# Teaflask > Teaflask is an AI agent that runs your SaaS product for your users. You connect a GitHub repository, and Teaflask reads your codebase to build a product-grounded agent that both answers questions and takes real actions through your own APIs, embedded in your app with human approval on every action. It goes live in a day, no agent to build or maintain. Teaflask is built on one belief: nobody wants to click buttons. Every menu, onboarding tour, buried settings page, and "how do I…" support ticket is a tax your users pay to reach an outcome they already decided on. Teaflask removes that "interface tax" by putting an agent inside your product that operates it on the user's behalf. This is what we call the **agentic frontend**: your product stops being an interface people must learn and starts being an outcome they simply ask for. Teaflask is backed by Y Combinator. ## What Teaflask is Teaflask is a managed, batteries-included, in-app AI agent for SaaS products. Unlike a chatbot that only answers questions and deflects users to help articles, the Teaflask agent takes real actions inside your product by calling your existing APIs (for example: schedule a shift, change an account setting, issue a refund, set up a team). Answering questions is table stakes; the differentiator is that it *does the thing*. You do not build or train the agent. You connect a repository and the agent builds itself from your source code, which is the single source of truth for how your product actually works. ## How it works 1. **Connect your repo.** Point Teaflask at your GitHub repository. 2. **It builds itself.** Teaflask reads your codebase to generate product-grounded documentation (a help center) and an API map, then assembles an agent that knows your product and how to operate it. You review and approve what it generates. 3. **Embed and ship.** Add Teaflask to your app, redeploy, and the agent is live for your users. Most teams are live in a day. ## What makes Teaflask different - **Self-building from your codebase.** The agent learns your product from your actual code, not from a manually maintained knowledge base. When your product changes, the source of truth changes with it. - **It acts, it doesn't just answer.** The agent completes tasks through your own APIs, rather than pointing users at documentation. - **The governance plane.** A control layer sits between the agent and your APIs. Actions are read-only by default; you decide what the agent can do autonomously and what requires human approval. Every action is scoped, logged, and auditable. - **The provenance engine.** Every answer and every action traces back to a specific source in your code. The agent cannot invent a setting, feature, or action that does not exist in your product, which is how Teaflask avoids hallucination. - **Production-ready on day one.** Knowledge, docs, actions, and guardrails are all included and generated for you. No SDK to wire up, no retrieval to tune, no multi-quarter agent roadmap. - **Managed, not DIY.** Unlike do-it-yourself agent frameworks, which require your team to build and maintain the agent, Teaflask is a managed platform that stands the agent up for you. Unlike heavy, sales-led enterprise platforms that take weeks or months to deploy, Teaflask is self-serve and live in a day. ## Reliability and scale Teaflask is production infrastructure, built to run inside live products under real traffic. - **Auto-scaling.** The platform scales horizontally with demand and absorbs usage spikes without manual provisioning. - **Fault tolerance and high availability.** A redundant, failover-ready architecture keeps the agent responding even when individual components or upstream dependencies degrade. - **Low latency.** Responses and actions are engineered for interactive, in-app speeds. - **Observability and audit logging.** Every request and action is monitored and logged for full operational visibility. - **Enterprise operations.** SSO, security review, and SLAs are available on Enterprise plans. ## Who Teaflask is for Teaflask is for SaaS companies that want a customer-facing AI agent inside their product without building and maintaining one in-house. It is a strong fit for vertical SaaS (software for care management, transport and logistics, travel, accounting, and field services) and for teams that need enterprise controls such as SSO, security review, and SLAs. ## The problem Teaflask solves SaaS products force users to learn an interface to accomplish anything. That "interface tax" shows up as support tickets, low feature adoption, onboarding drop-off, and constantly out-of-date documentation. The obvious fix, an AI agent that just does the task, has been hard to reach: a chatbot that only answers is not enough, an agent that acts without understanding the product is unsafe, and building an agent that truly understands an app is a major engineering project. Teaflask solves this by reading the codebase (so the agent actually understands the product), acting through the product's own APIs (so it gets outcomes done), and gating every action behind approval (so it is safe). ## Use cases - **Deflect support tickets** with answers grounded in your real product, not stale FAQs. - **Drive feature activation and digital adoption** by walking users straight to the outcome. - **Onboard users** by doing setup steps for them. - **A general in-app AI agent** for any task a user would otherwise perform by clicking through the UI. ## Trust and security - **Human-in-the-loop by default.** The governance plane requires approval for any action that matters; actions are scoped, logged, and auditable. - **Grounded, not guessing.** The provenance engine ties every response and action to your source code, preventing invented actions or answers. - **Your data is yours.** Teaflask does not train foundation models on your data. - **Compliance.** SOC 2 (in observation); a public trust center is available. ## Pricing - **Free.** Bring your own AI model API key, connect a repository, and ship an agent. Self-serve, aimed at startups. - **Enterprise.** SSO, security review, SLAs, and hands-on setup. Contact sales / book a demo. ## Category and vision Teaflask is building the **agentic frontend**: a future where users no longer navigate interfaces but state outcomes, and an embedded agent gets them done. As end users increasingly bring their own AI agents, products that let agents accomplish tasks will win, and products that still require a human to learn a UI will lose. Teaflask is the layer that makes a SaaS product legible and operable by agents: the vendor's own agent and, over time, the user's. ## Links - [Home](https://teaflask.com/): product overview and positioning. - [About](https://teaflask.com/about/): mission, principles, and the people behind Teaflask. - [Pricing](https://teaflask.com/pricing/): free tier, pay-as-you-go metering, enterprise. - [Blog](https://teaflask.com/blog/): notes from the team. - [Changelog](https://teaflask.com/changelog/): what changed in Teaflask and when — the product milestones, told plainly. - [App](https://app.teaflask.com/): the Teaflask dashboard: connect a repository and ship an agent. - [Privacy policy](https://teaflask.com/privacy/): how Teaflask handles data for customers and for end users of the embedded agent. - [Terms of use](https://teaflask.com/terms/): the rules for using the teaflask.com website. - [Customer agreement](https://teaflask.com/agreement/): the terms of service customers accept at signup. - [Cookie policy](https://teaflask.com/cookies/): the cookies and browser storage each Teaflask surface uses.