A native agent that synthesizes workspace context, scopes customer feedback into issues, creates follow-up work, runs coding sessions, and can be triggered automatically when issues enter triage…
How companies build internal AI agents
Case studies of AI agents that organizations build or adapt to do work for their own teams. Each of the 53 shows the workflow, tools, and human review steps, with every claim linked to a saved public source.
53agents
42organizations
110sources
Explore the catalog
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.
Homegrown one-shot coding agents that read work context, implement a change end-to-end, and produce a PR for human review.
Datako is an internal data application that helps Airbnb employees query business data without knowing the relevant tables in advance.
Pascal helps Airbnb product managers and designers turn an idea into a concept brief.
Rovo Dev is Atlassian's coding agent, available internally on all Jira sites. It works from a Jira work item to a pull request, and the developer reviews the plan and the code at each step. It became…
Bitrise runs Kolega, an internal coding agent that lives in Slack. A Jira ticket assigned to its Jira user or an @mention in a thread starts a session; the agent reads the requirements, posts a plan…
A multi-agent orchestration layer built on goose + MCP that coordinates agents across Block's entire codebase, invoked in Slack to take a ticket end-to-end to a reviewed PR.
Brex’s onboarding system verifies applicants and synthesizes KYC and underwriting evidence into decisions for its operations team.
Cloudflare’s reviewer analyzes merge requests and applies approval decisions, including merge blocks for serious findings.
Forge, previously Claudebot, turns employee discussions into Linear issues, drafted fixes and pull requests returned for review. Coinbase separately uses Mux to host concurrent coding-agent…
A general-purpose 'AI colleague' spanning sales, finance, client ops, engineering, and recruitment, later split into a reusable toolkit plus Slack and desktop surfaces.
A specialized agent that automatically reviews 10,000+ PRs a week across 56 repositories as of May 2026, emphasizing grounded high-confidence findings over noisy comments.
DataExplorer helps DoorDash employees explore internal data by selecting tables and generating grounded starter SQL.
Deflaker investigates and repairs flaky tests for Dropbox engineers using Nova.
Figma's security engineering team assembled an alert-response system from commercial parts rather than writing an agent framework: agent loops run inside Tines workflow automation on Claude models…
Flex runs an internal Slack agent that support, operations, and engineering use to debug HSA and FSA payment problems. Given an email, order number, or error string, it traces the transaction across…
GitHub's internal data-analytics agent, powered by GitHub Copilot. Employees ask questions about the company data warehouse in plain language.
Harvey’s SOC combines independently scheduled reporting, alert-triage and threat-watch agents for its security team.
Sidekick is HubSpot's internal AI code reviewer, built by its Developer Experience AI team. It runs on every pull request in GitHub. A second Judge Agent evaluates each draft comment for…
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…
Microsoft's internal AI-powered code review assistant, built in close collaboration with its Developer Division's Data & AI team. It joins each pull request as a reviewer, summarizes the change, and…
Notion built a Custom Agent that turns Slack bug reports into routed tasks.
Scruff investigates security alerts for Notion’s Detection and Response team, preparing analysis for human decisions.
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…
Plaid's internal agent for bank-integration reliability. Fix My Connection proactively detects bank-integration access issues and automatically repairs them. Plaid reports more than 2 million…
A GitHub-label-triggered PR approval agent that applies fail-closed deterministic safety gates, asks an LLM to check for showstoppers, autonomously approves eligible changes, and refuses or escalates…
Ramp Labs pairs an internal finance agent (the Doer), which executes spreadsheet accounting workflows such as monthly revenue reconciliation and month-end inter-company transfers into ERP, with a…
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.
Salesforce was 'customer zero' for the rebuilt Slackbot; an employee agent that finds company context, drafts work, and connects Slack context with Salesforce data; now also an external product.
An open-source Slack agent built at Sentry that retrieves context and acts across company systems. People can steer interactive tasks in a thread; Junior also handles scheduled tasks and inbound…
River is Shopify’s internal Slack agent for investigating questions and making code changes in public threads. Teams can provide channel context, and River carries knowledge across conversations.
Slack's engineering team runs an agentic service that investigates security alerts. A Director agent orchestrates rounds, Expert agents gather evidence, and a Critic scores each finding for…
Snap built CodePal, an internal AI code reviewer that comments on pull requests in its GitHub Enterprise instance before a human reviewer reads them. It builds symbolic context for the diff without…
Honk is Spotify's background coding agent; it runs on a Claude-Agent-SDK harness in Kubernetes, uses trusted CI tools, and combines formatting and linting with LLM-based diff evaluation. Xirp is a…
An internal agent system in which natural-language seeds and end-to-end scenario harnesses drive agents that write, validate, and iterate on code under standing rules that humans neither write nor…
An event-driven AI code reviewer for Uber's internal review platform that generates, grades, filters, deduplicates, and posts findings while leaving engineers in control of the reviewed change.
Horizon takes requests and external events into remote coding sessions, connects them to company context through MCP, and returns changes for human review. Its orchestrator manages sandbox lifecycle…
YC’s internal agent helps employees answer questions and carry out operational work using shared company tools.
CodeGen is Zup's internal coding agent. In the preserved paper abstract, its authors attribute reliability improvements to editing tools and layered controls, and adoption to progressive human…
Amplitude built Design Agent, an internal web tool that anyone in the company reaches behind Google OAuth to turn a text prompt, a screenshot, or a rough product idea into on-brand HTML output…
Brex uses an agent to personalize delinquent-account outreach and help its servicing team respond to customers.
Brex’s Payment Operations team built an agent to prepare reasoned card-dispute submissions.
Brex uses an agent to assess support interactions against its quality rubric and surface trends for team leads.
Cursor's technical support team runs customer investigations inside Cursor itself, configured for support work: multi-root workspaces over the product repositories, MCP servers that reach customer…
Deel runs a four-stage pipeline that triages failed US PEO payroll syncs without an engineer starting it. The pipeline detects and batches failures, retries them, investigates the rest with parallel…
Embat's internal agent platform began as a support tool for the Product Experience team and now serves the whole company through Slack. A router sends each message to one of more than ten specialist…
An internal agent system on Amazon Bedrock with agent identities, assigned managers, and evaluation scores. Atlas prepares feature changes; Morphex can merge and ship changes that pass the required…
An agent system built around OpenAI's internal Codex. A person defines the task; coding agents implement it and respond to CI results; specialist agents review changes under risk-based routing. A…
OpenAI's internal incident-response agent, built on Codex. When an incident is detected, it collects context, proposes mitigations, and answers questions in the incident Slack channel. The report…
Inspect runs coding tasks in prepared remote environments at Ramp. It can run tests, read telemetry and feature flags, and inspect the frontend. Ramp also builds other agents on its platform…
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…
Uber runs an internal coding agent that writes complete code changes with no human authoring, and engineers review and approve them. Its CTO reports that engineers now delegate tasks to the agent…
Infrastructure
Cloudflare's Dev Productivity team runs an internal AI engineering stack built on the company's own products. It puts MCP servers behind one OAuth portal, routes every model request through a…
Mux gives Coinbase employees a shared interface for working with multiple coding agents concurrently.
Databricks ships and tests engineering agents with coSTAR, using LLM judges as the test suite and a coding assistant to refine an agent until the judges pass. The agents cover internal engineering…
DoorDash’s analytics platform hosts agents and reporting workflows over internal data and operational knowledge.
Flux is DoorDash’s cloud platform for engineering agents. It supplies isolated sandboxes, a governed MCP gateway, reusable playbooks and invocation surfaces. DoorDash’s analytics AI Marketplace is a…
Nova is Dropbox's internal service for running coding agents in its cloud. Engineers launch parallel sessions from a web UI, CLI, or API, and internal systems call agents inside automated workflows…
Harvey's internal collaborative cloud agent platform; turns requests from Slack, the web app, or automations into durable runs that return reviewable summaries, diffs, branches, and PRs.
Custom Agents is Notion's platform for building agents in a Notion workspace, and Notion ships it internally first. Staff in IT ticketing, supply chain procurement, and recruiting build their own…
Plaid's internal Model Context Protocol server is supporting infrastructure rather than an agent. The central server connects engineers' AI tools to internal systems such as Jira, application logs…
The Aquifer agent platform (session/harness/sandbox split) powers River, a Slack-native coding agent, plus PR-review and headless Vanilla agent profiles; other teams have requested research…
Roast is the workflow orchestration framework Shopify's Augmented Engineering Developer Experience team extracted from its internal AI tools and open-sourced; Shopify runs Roast workflows internally…
Y Combinator built its own agent harness and infrastructure, led by partner Pete Koomen. It is an agent loop over a shared tool registry, now over 350 tools, including one that runs read-only SQL…
Airchat is Airbnb's internal agentic-coding harness, built by its Dev AI team as a wrapper over vendor coding agents such as Claude Code and Codex. The team first built its own orchestrator from…
Brex built a Retool-based platform where operations staff build, test and deploy agents for KYC, disputes, quality assurance and collections. Its systems engineering team maintains the builder; human…
Duolingo built shared infrastructure that turns a tested prompt into an internal tool. A JSON form defines a coding-agent workflow against one repository, Temporal runs the workflows that need…
Decisions you will face
Send a public write-up, talk, or post about a company's internal agent, or tell us what to fix in an entry. Pull requests are welcome.