Method

Tool / function calling

LLM invoking external functions or APIs.

38 cases from 28 companies apply Tool / function calling. 1 was checked in an online A/B test; 16 report results in production. Includes variants: MCP.

Typical tasks: Answer questions over data, Build an assistant over internal docs, Build a data platform, Evaluate models and 13 more. Companies: Databricks, LY Corporation, LinkedIn, Yandex Lavka, Avito, Grab and 22 more. Often combined with: MCP, LLM-as-a-judge, RAG, Text-to-SQL, Golden set / benchmark and 73 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
Agentic Risk Operationsfintech2026-06
Building Query Expert MCP: Using RAG to Build an Analytics Agent That Goes Beyond Text-to-SQLfintech2026-06
Building Higher Quality Genie Agents (fka Genie spaces): How to Ensure Accuracy and Trustgeneral2026-06
Why Data-Intelligent Agents Win: A Side-by-Side Benchmarkfintech2026-06
Agentic Feature Engineering: How McAfee Drives Personalization With Agent Bricksgeneral2026-06
How Samsara Built a Multi-Agent System to Drive a 36x Lift in Meeting Bookings on Databrickssaas-b2b2026-06
From 700 Trillion Signals to Action: Building Production AI Agents for Real-Time Media Planningadtech2026-06
From Bowls to Bots: CAVA's Ask Astro Multi-Agent Supervisor on Databricksretail2026-06
Beyond Tables: How Musinsa Built a Self-Optimizing Semantic Layer on Databrickse-commerce2026-06
A–Z of Unity Catalog Business Semantics: Open and Unified Semantics for Agents, Apps and BIgeneral2026-06
Behind the curtain: Key learnings from building Geniegeneral2026-06
Your BI Copilot Is Blind - Crafting an Agent That Goes Beyond the Dashboardgeneral2026-06
AI Agents for Optimizing Yandex Lavka's Businessfood-delivery2026-05
AgentOps in Production: Infrastructure for LLM Agents and Support Automation for Yandex Personal Servicesmedia-streaming2026-05
From an LLM Portal to a Factory of Internal Agentsclassifieds2026-05
Lemana-GPT: Building a Secure Corporate Gateway to LLMs and Scaling AI Products in Retailretail2026-05
How We Are Deploying AI at a Universityedtech2026-05
From Zero to Agents: Growing a Multi-Agent LLM Platform Inside a Companygeneral2026-05
Building a Battle-Tested Open-Source Agentic RAGgeneral2026-05
A Corporate AI Agent at Nornickelgeneral2026-05
Building RAG Systems That Work Accurately: From Prototype to Thousands of Users a Dayretail2026-05
Unified Context-Intent Embeddings for Scalable Text-to-SQLsocial2026-03
Our Multi-Agent Architecture for Smarter Advertisingadtech2026-02
Creating a domain-specific NL-to-SQL MCP serversocial2025-11
How RecSys & LLMs Will Converge: Architecture of Hybrid RecoAgentsadtech2025-10
Building the next generation of job search at LinkedInmarketplace2025-05
How LLM Automates Work at Avitoclassifieds2025-05
How We Built a Smart Assistant in Lavka on Top of YaGPTfood-delivery2025-05
Benchmark-driven Time-Series-Augmented Generationfintech2025-05
Labeling Product Cards with LLMse-commerce2025-05
Function Calling 101: One Agent Instead of a Zoo of Bots—general2025-05
AI Sales Agents: Architecture, Bottlenecks and the Evolution of Capabilitiessaas-b2b2025-05
Streamlining RiskOps with the SOP agent frameworkmobility2025-05
Leveraging RAG-powered LLMs for analytical tasksmobility2024-10
GigaSearch, or a Search System on GigaChatsearch-engine2024-05
Text interfaces for data—general2023-05