Agents
A configured teammate you staff once and reuse across threads, channels, and schedules.
An agent is an AI teammate that you give a role and a job to, and equip it with the tools, context, and access it needs to complete it at your quality bar. You shape it once, then the same teammate shows up in a thread, email, or a Slack channel delivering a Monday report without you rebuilding the briefing from scratch.
The agent carries its identity, methods, and standing context into each run. The thread is still where the agent completes the work. The agent is who shows up.
You do not need every layer on day one. Start with a job worth repeating, then add tools, knowledge, and triggers as the role earns them.
A role worth staffing
Use an agent when Hyperagent should own a recurring responsibility, not only answer one prompt. If you keep asking for the same kind of result, with the same tools and standards, that pattern deserves a named role. The agent becomes employable when it can carry the job, context, tools, and ways to start work without a fresh briefing.
Every agent should be equipped with a job description, the tools it needs to do the work, and the context it should carry into each run. The cards below show three example agents with their job, context, and tools.
Pipeline Lead
- Job
- Keep leadership honest about pipeline risk before the Monday forecast.
- Context
- Stage definitions, at-risk thresholds, forecast narrative skill, board metrics format.
- Tools and integrations
- Salesforce, warehouse or Sheets, Slack for #revops.
- Invocations
- Monday schedule, @PipelineLead in #revops, CRM stage webhook.
Leadership Brief
- Job
- Turn scattered updates into a tight leadership brief on a reliable cadence.
- Context
- Org priorities, voice guide, meeting cadence, open decisions log.
- Tools and integrations
- Gmail, Docs or Notion, calendar, Slack.
- Invocations
- Weekly schedule, Slack for leadership channel.
Renewal Watch
- Job
- Notice account health changes before renewal conversations go sideways.
- Context
- Health score rules, escalation playbook, customer voice notes.
- Tools and integrations
- CRM, support inbox, Slack for the CS channel.
- Invocations
- Live Mode health watch, Slack in CS channel, renewal webhook.
Every run has a thread
A run is one time the agent does the work. The messages, tool calls, files, decisions, and outputs always live in a thread.
Invocations decide how the run starts. Integrations decide which connected systems the agent can read from or write to. The role stays the same even when the route changes.
A person starts the run
Open a thread when you want the full workspace. Use Slack or Telegram when the request already lives in a team conversation.
A timer or system starts the run
Use schedules for recurring deliverables. Use Live Mode for monitoring. Email and webhooks start a run when another system owns the event.
What you configure
Agent settings answer practical staffing questions: who this role is, what it can use, what it knows, how it should think and spend, where a run can start, how much freedom it has, and how you review what happened.
The cards below follow one RevOps agent so the settings feel like a real staffing decision, not an abstract checklist.
Who is this agent?
Name, icon, description, and system prompt. Role, tone, decision style, standards, and boundaries.
What can it use?
Systems where the data and delivery live, plus research and creation tools. Connecting an account is not enough; the agent must be allowed to use it. See Tools and integrations.
How should it produce the output?
Repeatable methods for this job: how to review the pipeline, how to spot risk, how to write the update.
What context can it bring in?
Facts and standards the role should not need re-explained every run. Controlled by knowledge access.
How much should it think and spend?
Choose the model after you choose the job. Judgment-heavy forecast review can use a stronger model; recurring read-heavy checks can use a leaner one. Swap the model without rebuilding the role.
Where can a run start?
Threads, Slack, Telegram, schedules, Live Mode, email, and webhooks. Invocations.
What needs review?
Approvals and autonomy: whether the agent runs end-to-end or pauses before sensitive external actions. Unattended schedules have their own write rules.
What has it done?
Recent threads, usage, and cross-channel runs so you can inspect, continue, and debug real work.
How the role improves
Agents get more useful when repeated work stops living only in chat history.
- Skills capture methods: research process, report format, voice, or how to use a system the same way every time.
- Knowledge access controls what context the agent can see and whether conversations can change what it knows. Standing facts often live as memories.
- Rubrics define what good looks like so you can evaluate against a standard instead of vibes.
When other people should run the same role, share it through a team and set knowledge access first. Most channel-facing agents should start with a narrow knowledge boundary rather than access to every personal memory.
FAQs
An agent is the configured teammate: identity, instructions, tools, skills, knowledge, controls, and invocations. Threads are where individual runs happen. Skills are methods the role can call. As you teach the agent how your team operates, that context carries into the next thread, channel, and trigger.