Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free trial
All features

Agents

Hand work off. Check back later.

Delegated runs with schedules, bounded execution, and full progress traces.

Start free trialSee pricing

Four things every task gets.

A spending cap

Cap it at a dollar amount. When it hits the limit it stops and asks.

A regular schedule

Every morning, every Monday, the first of the month. Whatever pattern you want.

Other ways to start

Fire it from a button, an email, or a signal from another tool.

A full record

Every run leaves a row you can open up to see exactly what happened.

Chain what happens next.

A trigger fires, the agent runs, and the result kicks off the next step — a whole workflow you set up once and never touch again.

Keeps going without you

Close the tab, shut your laptop, lose your Wi-Fi. The task keeps running on our side and the results will be waiting when you come back. We can ping you when it's done.

What you get

Run controls

Keep delegated work bounded with explicit schedules, trigger rules, and run history you can inspect.

Schedules

Run every morning, every Monday, on the first of the month. The cron you wanted but never wrote.

Triggers

Webhook in, email in, file-changed in: the agent wakes up and does its work.

Live progress

Every step lands in the task pane. Open it at any point, see exactly where the agent is.

Pause, redirect, take over

Catch the agent mid-task, change the instructions, restart from a checkpoint, or finish the work yourself.

Who it's for

Operators

Every Monday 9am: pull metrics, summarise, post to the workspace channel. The task does it; you read the result.

Researchers

Overnight: re-run a benchmark across every model release this week. Wake up to the table.

Developers

On every PR webhook: skim the diff, flag patterns, comment if anything matches the workspace's style guide.

How it works

  1. 1
    Pick an agent and a job

    Either ask in chat 'do this every Monday' or build the task from the agent's task panel.

  2. 2
    Set the budget

    Cap by dollar, run count, or time: your call.

  3. 3
    Set the trigger

    Schedule it, wire a webhook, or run it on demand.

  4. 4
    Watch from the task list

    Every run becomes a row. Click in to see the trace, the artifacts, the cost.

See it in practice

Morning digest

“Every weekday at 9am, summarize what landed in /Inbox and post the digest here”

A fresh summary waiting each morning: with the full run trace
Folder watcher

“When a file lands in /Contracts, extract the key terms into a summary note”

New contracts turn into structured notes minutes after upload
Weekly report

“Every Monday, pull last week's metrics and draft the status update in /Reports”

A budget-capped draft ready before standup

Frequently asked

Set up the first one.

Pick an agent, set a budget, set a schedule. Get your mornings back.

Create a taskRead the docs

Read the docs

  • Capped runs
  • Agent notifications

Pair with

  • Agents
  • Subagents
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)