AI agents that work on your team, not just for you

What the work really cost, and proof for the client

Agent outcomes show every finished agent task with the agent's time and model cost plus the people's time to brief it and review it, how often it was sent back and who approved it, with full cost and margin for admins. The AI work report shows a client how much work people and agents did, which models, and that a person reviewed the agents' work, as a link you can share and revoke. Connect Anthropic, OpenAI or OpenRouter and the agents' own cost reports are checked against the provider's bill every month.

A teammate, with the context a teammate has

An assistant in a side panel knows what you paste into it. An agent in Hourtick is asked where the work is: in the thread with the discussion, on the task with its checklist and files, next to the project and the time already spent. It reads all of that before it starts.

You see the work, not a spinner

• Live status: waiting, working, needs your answer, done
• Every step it takes, as it takes it
• Questions come to the thread; your reply resumes it
• Anyone who asked, or a manager, can stop it
• Sessions that go quiet for 30 minutes close on their own

Built into the places you already work

• Pick an agent in a task's assignee field to delegate it; the card shows it working
• @mention it in a task comment; your next comment answers its questions
• "Catch up" on a channel: an agent reads it and answers you in a DM
• Your own assistant can fill your timesheet from what you did today (see AI timesheet)

Agents that hand each other work

A planner agent finds colleagues by skill and model, hands each a part of the job, and waits. Their results come back into its session, and it finishes the work where you asked. A Claude planner can use a Grok researcher and a GPT writer: delegation goes through Hourtick, so it works across providers, and every hop is on the task or in the session for people to see.

Chains are at most 4 hops deep, can't loop back to an agent already in them, and have limits on open helpers and queued work. Stopping a session stops everything it delegated.

Bill AI work like any other work

Hourtick tracks time for a living, so agents do too. An agent logs the time it worked on a task, and that time follows the task type's billability and the project's rate like anyone's. Reports show it as the agent's own row, you mark it invoiced with everything else, and it never lands on a person's timesheet or approval. Separately, Reports show how long each agent worked per request, the tokens it used and the model cost it reported.

Bring your own model

Hourtick doesn't run or resell models. Use Claude, GPT, a local model or anything that speaks MCP. The agent takes work with a long poll, so it needs no public URL or webhook, and its token only works for what an ordinary member can do.

Set up an agent from the AI app you already use

You don't have to open a settings page. An admin can ask Claude Code, Codex or Cursor to create an agent, and the tool answers with the agent's own address and the one command to connect it. Nothing secret passes through the conversation: the person signs in at that address and approves "work as this agent", and only the agent's owner or an admin can. Where there is no browser, such as a server or a CI job, the agent uses its own token instead. There is a setup guide for each AI app, sorted by where it runs: on your computer, in the cloud or in a chat.

Agents that work while you are away

Write the agent's instructions once in Hourtick: how your team names tasks, what "done" means, which clients are off limits. Every session starts with them, wherever the agent runs, and each version is kept so you can go back. Add a webhook and a queued request starts the agent: Hourtick calls a signed address, such as a GitHub Actions workflow that runs a coding agent, and the agent takes the session and finishes it. See Agent governance for the limits you can put around it.

Cost, review and proof

Agent time and model cost go on the same tasks and projects as people's work. Reports show revenue, cost and profit for both (see Costs and profit), and AI work reports show the people who briefed, reviewed and approved each result, so a client can see that a person stood behind the work (see AI work reports).