ProductWhy LeadtimeClientsProjectsServiceTeamMoneyAgents
MoreOverviewIntegrationsSecurityCalculator
Who it’s forPricing
ResourcesSwitchingTutorialsHelp centreBlogAbout usContact
Sign in
Start free trialBook a call
A man works at his desk in the evening in front of a large window, the lit-up city outside. He is typing and smiling, his screen and desk lamp glowing beside him.

Product · Agents

Agents that work alongside you, like colleagues.

An agent takes on routine tickets, research and reports, and your team only checks the result. It has its own account and a role, and books its time like everyone on the team.

See the agents in the real app.

Just under three minutes: the Leadtime Agent, your own agents, automations and what an agent may do. Jump straight to the part you care about.

Video transcript

Introduction

This video shows in four steps how agents work in Leadtime: the Leadtime Agent in the chat, your own agents, automations and the permissions an agent works with.

The Leadtime Agent

The Leadtime Agent is built in. You write to it in the chat, as you would to a colleague, or ask it in the search field at the top. For example: which projects need attention right now? The agent goes through open tasks, priorities and deadlines and answers with an overview. Below that it sums up what matters now.

Your own agents

You create your own agents in administration. Each agent is a user of its own, with a name and a role that decides what it may do. Describe what the agent should do, and Leadtime sets it up with you. Or you create it by hand. Besides your own agents, you can connect coding agents or run an agent environment of your own.

Automations

With automations, an agent works on a schedule or when certain events happen. You choose the trigger, for example once a week. And you describe in your own words what needs doing. You run it yourself or let the agent run it.

Role and permissions

In the settings you decide which role the agent works with when it takes on tasks from assignments or automations. In the chat it works with your permissions. That is how agents work in Leadtime, like colleagues: you assign them tasks, they work with the permissions of their role, and what they do shows up in the history under their own name, with the time they booked.

An agent joins the team like a new colleague.

It gets a name, a picture and a role. The role decides what it can see and change. Then you assign it tasks, mention it in a comment or message it in chat.

Set up in one sentenceDescribe in one sentence what the agent should do, and Leadtime sets it up. You try it out straight away in the built-in test chat.
Rights through its roleWith the “Agent” role it works on tasks, projects, organisations, time, invoices and insights, but not on admin and settings. You can also give it any other role.
Wherever you workAssign it something, mention it in a comment or ask it in chat. It can also be started by an automation, from Slack or in the editor.

A ticket goes to the agent. It comes back done.

Pia assigns the Rheintal Logistik ticket to the agent Pal. Pal reads the project documentation, replies with short instructions, logs its 18 minutes and marks the ticket done. Every step is in the activity log, under its own name.

  1. 1Assigned
  2. 2The agent works
  3. 3Reply in the ticket
  4. 4Time logged, done
Every assignment is a sessionThe timeline shows when the agent started, what it worked on and how it went. If something goes wrong, that’s there too.
Who did that?The activity log shows at a glance what a person did and what an agent did.
Asks instead of guessingIf something is unclear, the agent asks and lets you choose between options. It doesn’t just carry on and hope for the best.

It logs its time. So you can see what it has worked on.

The agent logs its time on the task as a perfectly normal entry under its own name. It sits in the time list next to your team’s and counts towards the retainer or the project. Whether it’s billable is set by the project, as with any other entry.

In a plain ticketing tool

  • The agent resolves the ticket.
  • Its time isn’t recorded anywhere.
  • The retainer knows nothing about it.
  • Nobody sees what it cost and what it earned.

In Leadtime

  • The agent resolves the ticket.
  • Its time is in the time list, under its own name.
  • It counts towards the retainer or the project.
  • Billable hours on tickets land in invoice review.

A monthly report: six hours of pulling it together, one hour of reading it through.

The agent puts together the management report from the projects, time entries and invoices in Leadtime, and your team reads it through. What it completes is logged with its time on the project, so every agent hour is recorded and traceable.

Today6 hrs
With Leadtime1 hr

Management report, per month

Factor6

Model calculation based on our assumptions, not a promise of results.Work it out for your company

Say what you need. Leadtime gets it done.

The Leadtime Agent is built in and handles everything its role allows: creating tasks and tickets, logging time, writing reports, changing projects. You type or speak, it carries it out and opens the right page, and if something is unclear, it asks.

Always within reachAs a page of its own with history, in the sidebar, as a floating window, via ⌘K “Search or ask AI”, in the editor and in Slack.
With voice and filesDictate your request or attach a file. It returns reports as a file to download.
You choose the modelModels from Anthropic, OpenAI, Google and others, or “Auto”. You set your favourites.

What did the agents get done this week? Just ask.

Press ⌘K, or Ctrl+K on Windows, and ask in your own words. The Leadtime Agent answers from tasks, time and automations and only shows what you’re allowed to see anyway.

⌘K

Leadtime Agent

Bring your own agents. They work in the same system.

Already working with Claude, Codex or Cursor? Connect them to Leadtime. Through the MCP server they can use the whole public API, with the identity and rights you give them.

ClaudeCodexCursorHermesOpenClawDevinAmp
MCP serverYour agent signs in with Leadtime, with an agent identity of its own if you like. It picks the right one from around 640 actions, reads its details and runs it. It also gets the help centre and links into the app.
Access tokensFor scripts and agents without a sign-in: read only or read and write, with an expiry date, revocable at any time.
Plugins with skillsFor Claude, Codex and Cursor. They teach your agent how Leadtime works:
  • leadtime read and maintain data
  • leadtime-setup from an empty workspace to ready to go
  • leadtime-coach setup, import, migration
  • leadtime-public-api scripts, Zapier, n8n
  • project-documentation document projects
Self-hosted agentsYou connect Hermes, OpenClaw and others through signed webhooks and the session API. There’s a setup guide for both.

A development task goes to Cursor. Back comes a pull request.

Assign the task to Cursor in the cloud or mention it. It works in the project’s repository, reports back with a comment, a status change and a link to the pull request, and then hands the task back to you.

  • A repo per projectYou set the default repository and settings once on the project.
  • Claude as a managed agentLeadtime sets up the agent, its environment and a vault for credentials, with skills, your own MCP servers, GitHub repos and a log of every session.
  • How much of Leadtime it seesWith “Basic” it reads the task, comments and sets the status. Or you give it full access to Leadtime.

Devin and Amp are connected too.

What runs the same every week takes care of itself.

An automation is a request in your own words and someone to carry it out: you or an agent. It starts on a schedule, when something is created, on a Slack message or a webhook. A test run shows you beforehand whether it does what it should.

Personal or for everyoneYour own Friday reminder or the report for the whole workspace.
Every run is loggedWhen it ran, what it did and whether it worked.
Recurring tasks tooAn automation creates the monthly maintenance task on the first Monday of every month.

People, agents and automations, all working in one system.

This is how a software company works with Leadtime. Specs, tickets, time and comments sit in one place, and people and agents work on them under their own names. Pick a station to see who does what.

You decide what an agent may do. And see what it has done.

An agent gets exactly the rights of its role, like everyone on the team. It can’t log in to the app; it works through the API and MCP only. And when you no longer need it, one click locks it out.

One role per agentWhether it only reads, edits or sees invoices is set by its role, as for anyone on the team. Who may chat with agents is a permission of its own.
Tool scopeA coding agent sees only its own task, or you give it full access to Leadtime.
Follow-up questionsInstead of guessing, the agent asks and lets you choose.
A trail under its own nameEvery change is in the activity log, with the agent’s name and who started it.
Tokens that expireRead or write, with an expiry date, revocable at any time. Webhooks are signed.
Deactivated instantlyOne click, and the agent can’t get in anywhere, neither via the API nor via MCP.

Our proposal: built-in agents on a subscription, or bring your own.

For the built-in agents we’re planning a subscription for the whole team, in three sizes with a fixed volume. If it isn’t enough in a given month, you top up. Your own agents run on your account with the provider. Prices are still to be decided.

Small

about €20per month

for a team that asks the agent now and then

  • Leadtime Agent for the whole team
  • a fixed monthly volume
  • top up when it isn’t enough

Medium

about €50per month

for agents that take on tickets and tasks every day

  • everything in Small
  • more volume per month
  • top up when it isn’t enough

Large

about €100per month

for teams with several agents and automations

  • everything in Medium
  • the largest volume
  • top up when it isn’t enough

Your own agents

Your accountwith the provider

Claude, Codex, Cursor, Hermes and others

  • you pay the provider directly
  • work in Leadtime with their own account
  • leave a trail under their own name

Draft for discussion. Prices, volumes and top-ups are still to be decided.

All agent features at a glance.

Each feature comes with a sentence on what it does for you.

  • Create an agent

    Enter a name, picture and role by hand, or describe the agent in one sentence. You try it out straight away in the test chat.

  • The “Agent” role

    Access to tasks, projects, organisations, time, invoices and insights, but not to admin and settings. You can assign any other role too.

  • Assign and mention

    Assign the agent a task or mention it in a comment. Every assignment and every mention is a session of its own.

  • Sessions on the task

    You can see when an agent is working on the task. The timeline shows every session from start to result, with the trigger and who started it.

  • Log time

    The agent logs its time on the task as a normal time entry under its own name. It shows up in the time lists like your team’s.

Let us show you with one
of your tickets.

Bring a ticket that comes back every week. In 30 minutes you’ll see how an agent resolves it in Leadtime and logs its time.