# What June can do in a reply > Every tool June can use while it answers, when it reaches for each, and where one is not available: the web and the app, Slack, or a scheduled run. Source: https://www.dearjune.ai/docs/how-june-works/tools In a reply, June can do more than write: it searches, runs code, reads your connected tools and starts threads. Each use of a tool shows as a step in the reply that you can open. For a useful result, name the source, the action and the output you want: for example, search a particular repository and return a list of matching files. June picks the tools from what you ask. You never have to name one, but it helps when you want one used ("search the web for…", "run it in your sandbox"). _Demo: A tool step in a reply: open it to see what went in and what came back._ ## Every tool Every tool works on the web and in the app: in your own chats, projects, organization chats and calls. What June may do with an integration can differ in an organization ([personal or organization](/docs/integrations#personal-or-organization)). ### Find out | Tool | What June does with it | In Slack | | :-------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- | | Date and time | Checks today's date and the time | Yes | | Web search | Searches the web and cites what it found. Not when an API key pays | Yes | | Read a document | Reads a PDF, an image, a Google Doc or Slides deck, or a file in its sandbox or your project | No | | Your threads | Lists your threads, reads one or searches them for up to 30 matches, from the web and from Slack. In a chat other people read, it sees only threads everyone there can read | No | | Databases | Runs read-only queries on your [databases](/docs/databases) while a skill that uses one is loaded | No | | Skills | Finds the [skill](/docs/skills) for the task and loads its instructions | Yes | ### Make and run | Tool | What June does with it | In Slack | | :------------------- | :---------------------------------------------------------------------------------------------------------------------------- | :------- | | Run a command | Runs code and command-line tools in [June's sandbox](/docs/how-june-works/sandbox) | No | | Image generation | Makes an image and adds it to the reply, when a ChatGPT plan pays | No | | Send a file back | Attaches a file it made in its sandbox to the reply, up to 20 MB | No | | Save to Google Drive | Saves 1 to 10 files it made into your Drive, up to 20 MB each, with [Google Drive](/docs/integrations/google-drive) connected | No | ### Act in your tools | Tool | What June does with it | In Slack | | :---------------------- | :----------------------------------------------------------------------------------------------------- | :------- | | Your integrations | Reads and acts in the tools you connected on the **Integrations** page | Yes | | Connect an integration | Checks whether an integration is ready, and gives you the link to connect it if not | Yes | | Reminders and schedules | Sets up, lists, changes, pauses, resumes, runs and removes [reminders and schedules](/docs/follow-ups) | Yes | ### Hand off | Tool | What June does with it | In Slack | | :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------- | :------- | | Start a thread | Starts a [thread of its own](/docs/chat/threads#threads-june-starts) for part of the work, when you ask for one | No | | Message another thread | Sends a message into another of your threads as you, stops June there, or changes the messages it queued there | No | | Hand off a task | Gives part of the work to a [child thread](/docs/chat/threads#threads-june-starts) that sees only the task, then reads its result or stops it | No | | Ask one of your agents | Hands a task to one of your [agents](/docs/agents) and brings back its answer, once you have an active agent | No | | Design an agent | Drafts a new agent from the work you described | No | ### Remember | Tool | What June does with it | In Slack | | :------------------------- | :------------------------------------------------------------------------------------------ | :------- | | Remember and forget | Saves a fact as a [memory](/docs/memory/how-memory-works#when-you-ask), or forgets one | Yes | | Update the Soul | Adds to, clarifies or removes something from the [Soul](/docs/memory#your-soul) of the chat | No | | Where it learned something | Finds the chats where a fact it knows was said | Yes | ## How some of them work **Your integrations.** June reaches every connected integration through one tool: it writes a short script that searches your connections for the right action and calls it. Your passwords and tokens never enter that script. A run stops after 60 seconds, and its result is cut at 64 KB. What June may read or change in each service is on that [integration's page](/docs/integrations). > Example prompt: Which of my Notion pages mention the Meyer GmbH contract? **Start a thread.** June starts a thread only when you, the project's instructions or an agent's skills ask for a separate thread or parallel work. A question that needs research or depth is answered in the chat you asked it in. When you ask, the new thread can run as one of your agents, or on another model of your ChatGPT or Claude plan; June may also pick a lighter model of that plan for a light task, such as a lookup. June starts at most 5 threads in one reply. A child thread, linked under the one it came from, nests at most 3 levels deep; a side thread stands alone and has no such limit. At most 10 threads it started can run at once for you, and 30 in one organization. A thread June just started cannot start another in its first reply, though it can ask one of your agents. In an organization or a project, the new thread stays there. **Message another thread.** June can send a message into another of your threads as you: it starts June there, updates the reply June is writing there, waits until June is free there, or stops that reply and goes next. It can stop June in another thread as your Stop would, and change, reorder, send now or remove the messages it queued there. It never writes into the chat it is in, and it writes only where everyone who reads the chat it is in may read too: from a chat with other people, never into your own chats, and the other way round. In an organization's shared chat June speaks only when someone tags it, so a message June sends there is posted for the members and does not start it. > Example prompt: Start a separate thread for each of the three suppliers and compare their offers **Hand off a task.** For work it needs back, such as one part of a larger job or a second opinion on a draft, June hands a task to a child thread under the chat it is in. The child sees only the task June wrote, not the chat, and works on its own. When the child finishes, June receives a notice and reads the result after its current reply. If June has already read the result, it receives no extra notice. Stopping the parent chat cancels pending notices. A child waiting for your answer or approval still needs attention in its own thread. June can stop a task, and stopping a reply also stops the tasks that reply handed off, together with the ones those handed off. The same limits as for starting a thread apply: 5 per reply, together with the threads it starts, 3 levels deep, and 10 running at once for you. > Example prompt: Hand the three supplier offers to separate tasks, then tell me which is cheapest once they are done **Ask one of your agents.** June offers this only once you have an active agent, and knows your agents by name on the web and in the app. The agent answers from its own instructions and skills, in up to 8 steps, and June brings its answer back into your thread. **Image generation** draws on a ChatGPT plan's image allowance, which runs out faster than text. The plan can be yours or one shared with the organization. ## In a scheduled run A [schedule](/docs/follow-ups#schedules) runs with only the tools it was set up with, in groups such as web search, integrations, documents or the sandbox. A schedule set up with none has only the date and time, and one June sets up from chat has none unless you ask June to turn some on by name: `integrations`, `web`, `documents` or `terminal` ([what each opens](/docs/recipes#set-up-a-schedule-with-the-form)). In a scheduled run June also cannot: - set up or change schedules or reminders, - generate images, send a file back to the thread, or save to Google Drive, - use databases, read or search your threads, start threads, hand off tasks, ask an agent or update the Soul. A scheduled run stops after 4 minutes without activity, and after 13 minutes at most. ## What June does not do - It does not browse websites like a person, with clicks and forms. It searches the web and reads what search returns, or fetches a page from its sandbox. - It asks your approval only for a step that changes something in a connected account ([what the card shows](/docs/how-june-works/connections#a-step-that-needs-your-confirmation)); reading never asks. In the sandbox it cannot ask yet, so [a command that would need it](/docs/how-june-works/sandbox#commands-june-refuses) does not run. - Mail capabilities depend on the connection. A password-connected [mailbox](/docs/integrations/mailbox) saves drafts for you to send; a Gmail connection can also send a new message, reply or saved draft, subject to [your approval rules](/docs/how-june-works/connections#a-step-that-needs-your-confirmation). Do not assume that every mailbox can send.