Internal Agents Map

Answer questions about company data

These records have the Data work-domain tag. Compare how each system finds the correct data, how it checks its answers, and who can see the results.

Agents

Replit's Manager agent (agent-of-agents)

An internal agent-of-agents stack where every employee gets a manager agent that spawns multiple agents for verifiable work and escalates judgment to humans.

AgentCodingCode reviewSupportResearchDataDetailed

Sierra's Pinecone

Pinecone is Sierra's shared agent interface for employee work. It routes requests to a model, harness, and environment, runs sessions on Agency, and connects to company systems through an MCP Gateway.

AgentCodingCode reviewSupportResearchDataDetailed

Airbnb's Datako

Datako is an internal data application that helps Airbnb employees query business data without knowing the relevant tables in advance.

AgentData

DoorDash's DataExplorer

DataExplorer helps DoorDash employees explore internal data by selecting tables and generating grounded starter SQL.

AgentData

GitHub's Qubot

GitHub's internal data-analytics agent, powered by GitHub Copilot. Employees ask questions about the company data warehouse in plain language.

AgentData

Meta's Ranking Engineer Agent (REA)

Meta built the Ranking Engineer Agent (REA) to run machine learning experimentation for its ads ranking models. REA generates hypotheses from a historical experiment database and a deep ML research…

AgentDataResearch

Plaid's AI Annotator

Plaid's internal labeling agent for its own model training. AI Annotator automates large-scale labeling of anonymized transaction data, with targeted human validation when a product use case requires…

AgentData

Snap's Casper

Casper is Snap's fleet of remote coding agents. An engineer describes a task in a Slack DM, a channel mention, or the Agents Portal, and Casper starts a durable session in an isolated sandbox…

Agent familyCodingMaintenanceOn-callData

Infrastructure

Related lessons

Know an internal agent?

Share a resource or public mention, suggest an addition, or correct an existing entry. Pull requests are also welcome.