Create your first agent

Create an agent when a named, persistent role should own work across multiple check-ins. Configure its instructions, files, connections, and continuing conversation as an ongoing teammate.

Start with a responsibility

When the workspace has no agents yet, open Agents and select New agent to choose a creation path. You can also open the agent selector on Chat and choose Add an agent. Sending to the default d5s target starts a one-off chat; it does not create a persistent coworker.

If you see the illustrated first-agent steps, follow the path below. Otherwise, onboarding shows the workspace welcome tour and does not create an agent.

During first-login onboarding, d5s asks how many people are expected to use the workspace, then prepares a private coworker draft named Milo if you see these steps. The answer tailors the colleague invitation prompt. You can connect Slack or Microsoft Teams to that coworker during Connect your tools. An available managed inbox is assigned automatically and can be viewed during setup. On Create your first agent, choose Milo's general, engineering, or research focus; Add some context can add a short description of your team's work to his standing instructions. With a verified work email, d5s pre-fills it with a short draft from your company website; edit or delete it before you continue. Neither choice grants new tool access. Invite a colleague opens the standard invitation review for the automatically created shared workspace, named after its owner. Finishing the journey activates Milo, refreshes the workspace crew, and opens the agent's chat directly. If no draft appears, onboarding opens workspace chat. You can configure more profile details later using the steps below.

1. Create the profile

From Chat, open the agent selector beside the composer and choose Add an agent. Quick create opens a compact form for the agent's name (up to 29 characters) and standing instructions, then selects the new agent as the composer target. The form lists the workspace connectors the agent will be able to use; Manage opens the workspace connectors page and keeps what you typed. Model shows the workspace default level, such as Medium. Choose another level or model for the agent. The agent uses this model for every run, including the first. When a mail, chat, or calendar connector is connected, Learn how you work is on. After creation, the agent does one read-only first run: it reads recent sent mail, chat messages, and calendar events, then saves memories. It sends nothing. Turn the switch off to start the agent idle. Add persona adds an optional one-line role. Agent Builder opens the guided setup workspace. Browse agents opens the reviewed catalogue and starts a draft from your selection so you can review it before activation.

You can also choose an example on a connected provider's Connectors detail page, then use the same agent picker and Add an agent → Quick create path. After creation, the example is an editable draft addressed to the new agent; review it and press Send when ready. Creating the agent does not run the example.

You can also open Agents and select New agent. Search the reviewed Agent templates or narrow them with the team tabs. Opening a template shows what you get, how it works, the recommended connections, the suggested schedule, and what the agent asks you first; browsing or previewing does not create anything. Select Use template to open a reviewable draft based on that exact preset version, then review it before activation.

A preset copies its trusted profile and working instructions, not authority. Starting from a preset does not connect an account, inherit workspace credentials, configure a channel, create a schedule, or run a task. Recommended connections and timing remain guidance that you can configure later.

For a role that is not in the catalogue, choose Agent Builder and describe it in your own words. This opens a private configuration workspace. On a wide desktop, the Setup assistant appears on the left and the editable agent card on the right; on a tablet or phone, use Chat and Agent to move between the same views. Describe the work, result, preferences, and boundaries in the assistant, or edit the card directly. Setup replies use the High model level. On the Free plan, they use Light. If an organization Owner or Admin turns off High, they use the workspace default. Setup replies use your credits.

When dictation is available in your workspace and browser, select the microphone beside Send in the setup assistant. Select Stop recording to transcribe your description into the editable message, then review it before sending. Press Escape while recording to discard the clip. If transcription fails, choose Retry or discard the recording.

The setup assistant updates the draft but is not the future agent. It can only search the connector catalog. It cannot execute work, select accounts, or activate itself. The assistant knows your team, the workspace's connected connectors, and the workspace's skills, and it can suggest skills for the agent. A suggestion does not give the agent a skill. Platform skills are always available. Review and edit the name, description, Instructions, Connectors, Channels, Skills, Schedules, and Model directly on the card: select the name or description to edit it in place, select Edit for the instructions, and use Add beside a section name to add to it. The card shows the configuration the future agent will receive. A green dot marks a connector or channel that is connected; an orange dot marks one that still needs steps; a grey dot marks one you chose to set up later. Under Skills, All workspace skills is on by default: the agent gets every workspace skill, and skills added to the workspace later. Turn it off to give the agent only the skills you add. The setup assistant can suggest skills, shown with a dashed outline. Select a suggestion and choose Add to agent to use it, or Dismiss. Under Model, the pill shows the workspace default level, such as Medium, and the agent follows it. Choose a level, or search the model list for a model, to give the agent its own. On the Free plan, the agent runs Light. Below Model, Learn how you work shows which connected sources the first run reads. Turn it off to activate the agent idle. If a setup reply fails, the error appears in the conversation with Retry. Unsaved edits may be recovered when you reopen the draft in the same browser. Edits save when you finish a field; sending another setup message or activating the agent also persists the exact visible configuration. Drafts and setup history are private to their creator in the workspace. d5s saves a draft when you send the first setup message, and keeps it once it has instructions or a connector. To return to a draft, open New agent and choose it under Continue a draft, or use the draft menu at the top of Agent Builder. The same menu starts a New draft or deletes the open draft with Delete this draft. You cannot restore a deleted draft.

The setup conversation explains your communication options before asking about connectors. If your draft shows an inbox address, your agent already has a private, inactive identity. The address appears with Enabled and Copy address. You can configure Slack, Telegram, or Discord (beta) inside setup. Slack setup has two steps: Give Milo a Slack account creates the agent's own Slack app through one Slack approval screen, then Invite Milo to a channel tells you to type /invite @Milo in Slack (with your agent's name in place of Milo). Select the name on the Slack or Teams card to give the bot a different name. Workspace admins can pick Use the shared d5s app instead. A connected channel does not activate the agent or authorize sending messages. You can skip extra channels and set them up later in Manage agent → Channels.

In guided preset setup, Connections starts with the preset's recommended products and uses the same searchable rows as the workspace connector directory. Select a row to attach an existing workspace account or connect a new one directly; when reusable accounts exist, d5s offers those first. If several accounts are available, check the account label before choosing one. New connections require a workspace administrator, while members can attach an account that an administrator has already authorized. You can continue without a connection and add it later.

In the full Builder, one picker adds both connectors and channels, and it keeps selection separate from authorization. Selecting a connector records the intended capability; it does not connect the app or grant access. Slack, Telegram, and other messaging products appear under Channels only. After you confirm, numbered setup steps open for each item that needs them: choose an existing workspace connection explicitly or connect a new account, then optionally describe how the agent may use it; the setup assistant can also fill this guidance from your conversation. You can instead choose Set up later and finish from the amber chip or after activation.

Connector setup preserves the draft across sign-in redirects. Slack and mailbox authorization return to the draft and reopen the relevant channel settings. Cancellation or failure leaves the draft available to resume. A connection successfully added to the workspace remains there even if you do not finish creating the agent.

Review the visible draft, then select Activate agent (or Create agent if your draft shows that button). Activation keeps the same identity, inbox address and configured channels, applies the reviewed instructions and connections, and enables agent work. A draft cannot run tasks or reply through its channels. Find your private setup conversation under Agent settings → Setup history, including when returning to the agent later.

Conversationally created agents use the connections explicitly reviewed during setup. They do not automatically receive other existing or future workspace connections. You can change their access later in Manage agent → Connectors. Instructions about how to use an app are working guidance, not additional provider permission boundaries.

This setup creates an agent that works when you ask. Timing requests and requested trial tasks are saved as deferred: no schedule is configured and no task has run. Configure those separately after creation.

Choose a character

Open Manage agent → Profile. The Character row appears below Name. If you can edit this agent, select Upload image. Choose a still PNG, JPEG, or WebP image of 2 MB or less and at most 16 million pixels.

Check the square crop in the row, then select Apply. Cancel discards the preview. The saved character appears in d5s, including the desktop and mobile apps, and in new email and supported chat messages. Everyone with access to the agent sees the same character. Activity indicators do not replace it.

Select Replace image to choose another image. Select Use default to restore the generated character. If the image exceeds either limit, reduce its file size or dimensions before uploading it again. For a temporary save failure, keep the preview and try again. A read-only profile shows the saved character without upload or reset controls.

Dedicated Slack and Teams bot profiles need their existing Sync Slack profile or Sync profile action in Channels. Saving a character does not update those profiles automatically. Teams may require an app update. Older messages and email may keep their earlier image.

2. Write standing instructions

Open the agent, select its avatar at the right end of the page header to open Manage agent. The Profile section holds Persona and Standing instructions below the name and model. Standing instructions should describe the responsibility that remains true across every turn:

The model starts on Workspace default. If a shared Codex connection is enabled and available to the account, members inherit the same Codex model and organization-owned connection across the organization's workspaces. An Owner or Admin can choose another available Codex model or catalog model family for this agent. A model family uses its newest available version on later turns. Select Workspace default again to clear the override and resume inheritance.

• the outcome the agent owns;
• sources it should check;
• decisions it may make;
• actions that require approval;
• the expected output or destination; and
• what to do when there is nothing meaningful to report.

Avoid placing today's task or a one-off deadline in standing instructions. Send that as a direct message, or set up a task-specific scheduled wakeup for it, either by asking the agent or by adding one yourself under Manage agent → Autonomy.

3. Add durable context and capabilities

Use the Manage agent sections to configure its working context:

• Files for reference material that should remain available;
• Connectors to review selected or inherited workspace credentials and remove any this agent should not use; and
• Skills for reusable methods or instructions. A new agent gets every workspace skill, and skills added to the workspace later. Remove any that it should not use. Select Add skill to add one skill or a whole plugin. See Choose an agent's skills.

Workspace connectors are available by default to agents made through advanced creation. Agents made through conversational creation start with only their reviewed connections and retain that explicit access policy. Removing one affects only that agent. MCP tool policy still controls whether individual operations allow, ask, or deny; API operation controls apply only when they are available and enabled for that credential.

For independent recurring checks, open the Automations page, then open a routine and select Manage team, then Add people or agents…, and add the agent. Keep informed shares short result handovers when the agent next works. Enable Act on findings only when actionable results should wake it. The automation keeps its own run context; attaching an agent does not grant access or copy its conversation into the run.

4. Test in the conversation

Keep autonomy off and send a representative request directly to the agent. Review the sources it selected, tool calls it made, approval requests it raised, and whether the result followed the standing instructions.

Test at least three conditions: a normal case, incomplete evidence, and a case where there is nothing to do. Correct the instructions or capability set and repeat until all three behave predictably.

5. Add autonomy last

Open Manage agent → Autonomy only after direct tests pass. You can create, edit, pause, and remove one-time or recurring scheduled wakeups, and configure the daily budget and agent pause state.

Start with a conservative cadence and a finite daily budget. A broad Routine check-in wakeup can ask the agent to inspect its project and decide whether work is due, while named wakeups should carry one concrete responsibility. Every wakeup that starts agent work invokes the configured model. A mailbox check starts agent work only when new mail is found. Pausing the agent blocks work without deleting its conversation or configuration.

Read Agent wakeups and schedules before enabling the first autonomous check-in.

New agents created by signed-in users with a verified email automatically get a d5s inbox where available. Incoming and outgoing permissions default to the organization's inferred business domain or the creator's exact personal-provider address, and sending requires approval. Review these rules under Manage channels → Email before relying on email for work. Existing agents can choose Create d5s address, and any agent can connect a dedicated Gmail or Outlook mailbox. The optional Accept replies from people this mailbox emails exception starts off for automatic inboxes and on for manual mailbox setup. Review outgoing rule changes carefully: saving them can authorize matching sends without individual approval. Read Agent email for details.

An authorized Owner or Admin can select Add Telegram in the conversation’s Channels panel or open Manage agent → Channels → Telegram. Follow the illustrated guide to create a bot in BotFather, connect its token, link your account and test a reply from Telegram. Bot connected confirms the bot connection only; see Telegram teammate DMs.

For Telegram, you can connect the bot while your agent is a draft. Activate the agent before linking your personal Telegram account or trying a message; return to Telegram in channel settings for those remaining steps.

An authorized Owner or Admin can begin setup while the agent is a draft or open Manage agent → Channels → Discord later. Create a dedicated application and bot in Discord, connect its Application ID, Public Key, and bot token, configure the generated interactions endpoint, and bind only the server channels this agent should hear. Teammates confirm their own d5s account before a Discord DM can enter the agent's conversation. See Discord agent channel for the complete setup and test boundary.

Open Manage agent → Channels → Microsoft Teams after creating the agent. An organization Owner or Admin with workspace administration access connects provisioning once, then creates the named identity and continues through Microsoft installation. Activate the intended verified standard channels separately. See Teams agent setup for permissions, testing, and supported scope.

Optional local file access

To let this agent work with local files, add folders in Settings → Desktop, then grant Read only, Write only, or Both in Manage agent → Local files. Confirm access in the native dialog and ask for the operation in a Desktop conversation. See Local files.