-06
Lemana-GPT: Building a Secure Corporate Gateway to LLMs and Scaling AI Products in Retailretail2026-05
Encoder vs LLM-as-a-Judge in Guardrails: Architecture Details and Trade-offsgeneral2026-05
Deploying LLMs in Moderation: From PoC to the Target Solutionclassifieds2026-05
How Khan Academy Is Building a Better AI Tutor: Our Most Recent Learningsedtech2026-05
Better Experiments with LLM Evals — A funnel, not a forkmedia-streaming2026-05
Building Biz Ask Anything: From Prototype to Productmarketplace2026-03
Building a multi-agent pipeline for NL-to-SQL analyticssocial2026-01
Creating a domain-specific NL-to-SQL MCP serversocial2025-11
Building The Intent Engine: How Instacart is Revamping Query Understanding with LLMse-commerce2025-11
Creating AI agent solutions for warehouse data access and securitysocial2025-08
How Ramp Fixes Merchant Matches with AIfintech2025-06
Preventing Revenue Loss With Real-Time A/B Test Monitoringtravel2025-06
How We Built a Smart Assistant in Lavka on Top of YaGPTfood-delivery2025-05
AI Tutors for Teaching Schoolchildrenedtech2025-05
5 Stops on the Way to LLM in Your Productiongeneral2025-05
Using LLM to transcribe restaurant menu photosfood-delivery2025-03
Path to high-quality LLM-based Dasher support automationfood-delivery2024-09
How we build experiments in-housesaas-b2b2024-06
Socratic Dialogues with LLMs in Problem Solvingedtech2024-05
Auto-Generating Product Descriptions in Fashionclassifieds2024-05
Applying NLP Models to Automate Call Center Workbanking2024-05
A Personal Mentor Powered by GPTedtech2024-05
WISE: Skyscanner’s Bayesian AB experimentation library and decision enginetravel2024-04
Navigating Fair Housing Guardrails in LLMsmarketplace2024-01
Growth platform series: Getting started with instrumentation and analyticssaas-b2b2023-11
Ecosystem Success Metricsfintech2023-04