Skip to main content
Hyperagent
ConceptsAgents

Configuration

Set up each part of an agent — its brief, autonomy, knowledge, integrations, doorways, and tools.

You want an agent to produce work you recognize, even when the request arrives next week or through a different channel. Its configuration is the durable contract behind that consistency: the responsibility it owns, the standards it follows, the resources it can use, and the boundaries it works within.

Configure the role, not one assignment

An agent's configuration describes how it should work across many jobs. The request, source material, and finished output for one job belong in its thread.

Everything below lives in one place. Open Agents in the sidebar and click your agent: the configuration tabs run across the top of its page — Instructions, Autonomy, Knowledge, and Integrations, with Invocations and Tools under More. The sections here follow that same order.

Set up each part

Give it a brief and a model

Instructions are the role itself: who the agent works for, what finished work looks like, and the judgment calls it should make without asking. The model settings underneath decide how much thinking each new thread starts with.

The Instructions tab of an agent: a System prompt editor holding the agent's standing brief, above a Model and limits section with Model and Subagent model dropdowns, a Budget limit per query switch, and a Turn timeout set to 4 hours.
The standing brief on top, the model and its limits underneath.

On the agent's page, open the Instructions tab:

  • Write the System prompt — the responsibility the agent owns, the standards its output must meet, and how it should decide when you're not there. Keep reusable methods and standing facts out of it; those belong in skills and memories, where they can grow without a prompt rewrite.
  • Under Model and limits, pick the Model new threads start with, and the Subagent model for workers it dispatches. Match the compute to the work, not the agent's title — see Models and compute.
  • Turn timeout caps how long one run may go before it's stopped; runs inherit it unless their invocation sets its own. Budget limit per query caps spend per request.

Decide what it may do on its own

Reading and drafting carry different consequences from sending messages or changing records. Autonomy sets the default posture once, from the consequences of the work.

The Autonomy tab of an agent: a When you're in conversation control set to Ask first, a note that scheduled and live runs follow per-schedule rules, and an Agent delegation section set to Delegate to select agents with four named agents and an Ask for approval toggle turned on.
Conversation posture on top, delegation and its allowlist underneath.

On the agent's page, open the Autonomy tab:

  • Set When you're in conversation to Auto (runs end-to-end) or Ask first (pauses for your approval before sensitive actions). Ask first needs you present to answer, so it applies in conversation; any thread can override it for itself. Scheduled and live runs are governed separately, by each schedule's own rules in Invocations.
  • Under Agent delegation, choose whether this agent may hand work to other agents, and to which ones — an explicit allowlist, or a mode that includes your other agents automatically. Leave Ask for approval on to see each handoff before it runs. See Other agents for how a delegated run works.

Choose what it knows and how it learns

Knowledge is what the agent brings to the work beyond its prompt: the memories and skills it may reach, the documents it always carries, and what it's allowed to keep from its own runs.

The Knowledge tab of an agent: four Knowledge profile cards named Synced self-learning, Curated, Standalone self-learning, and Custom, with Synced self-learning selected, above a Self-learning section with a Learns automatically switch and per-type rows for Memory, Skill, and Prompt suggestions and Agent configurations.
One profile card sets the whole posture. Custom opens every control below it.

On the agent's page, open the Knowledge tab and pick a Knowledge profile to define how the agent learns. Synced self-learning shares your full library and learns as it works; Curated sees only what you add and doesn't learn on its own; Standalone keeps what it learns to itself; Custom lets you set each control yourself. See Knowledge access for more detail.

Give your agent the right context

Further down the Knowledge tab: a Memories section choosing which memories the agent sees and where it saves new ones, a Skills section with a global-skills toggle and five attached skill chips, and a Context files section pinning two prep documents.
What it recalls, the methods it can run, and the documents it always carries.

Connect the services it works in

Integrations are the external systems the agent may act in — email, calendars, CRMs, databases. Each card is a service; each chip under it is an account the agent may use.

The Integrations tab of an agent showing nine active services as cards — Slack, Airtable, Granola, Google Docs, Gmail, Google Drive, Google Calendar, Twitter/X, and Apollo.io — each listing the connected accounts the agent may use.
One card per service, one chip per account the agent may act as.

On the agent's page, open the Integrations tab:

  • Click + in the corner to add a service, or + Add account on a card to connect another account for one it already has.
  • Remove an account chip to narrow the agent to the accounts its job actually needs. Start from the responsibility and grant no broader.

Browse what's available in Integrations, or go straight to Slack, HubSpot, Databricks, or custom MCP servers.

Bring your agent to where your work is

The same configured role can be reached from a thread, a schedule, Slack, email, a webhook, or another agent. Each row on this tab is one doorway, with its own setup.

On the agent's page, choose Invocations:

  • Thread is on from the start — that's chatting with the agent in the app.
  • Choose how and where the agent should start and deliver work: on a schedule, through Live mode, in Slack or Telegram, by email, or through another invocation.

Learn more about Invocations to pick the right channel for your agent, including Telegram.

The Invocations tab of an agent: rows for Live mode with a Set up button, Thread with a toggle, Other agents with an audience dropdown, Slack with Add to channel, Telegram with Configure, and Scheduled, Webhook, and Email rows each with a Create button.
Every way work can reach this agent, one row each.

Enable its built-in capabilities

Tools are what the agent can do directly — search the web, drive a browser, run code, generate media. Instructions define the responsibility; tools decide which parts of it the agent can execute itself.

  • Toggle each capability on or off. They're grouped — research, browser, data and code, documents, media — so related tools travel together.
  • Use Smart pick to have a sensible set chosen from the agent's role, or All / None to start from either end.
  • Enable the smallest useful set: add a tool when the work requires it, not because it might be useful someday.

Go deeper on research, the browser, data and code, webpages and slides, or media generation.

The Tools tab of an agent with 19 active tools grouped by capability: a Research group holding Search, four Exa tools, and Thread Search, and a Browser group with persistent sessions and saved logins, with All, None, and Smart pick controls in the corner.
Toggle capabilities individually, or let Smart pick choose a set for the role.

Test it before you put it on call

A configuration is a working hypothesis about how the agent should perform. Test it with real work before teammates or automations depend on it.

01 · Representative work

Run the job by hand

Give the agent a realistic assignment with the source material, ambiguity, and quality bar it will face in practice. A polished demo prompt hides the gaps you need to find.

02 · Evidence

Audit the thread

Inspect what the agent read, which tools and integrations it used, where it paused, and what it produced. Fix the configuration from evidence in the run rather than from the final answer alone.

03 · Durable change

Fix the right layer

Clarify the role in Instructions. Save a repeatable method as a skill, a standing fact as a memory, and larger source material as a document.

04 · Real conditions

Test the actual doorway

If the agent will run from a schedule, Slack, email, or another invocation, test it there. Unattended work exposes missing context, permissions, approvals, and delivery choices that an interactive thread can hide.

Configuration changes apply to new threads

A thread keeps the instructions, model, and runtime it started with. Test edits in a new thread, and use configuration history to restore an earlier version when a change misses the mark.

FAQs