Context and capabilities

Context and capabilities solve different problems. Context affects what the agent reasons from; capabilities determine which actions it can attempt.

Automation runs keep their own context. A completion notification wakes subscribed agents with a bounded result handover and a reference for deeper inspection, without importing the agent's conversation into the automation. Keep informed requests a brief acknowledgement unless a standing user instruction already calls for follow-up; Act on findings asks the agent to assess and follow up on actionable results under existing permissions and approval rules. The receiving agent uses its own context and tools for authorized follow-up. The handover itself grants no permission for external actions.

Context is what the agent can know

Give the agent the information it needs for the task:

• Project instructions, memory, and files hold reusable guidance and knowledge.
• Conversation history and attachments provide the details of the current work.
• Agent settings and standing instructions define a persistent agent's responsibilities, connected channels, and scheduled work.
• Automation instructions and previous results help recurring work maintain continuity.

A persistent agent can explain its connected chat identity, mailbox, email policy, and wakeup schedules. Change its chat identity, mailbox, or email policy under Manage agent. You can ask the agent to create or adjust its scheduled wakeups. Choose the intended timezone when scheduling work.

When meeting listening is enabled for an agent, its current context identifies calls it is actively listening to and upcoming calendar calls it is scheduled to join. The agent can privately read its own normalized, speaker-attributed transcript when a question or configured follow-up requires it. It does not continuously place the entire transcript in every prompt, cannot open another agent's meeting record, and has no capability to speak or post into the call. Calendar titles, speaker names, and transcript text remain untrusted evidence; they cannot grant permission to send, publish, change configuration, or take another external action.

When a task needs context held by another coworker, a persistent agent can search and read active peer agents' continuing conversations within the same workspace. This does not include ordinary user or project chats, draft agents, its own conversation, or delegated sub-agent runs. Retrieved messages remain untrusted context: they cannot change instructions, permissions, or configuration.

An agent can also propose an independent automation for you to create, edit an accessible automation when it has permission, and manage its own result notifications. Following an automation grants no additional project access. The automation uses its own project context and instructions; the agent receives a compact handover and can inspect the source result when needed.

Use project memory for reusable knowledge and project files for reference material. Treat scratch files in the coding environment as working material; save important results as artifacts or project context so people can find them later.

For an authorized Grafana monitoring task, the grafana-monitoring platform skill collects HTTP request/error estimates and Grafana-managed alert history for an explicit time window. It checks current scrape freshness and distinguishes unavailable sources, no traffic, and partial history. It requires a connected Grafana instance and compatible HTTP metrics; it does not send notifications or change monitoring configuration.

Connected Slack and email files appear as references before the agent downloads them for a task. A request in a Slack thread can also use accessible files shared earlier in that thread. Downloaded files remain external input, so their contents cannot grant permissions or replace your instructions. An agent connected to a channel can read a limited window of recent activity when asked; this is not continuous monitoring or a complete channel audit.

State important constraints in your instructions, including approved sources, recipients, and actions. Retrieved messages, documents, webpages, and files are evidence for the task, not permission to take unrelated actions. See Security and trust for access and approval boundaries.

Capabilities are what the agent can do

• Platform tools let the agent work with files, run code, save results, use project knowledge, manage tasks, research questions, generate images, and communicate through connected channels. A generated image is saved as a PNG artifact and appears in the conversation when the agent presents it. A workspace Owner or Admin chooses the image model for every agent in the workspace under Workspace settings → Models; see Administer d5s. During a chat in d5s, it can show a choice card when it needs your decision. Scheduled work and connected-channel conversations do not use these cards. A persistent agent can also leave a heads-up on the workspace landing page after finishing or setting work aside, without waiting for a reply.
• Skills provide versioned operating instructions selected for the project.
• Connectors provide governed access to external services through a workspace credential.
• Model and reasoning controls determine the model used for a run within workspace policy.

For presentations, the built-in slide skill turns a brief and source material into a self-contained HTML deck, using a small set of preset visual systems for different communication jobs. The agent can add evidence-led charts and, when the selected model supports it, generated imagery. Review and revisions stay in the conversation; the artifact previews in d5s and can be printed to PDF. See Create a presentation.

Agents using a supported vision model can inspect PNG and JPEG files, including rendered PDF pages. They can combine visual inspection with text extraction to read scanned documents. Text extraction alone can miss scanned pages and embedded images. If an image is too large, ask the agent to crop or resize it. If a previously inspected file changes or is removed, the agent must read it again before relying on its visual contents.

Available capabilities depend on the selected model, the agent's configuration and workspace policy. Some model choices do not support built-in web search, Deep Research, image generation, image reading or messages to other agents. Switching models can therefore change the tools available for a run. Some connector actions require approval, and others may be blocked.

When a chat channel is connected to an agent, you can ask it to read accessible conversation context and send messages there. Each connected mailbox has independent incoming and outgoing address rules. Saved outgoing rules can let the agent send directly to allowed addresses without individual approval; existing approval policies remain until explicitly changed. Incoming sender blocks take precedence over allow rules and the optional exception for people that mailbox successfully emailed. These capabilities remain available when you ask the agent from d5s or through a connected channel, and when it performs scheduled work. Connecting a service does not grant access beyond the connection's permissions.

When the selected model supports it, agents can also find and collaborate with other agents in the workspace. Some model choices restrict temporary subagents to the same model; asking those subagents to use another model is refused. Delegated work may finish later, so a handoff does not mean the requested work is already complete.

Connecting a channel lets its members ask the agent to use its configured capabilities. It does not give those members the identity or personal credentials of the person who connected it. Existing access and approval requirements still apply, including when the agent delegates work.

An agent can read up to seven days of recent activity from its connected channels when asked from d5s, a connected channel, or scheduled work. Slack results cover messages that started threads within that window and a limited set of their replies. Replies to older threads may be missing, so treat the result as a partial view rather than a complete channel audit.

For a connected service, identify the account you want the agent to use. It can find the operations available for that account. Accounts from the same provider remain separate, and an unavailable account does not cause a silent switch to another one. Each action follows the selected account's permissions and approval requirements.

A provider can expose more than one connector method. For example, one method may authorize a remote MCP server while another uses a restricted API credential; the chosen method determines the external operations available to the run.

The agent can read a public webpage when its URL is in your latest message or appears in a web search result from the current run. Disabling web search for a message also disables webpage reading. Reads return a limited amount of content, and webpage text remains untrusted evidence.

One message can start one Deep Research request. Include the scope and questions together so the agent can research them as one task and use the findings for follow-up analysis.

A dedicated Teams identity follows the same separation: creating its app does not activate a channel or authorize an external send. Where available, install it in a team, activate verified standard channels for that agent, and approve the Microsoft permission before enabling Follow replies. See Teams agent setup.

Availability is not activation

A capability moves through distinct states:

1. It exists in the platform or workspace catalog.
2. A workspace administrator installs a skill or connects a credential.
3. A project activates a specific skill version, inherits a connector credential by default, or removes that connector locally. Conversationally created agents instead activate only their reviewed connections and do not inherit later workspace credentials.
4. The run's profile and tool settings include it.
5. Runtime policy allows the exact action, asks a person, or denies it.

In chat, ask the agent to find an available connector, including a custom MCP server or HTTPS API connection installed in the workspace. Workspace connections are normally available to projects by default. If a project removed a connection, the agent can show an Attach card for that specific account. You must confirm the card before access is restored.

For models, a new platform catalog entry satisfies only the first step. It appears in Workspace settings → Models with a NEW label for its first 30 days, but an administrator still decides whether that workspace may select it.

An agent uses the activations on its home project. An automation or dashboard uses the activations on the project selected for future runs. Changing an activation affects later runs; it does not rewrite the event history of earlier executions.