HumanLayer provides CodeLayer, an IDE that integrates AI coding agents powered by Claude Code to automate complex codebase tasks. It offers keyboard‑first, context‑engineered workflows that enable developers and teams to run parallel AI sessions, manage worktrees, and integrate custom tools, improving productivity and reducing token usage. The platform is sold via subscription and enterprise contracts, with additional consulting services for organizations adopting AI‑first development at scale.
Funding
$500K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
AI agents often require human intervention for critical decision-making, but integrating human oversight into automated workflows can be cumbersome and inefficient. Current solutions lack seamless integration with existing AI frameworks and communication channels, hindering the development of reliable AI systems.
Solution
HumanLayer provides an API and SDK that enables AI agents to request human feedback, input, and approvals directly within automated workflows. By implementing a human-in-the-loop approach, HumanLayer ensures that critical function calls are reviewed by humans, with feedback seamlessly integrated back into the agent's context. The platform supports omnichannel contact, allowing agents to communicate with humans via Slack, Email, Discord, and other channels. HumanLayer facilitates the creation of reliable AI agents by providing tools for approval workflows, custom responses, and escalations, ensuring that AI systems operate safely and effectively.
Target Audience
HumanLayer is designed for AI agent builders and software development firms seeking to integrate human oversight into AI systems, as well as engineers focused on building reliable and impactful AI agents.
Features
- `@hl.require_approval()` decorator to block specific function calls until human consultation
- `hl.human_as_tool()` function to enable AI agents to contact humans for answers, advice, or feedback
- Support for custom responses and escalations to coordinate approvals across multiple teams and individuals
- Granular routing to direct approvals to specific teams or individuals
- Compatibility with any LLM and major orchestration frameworks that support tool calling
- TypeScript SDK and REST API for integration into existing stacks
- Learning and auto approvals to set thresholds for automatically approving or denying requests based on past human interactions