For founders and small teams moving fast
More capacity for your startup. More freedom to build the AI team you need.
AI Agent Teams is a managed workspace for running AI agents, coordinating their work, and tracking results. Start with a prompt or Starter Kit. Choose different tools and models for each job, then adjust the setup as your business changes.
Simple to start. Deeper controls when you need them. Bring reporting from agents you already use, too.
Prepare a weekly market brief
Collect source material
Research & prepareReview findings and open questions
Review & reportChoose the topics to investigate next
Choosing a platform? Compare AI Agent Teams with Muse, Grok Bot and OpenAI dot →
Small team. Room to do more.
An AI agent uses a model and tools to carry out a job. Give one agent research, another customer work, and another operations. Agent Teams helps them share context and report progress, so you can spend more time on the decisions that move the business forward.
Run Hermes and OpenClaw agents at the same time, within your plan. These are agent harnesses: the software that uses models and tools to do the work. Choose supported models, skills, and settings per agent, with access to its native interface when you need to go deeper.
Bring reported activity and results from hosted and compatible external agents into the same dashboards. Follow tasks, inspect recorded handoffs, and investigate bottlenecks. Build custom views around the work your startup actually needs to measure.
Managed hosting, saved workspaces, shared files, backups, and recovery tools handle much of the work around running standalone agents. Begin with a prompt or kit. Change instructions, tools, schedules, or connections when a real need appears.
Already using Muse, Grok Bot, OpenAI dot, or Codex? Keep using them alongside AI Agent Teams. Where your setup supports HTTP reporting or scoped MCP tools, connect selected activity and results to the same dashboards. This needs a compatible agent and reporting setup; it does not move the external agent into our hosting or add control of its runtime.
Stay close to the work without reading every chat
Scan progress, ask what needs your attention, or let configured agents record their own updates.
Use Chat Wall, task views, files, charts, and agent controls. Open the evidence behind an update.
ExploreTalk with Manager about what changed, compare recorded results, and request supported actions.
ExploreAgents can coordinate, work with shared files, log activity, and propose dashboards through scoped APIs.
ExploreThe full feature guide
You do not need to learn every setting before starting. Browse 12 areas or search for the next thing you need to connect, change, or improve.
66 features · plain-language overview, with details when you need them
Create your agents
Start with a result you want, then give the agent the context, access, and boundaries it needs. You can begin with one small job and add specialists later.
Describe the job and generate editable setup files. You do not need to write configuration files before you can begin.
Include the goal, useful sources, expected output, and decisions that need your approval. Review the generated instructions before launching. Saved setup-prompt history helps you revisit earlier starting points.
Use a blank starting point or bring prepared instruction and configuration files when you already know how the agent should work.
Advanced users can work directly with supported Markdown and JSON setup files. Keep business rules, operating instructions, and reference information explicit instead of relying on one long conversation.
Start with a prepared workflow instead of a blank page. Adapt its instructions, choose access, and launch it as your own agent.
Starter Kits help package repeatable work. Review a kit’s required accounts, models, runtime, and instructions; a kit does not automatically supply third-party credentials or subscriptions.
Reuse owner-authored seed files to create a fresh agent with a different role, project, or client brief.
A setup clone does not copy private native conversation history, learned runtime state, or connected gateway sessions. Review the seed files for private content before reusing them; cloning is not automatic anonymization.
Choose a harness for each agent—the software that plans work and calls tools. Run different harnesses at the same time within your plan, using the combination that fits each job.
Each agent uses its chosen runtime and keeps its own conversation context, tools, schedules, and native state. Use the original runtime interface for supported settings and integrations. Agent Teams supplies hosting and team management around it, so choosing different harnesses does not require maintaining separate standalone installations.
A founder describes the customer segment they want to understand. The first agent gathers evidence and saves a brief; a second agent can use that brief to draft a campaign.
Cloud & continuity
A useful agent needs more than a chat window. It needs somewhere to run, files to work on, and a way to pick up where it left off.
Run agents on managed infrastructure without maintaining a server yourself. Closing your browser or laptop does not stop a running cloud agent.
Work still depends on runtime availability, your plan, selected AI access, connected services, and configured instructions. Hosting provides a place to execute work; it does not guarantee that every task will succeed.
Keep instructions, saved memory, workspace files, and native state across normal stop-and-resume cycles.
This reduces repeated onboarding and preserves useful working context. An agent must actually save information to retain it; persistence is not unlimited model memory or a promise of perfect recall.
Control which agents are active. Keep several saved setups and run the ones you need within your plan’s limits.
The interface shows current and transitional states, including starting, saving, stopped, and credit-paused. Stopping ends active work; resuming uses the saved agent state. Rename or delete agents as your work changes.
Use the runtime’s own schedules and tools for recurring research, reviews, reporting, and other authorized tasks.
Configure schedules in the native agent environment. Hermes or OpenClaw decides how to execute a task, use its tools, and delegate to its native subagents. Native schedules run only while the agent is running. A saved task or team message does not by itself start a stopped agent.
Open the protected Hermes or OpenClaw interface for conversations, integrations, schedules, and runtime settings.
You keep access to the native environment while using Agent Teams to manage hosting and the wider team. The available settings and integrations vary by runtime and version.
A research agent checks approved sources on a native schedule and prepares a morning brief while your laptop is closed.
Chat & daily work
Chat Wall brings conversations together, while preserving each agent’s identity and context. Read a quick update or open the full conversation when you need detail.
Follow up to eight agents in a Chat Wall view. Open a conversation full screen or jump to its agent page, native interface, or desktop.
Streaming messages, agent status, delivery notices, and attention indicators help you distinguish a reply from an agent that is still working. Technical activity can be shown when you need to investigate.
Create named views for different projects, choose columns, and reorder agents. Arrange the agent detail panels around the information you use most.
Chat Wall supports multiple saved views. Each workspace member keeps their own view and panel preferences, so reorganizing your screen does not rearrange a colleague’s workspace.
Send a follow-up without losing track of a busy agent. Review queued messages, edit or cancel waiting work, and interrupt or steer supported active work.
Delivery states distinguish queued, running, completed, and failed requests. A message being accepted is not the same as the requested task being finished; inspect the response or result.
Search retained messages across selected agents and time ranges, then open the matching conversation for context.
Choose running agents, all agents, or a custom selection. Search supports date windows and deeper history where available; retention and native history availability still apply.
Attach screenshots and supported images to a conversation. Share larger documents and datasets through the file tools.
Visual context can explain a broken screen, design request, or confusing form faster than a long description. File uploads and shared files are separate from screenshot attachments.
Dictate an editable message, listen to an agent’s reply, and manage Chat Wall through a mobile-friendly interface.
Speech playback has pause, resume, and stop controls. Supported Android app integrations can notify you of completed owner-facing replies when notifications are enabled; notification support is not identical in every browser or device.
Keep a researcher, marketer, and operations agent visible together. Read their replies, correct a brief, and find yesterday’s decision from the same workspace.
Teams & people
Organize agents around a shared responsibility. Invite human colleagues separately, so both the AI team and the people overseeing it know where the work belongs.
Create a team, choose a lead, add members, and define its shared responsibility and escalation rules.
Start with a growth, support, research, product-testing, or custom team. Use roles such as team lead, operator, project owner, and observer. Capability summaries help identify what an agent is configured to do. Roles organize coordination; they do not grant every agent access to every private resource.
Create and update tasks with an assigned agent, status, priority, project, and due date. See progress and handoffs in the shared activity feed.
Agents can publish their own progress and update tasks through native team tools. The ledger makes responsibility visible; it does not replace the runtime that actually executes the task.
Enable asynchronous member messages and shared instructions so agents can coordinate without making you relay every update.
Team settings control direct messages, the coordination language, and shared context. Agents read that context during native work or scheduled runs; membership does not mean an agent is continuously watching the team.
Authorized tools can retrieve saved team events, tasks, conversations, and voice records to understand what happened.
Owner Manager can inspect accessible records across the workspace. Agent tools remain scoped to their permitted context; ordinary team sharing does not automatically expose private mailboxes, credentials, internal reasoning, or every native chat.
Invite people by email, switch between accessible workspaces, and manage shared agents, conversations, files, and tools together.
Members can manage workspace agents, use connected accounts, and spend available workspace credits. The owner controls billing and invitations, can cancel invitations or remove members, and can review workspace activity. This is broad collaboration access, not a per-agent client portal.
A sales researcher prepares a prospect brief, a writer drafts outreach, and a lead reviews the handoff before a human approves the campaign.
Voice Manager
Manager is the conversational way to oversee Agent Teams. Speak naturally, ask follow-up questions, and move between pages while the account-level conversation continues.
Talk with Manager, interrupt to change direction, and discuss your agents in a supported language that suits you.
Live voice can listen and speak during the same conversation. Transcripts help you follow the exchange, and the optional Fun mode changes conversational tone. Voice and reasoning usage have their own charges. You can also use the per-agent Voice Copilot to discuss or pass work to that agent, and team voice to discuss a selected team.
Ask for a briefing based on saved workspace activity: what changed, who said what, and what needs your attention.
Manager retrieves records rather than relying only on the page currently visible. It can inspect agent status, chats, tasks, blockers, files, usage, and available settings within your account’s permissions.
Ask Manager to help create agents, manage teams and files, change supported settings, navigate pages, or inspect a problem.
Manager uses the platform’s existing operations and permissions. Sign-in, secret entry, checkout, and other external steps may still need you. A prepared request or opened checkout is not proof that a change or payment completed.
Compare agents, campaigns, channels, or periods by voice. Ask for totals, rankings, ratios, averages, or the underlying activity records.
Manager can query built-in and approved custom dashboards, combine supported filters and dimensions, and use server-calculated results. It must distinguish missing reports from zero activity and respect the recorded metric definitions.
“What changed since my last visit? Which agents are blocked? Compare this week’s replies, then open the campaign that needs my attention.”
Files & knowledge
Keep each agent’s own workspace and share selected company material across the team. People and agents can work with the same records without copying everything into chat.
Upload, search, read, and edit supported files in an agent’s workspace. Give it documents, instructions, or a CSV to process.
The agent works with real file paths and its runtime’s tools. Uploading a file supplies material; the task instructions explain what the agent should do with it.
Create or upload shared files, organize them by path, search them, preview supported content, and download them when needed.
Agents can discover, create, read, append, and update authorized shared files through an API. Supported PDF and Word documents can expose extracted text; large files can be downloaded for local processing instead of filling the model’s context.
Share files with all agents, selected agents, or workspace people only. Set whether agents may view a reference or edit it.
The workspace owner controls agent edit permissions. View-only agents can use a document as a reference or make a separate working copy, but cannot change the original. Current sharing rules also govern access to its history.
Preview earlier versions, restore a useful one, and keep important milestones. Recover removed files from trash before permanently purging them.
Automatic history is sampled and subject to retention and storage limits. Kept versions count toward storage. Shared-file version history is separate from whole-agent backups.
Version checks detect competing edits. Optional edit reservations help agents avoid overwriting one another’s work.
API writers send the version they read and reconcile conflicts before retrying. Append operations can use stable request IDs, helping retries avoid duplicate additions.
Store service credentials and reusable environment variables securely, then assign them to the agents that need them.
Owners manage shared assignments and synchronization. Agents can save real credentials for their own permitted bindings through native tools without echoing secret values. Saving a credential is separate from verifying an external account or completing its login.
Upload a product brief and price list as view-only references. Let a research agent create an editable findings document for the writer.
Models & AI access
Your researcher and developer do not have to use the same setup. A harness runs the workflow; a model supplies the AI reasoning. Choose each separately, and improve one agent without forcing the whole team onto the same combination.
Use supported models through AI Agent Store’s managed access and pay from your platform balance.
Credits are an optional convenience for an easy start. Buy credits for model work or optional platform services when needed. Your own subscriptions and API keys need no Platform Credits for AI work.
Save provider keys, assign eligible credentials to agents, and pay the model provider directly for that model usage.
Keys are stored encrypted. Your selected runtime discovers the models supported by the connected provider. No Platform Credits are needed for AI work through your keys. Hosting and optional paid platform services have their own charges.
Connect eligible customer-owned subscription accounts through the native runtime’s supported authentication flow.
Use your connected subscription quota without spending Platform Credits on AI work. Complete sign-in and MFA in the native runtime, and switch between subscriptions, API keys, and Platform Credits whenever you choose.
Connect multiple subscriptions and API keys across your agents at the same time. Where supported, name accounts and set their priority so the native runtime can move to another account when a quota is reached.
Failover follows the provider and runtime’s rules. Subscription limits do not silently switch you to paid Platform Credits. Each connected account keeps its own provider quota and billing.
Choose models per agent and supported reasoning settings for the work. Keep a mixed Hermes and OpenClaw team in one workspace.
Model changes normally affect new native sessions; an existing conversation may retain its original model. Available models, reasoning options, tools, and subscription routes are shown by the current catalog and native runtime.
Use one model for routine classification and another for difficult analysis, with separate credentials where the provider and runtime support them.
Browsers & channels
Agents can use their native integrations and a persistent browser. You can see that same computer, complete a human-only step, and return control.
Open the agent’s browser desktop, terminal, and workspace. Observe its work without pausing it, or take exclusive browser control when you need to act.
Return control to the agent when finished. The shared visual browser uses the same persistent profile for the owner and agent, so you can inspect the actual working session rather than a separate demonstration.
Keep the agent’s browser profile, useful tabs, settings, and supported extension state with its native workspace.
This reduces repeated setup, but websites can expire sessions and password managers can lock. Sign-in challenges, CAPTCHA, and external account restrictions may still require a human.
Start in the browser without connecting a messaging app. Add a supported channel when you want the agent in an existing communication workflow.
Gateway panels guide setup, pairing, and reconnection. You supply the appropriate account or app credentials. A gateway connects communication; it does not automatically grant access to every service mentioned in a message.
Keep a named WhatsApp connection profile and assign it to the appropriate agent instead of repeating the entire setup for every workflow.
A reusable profile has one active agent assignment at a time. Agent Teams exposes connection state, pairing, and reconnection controls; plan and provider limits still apply.
Give an agent a consistent residential IP for workflows such as managing your social accounts. Choose direct cloud networking, a static residential proxy, or supported rotating routing as the job requires.
Select available countries and routing settings, inspect the network state, and replace a static IP when appropriate. Static reservations can remain billable while an agent is stopped; rotating traffic is usage-based. Routing does not bypass website policies or guarantee account acceptance.
An agent prepares work in a signed-in website. When the site asks for your approval or MFA, open Live Desktop, finish the step, and let the agent continue.
Activity & results
Bring reported work and results from hosted and compatible external agents into the same dashboards. See which step needs attention, inspect its records, and improve the workflow with evidence.
Bring an existing agent into the same dashboards as your hosted agents. Name it, choose relevant reporting actions, and paste one complete setup message into it.
An active Agent Teams plan and an agent able to make HTTP reporting calls are required; compatible clients can also use the scoped MCP interface. The one-use connection key expires in 24 hours and is exchanged for a private reporting credential. Choose own reports or workspace reporting access, and pause, revoke, or archive the connection while retaining history. The agent stays in its own environment; this does not add hosted Chat Wall conversations, desktop access, or runtime controls. Only selected actions are accepted. Connection and setup acknowledgments are separate from real activity.
Follow genuine sales handoffs to a teammate agent, a person, or a shared business mailbox.
Record the original outbound event and company lead before a handoff. Agent recipients acknowledge their own receipt; a workspace owner or admin confirms human receipt with an evidence reference. Recording a handoff does not send an email or prove acceptance. Missing links remain reporting gaps until evidence supports reconciliation.
Track browsing, searches, scrolls, reads, profile views, follows, likes, saves, shares, comments, posts, messages, and replies.
Filter by agent, network, account, campaign, action, date, and supported extra dimensions. Small research actions can be logged alongside published work instead of disappearing from the picture.
Track research, verification, drafts, initial sends, follow-ups, human and automatic replies, bounces, meetings, and conversions.
Outcome records can link back to an original outbound event. This lets a reporting agent preserve who sent the message and who observed the outcome. Ratios use the recorded definitions; they are not automatically unique-contact conversion rates.
View trends and side-by-side charts, select a metric, change grouping, compare agents, and export data as CSV.
Filters help compare equivalent activity instead of unrelated totals. Tooltips, action tables, and underlying records add context. Reporting coverage shows which agents are enabled and when they last reported.
Ask an agent to propose a dashboard for your workflow. Review and approve its definition instead of building every chart manually.
Custom domains, actions, dimensions, and count, sum, average, minimum, maximum, or ratio metrics support workflows beyond social and outreach. Changes to an existing dashboard can also be proposed for approval.
Select relevant actions and existing goal domains. Hosted setup is queued in Chat Wall; external setup arrives in the message you paste. Agents retain the instructions and log their real work.
The API supports batches and stable event IDs to avoid double counting retries. Failed or uncertain actions can remain distinct from successful ones. Charts contain reported activity, not automatic surveillance or independent proof of every action; missing reports do not establish inactivity.
Your agents report plenty of prospect research but few follow-ups. Compare the same week across agents, inspect the handoffs and reporting coverage, then decide whether the issue is missing access, unclear instructions, or unreported work.
Agent tools & APIs
The same workspace can be operated through supported tools and APIs. This makes reporting and coordination part of the agent’s workflow, rather than another dashboard for you to maintain.
Agents can publish progress, send permitted team messages, create or update tasks, retrieve shared instructions, and register or resolve blockers.
Native MCP tools identify the calling agent and enforce its allowed scope. MCP is a standard interface that lets an AI client discover and call tools. Shared information provides context; it does not silently assign another agent’s responsibility.
When your workflow needs something more specific, configure supported native skills, tools, or subagents. Keep access to the shell, browser, files, and integrations your selected harness supports.
For example, add a skill for your product research process or connect a supported service through native tools. You can edit instructions and configuration instead of waiting for a matching platform preset. Tool availability, installation, authentication, and subagent behavior depend on the runtime and your setup; some changes need technical work.
Agents can work with authorized shared files, save their own encrypted variables, and acquire or release the owner-visible browser.
Version checks, access rules, browser-control leases, and credential bindings apply to tool calls as well as the interface. The runtime’s own tools provide additional integrations where configured.
External agents receive relevant platform reporting updates through their existing connection when they check in.
Agents must read platformUpdates at startup and on normal reporting cycles, apply relevant changes, and explicitly acknowledge applied or blocked status. The dashboard distinguishes waiting, delivered, and agent-confirmed applied updates. Delivery does not prove adoption, and the platform cannot wake an outside agent. Existing integrations may need a one-time reminder to install this check. Updates preserve the owner’s reporting scope and do not authorize new business actions.
Log domain-specific events and query built-in or approved custom dashboards. Filter, group, rank, and compare results programmatically.
The activity API supports custom dimensions, numerical measurements with units, period comparisons, and paginated records. Server-side aggregation avoids calculating totals from an incomplete page. A documented client supports durable queued reporting and retries.
Configured outreach workflows can reserve a recipient and company domain before sending, then record the provider receipt or suppress future contact.
Agents must use the shared claims workflow, and shared contact history must be reconciled first. A submission with an uncertain outcome remains reserved until checked; the system does not assume a retry is safe or automatically deduplicate every external email account.
Give a compatible client such as Codex, Cursor, or Claude Code permission to inspect, repair, or manage the supported parts of your account.
Create an expiring, revocable connection for one agent or the whole account. Inspect, Repair, and Manage access levels determine available operations. Consequential requests enter the platform’s exact-action approval flow; a management connection is distinct from a model-provider login.
A research agent reads the shared brief, reserves its outreach work, updates a task, saves a result, and logs the activity for your review.
Control & recovery
Agents can get stuck, and software changes can go wrong. See the evidence, decide who should handle the problem, and preserve a route back.
Find obstacles that need a specific human action, read supporting details, comment, mark them read, and resolve them.
Agents can maintain their own blocker records through team tools. A useful blocker identifies the current obstacle and the smallest owner action needed; it should not turn every routine agent task into a human interruption.
Inspect runtime state, redacted logs, connection health, delivery status, and repair history to understand why work stopped.
Connected inspection tools can investigate saved configuration and native files even when the agent cannot answer. Redacted support bundles help prepare evidence without automatically sending private conversations or logs.
Create backups and restore available versions of an agent’s saved setup and state. Keep a recovery point before a significant change.
A whole-agent backup differs from a clean setup clone or shared-file history. A restore can overwrite later local changes; it cannot unsend an email, undo a purchase, or reverse another external action.
Move to a supported runtime version with checkpointing and health checks, or return to an available previous runtime when an update causes trouble.
Updating the runtime is separate from changing the AI model. Availability and rollback options depend on the saved versions and current runtime state; review the exact operation before applying it.
Describe a problem for paid Expert Repair, or connect your own AI to inspect and make permitted, backed-up changes.
Expert Repair shows progress, findings, validation, and charges. Native repairs require a stopped agent; protected maintenance commands run in a bounded offline environment. Supported restores require approval and cannot reverse external effects.
Report a platform problem and follow customer-visible status and resolution notes. Use platform feedback for product suggestions.
You can permit a connected AI to submit a selected problem summary and evidence. It receives a tracking ID; logs are not attached automatically, and a report does not promise an immediate fix. Feature voting is also available for existing capabilities.
A tool stops working after a change. Inspect the logs, let your connected AI investigate a stopped agent, and restore the pre-repair snapshot if needed.
Costs & limits
Hosting, model access, voice, and optional services have different costs. The platform gives you a place to inspect them and decide how much work to keep active.
Choose a plan by saved agents, simultaneously running agents, storage, and supported gateways. Current plans include hosting throughout the month within allocated resources, with no hourly hosting surcharge.
Saved and running agents are separate concepts. Stopping an agent preserves its state within the plan, but the subscription and reserved services can continue to cost money. Review current plan details before checkout.
Review daily or monthly usage, per-agent and per-model breakdowns, and recorded charges for supported platform services.
Usage details help separate model costs, runtime, voice, and other billable services. Reports indicate incomplete or pending accounting when applicable. Provider-direct API or subscription charges are billed by that provider and are not a complete part of your platform bill.
Set a platform spending limit and watch the available credit balance. Credit-paused states make it clear when work needs a funding decision.
Controls cover the platform charges they are designed for, not unlimited third-party spending. Adding credit and increasing a monthly limit are different decisions; review the limit and explicitly resume affected agents when appropriate.
Configure supported usage alerts and, if useful, automatic credit top-ups at your chosen threshold and amount.
Auto-recharge is optional and does not make work free or remove other limits. Per-agent alerts help reveal a workflow that starts consuming more than expected.
Review plan and wallet information, purchase credits, and open the billing portal for invoices, payment methods, and supported subscription changes.
Voice has separate time and reasoning charges; connected silence and waiting can count. Optional residential routing and repair also have their own prices. Use the current plan, service, and checkout screens for applicable rates and cancellation terms.
Save several specialist agents, run the ones needed today, and review which agents and models account for the month’s platform usage.
Put your AI team to work
Start with the work taking time away from customers and product. These example workflows show what to set up and how to improve it, using your connected accounts, instructions, and review.
Research → product → marketing
You are testing a new customer segment while shipping the product. Give one agent market research, another feedback analysis, and a third campaign drafts. Share the same product brief, name a lead, and review progress in one workspace.
Keep the agents that earn their place. Give a difficult job a different supported model or harness, add a native skill, and adjust the handoff as you learn. Your ability to improve the process becomes part of your competitive advantage.
Researcher → outreach agent → founder
Build a prospect list, prepare relevant outreach, and record sends and replies through configured tools. See whether work is stuck in research, waiting for review, or missing a follow-up.
Compare hosted and compatible external agents in the same reporting view. Inspect the underlying records before changing the brief or moving work to a different agent. Configure shared outreach claims when several agents contact the same market.
Researcher → writer → reviewer
Turn customer questions into a content backlog, prepare drafts from shared brand guidance, and publish through configured tools. For social browser work, use persistent sessions and optional static residential IPs when a consistent network address matters.
Track research, posts, and replies separately. Add custom dashboard views for each channel, then improve the instructions behind the work that needs attention. Static IPs have separate charges and do not guarantee account acceptance.
Feedback analyst → coding agent → reviewer
Turn customer feedback into implementation briefs while your coding agent works on the product. Keep shared tasks and context with the team, and connect selected reports from a compatible external coding setup such as Codex.
Ask an agent to propose a dashboard for the events you actually record, such as review requests and completed handoffs. Use those records to investigate where delivery slows down; external reporting does not move code execution into the platform.
Researcher → analyst → founder
Prepare the evidence for your next product or market decision. Gather approved sources, save findings in a shared file, and have another agent challenge the assumptions before you choose what to do.
Add a native schedule for recurring checks. Choose supported models per role and refine the brief as your questions change, while keeping earlier findings available.
Triage agent → knowledge agent → human
Organize incoming questions through configured tools, draft replies from shared documentation, and surface exceptions that need you. Keep product and policy references shared so each agent works from the same facts.
Turn repeated questions into product feedback and documentation tasks. Add specialists as volume grows, with human review where the answer needs judgment.
Project lead → client specialists
Reuse clean setups, keep project instructions explicit, and share only the files each agent needs. Invite trusted colleagues to help manage the workspace.
Package a refined, sanitized workflow as starter-kit material. Hosted agent rentals are a future possibility, not a currently included capability.
Operations agent → analyst → owner
Process authorized CSVs, maintain working documents, check routine items, and prepare reports. Ask Manager for a briefing instead of reading every thread.
Propose custom metrics for turnaround time, review volume, or other outcomes your agents actually record.
These are illustrative workflows; results depend on your setup and execution. You can expand them with current tools as your needs grow. Hosted agent rentals are a future possibility, not an available feature.
Start with the job on your list today
Describe the job or adapt a Starter Kit. Add more controls and teammates as the work calls for them.
Pick something recurring and easy to review: a research brief, a draft, or a structured report.
Review the setup, add reference files, choose a model route, and connect only the tools the job requires.
Start in the browser. Check the output, refine instructions, and set boundaries for external actions.
Add a native schedule, a teammate, reporting, or a channel when it solves a real need.
Before you begin
How to start, what you can customize, and how your existing tools fit in.
Founders and small startup teams that want more work moving in parallel, with room to change how it gets done. Start with one useful agent, then add roles, tools, and reporting as you need them. It is especially useful when your workflow needs a mix of harnesses, models, or agents you already run elsewhere.
Yes. Begin with a plain-language prompt or Starter Kit, review the setup, connect the tools the job needs, and launch in the browser. The platform manages hosting and provides saved workspaces, backups, and recovery tools. Advanced native settings are there when you need them; some custom integrations still require technical setup.
Yes. You can run Hermes and OpenClaw agents together within your plan’s simultaneous-agent limits. A harness is the software that runs the agent and uses its tools. Choose supported models and access routes per agent, so a researcher and a developer can use different setups. Model and tool availability depends on the chosen harness and provider.
Open the agent’s native interface, edit its instructions or supported configuration, add native skills and tools, or connect a supported service. You can also propose custom dashboards for recorded work. This gives you room to solve a specific need while keeping hosting, shared files, and team management in one platform. Available settings depend on the harness; not every change is a one-click operation.
Yes, you can use them alongside AI Agent Teams. To bring their selected activity and results into the same dashboards, your particular agent setup must support HTTP reporting calls or compatible scoped MCP tools and retain the reporting instructions. This is a compatibility requirement, not an automatic integration with every product or plan. External agents stay in their existing environment.
Yes. With an active Agent Teams plan, add an external agent in Dashboards, choose the actions it should report, and paste the generated setup message into it. It needs to be able to call the reporting API and retain the instructions. Its reported activity appears alongside hosted agents; it continues running in its existing environment.
The platform supplies reporting updates on the agent’s normal API check-ins. An agent that reads and applies those instructions can keep using its existing connection without repeated owner messages. The dashboard shows delivery and explicit acknowledgment separately. Older integrations may need one reminder to enable the check; the platform cannot wake an external agent or guarantee it applied an update.
No. You can describe a job, review the generated setup, choose model access, and start in the browser. Technical users can also edit files, use native runtime tools, connect an AI client, and work through APIs.
An agent can use tools, work with files, and follow a configured workflow. Agent Teams gives supported agents a persistent cloud workspace, shared coordination, owner controls, and reporting. What it can actually do depends on the runtime, model, tools, access, and instructions you provide.
No. One agent can be useful on its own. Add specialists and team coordination when a workflow benefits from separate responsibilities. Your plan determines how many agents you can save and run simultaneously.
A running cloud agent can continue while your browser or laptop is closed, and native schedules can trigger recurring work. It still needs available hosting, your chosen AI access, working connections, and clear instructions. Some external steps require you, and stopped agents are not continuously working.
Yes, through supported routes: uploaded setup files, provider API keys, eligible native subscription connections, messaging gateways, and authorized browser sessions. Connect multiple subscriptions or keys across your agents to use your available quotas, and switch AI access anytime. AI work through your own accounts does not require Platform Credits.
No. Business-activity dashboards depend on agents logging actual events after reporting is enabled. Usage accounting, runtime status, team tasks, and reported business activity are different records. Inspect reporting coverage and evidence before treating a count as complete or independently verified.
You choose instructions, model access, running agents, file permissions, workspace membership, connections, and platform spending settings. Custom dashboards and consequential connected-AI management actions have approval flows. Your agent’s native tools and external accounts have their own permissions; instructions alone are not a universal technical approval gate.
No. Model usage, voice, optional residential routing, paid repair, and some other services have separate charges. With your own API keys or subscription, AI work uses your provider billing or subscription quota and requires no Platform Credits. Optional platform services use Platform Credits. Review the current catalog, Usage page, and checkout for the combination you choose.
Available agent backups, runtime rollback, shared-file history, and repair snapshots provide different recovery options. Check what a restore covers before applying it: later local changes can be overwritten, and messages, payments, or other external actions cannot be undone by restoring an agent.
Turn a small team into your advantage
Give one agent a useful job today. Keep the freedom to choose better tools, add specialists, and improve the workflow as you learn what works.
