Skip to content

Agent workspace for agencies

Run client work through one accountable AI agent.

Versabot's agent researches, drafts, runs browser and code tasks, schedules recurring work and prepares client reports across every client you manage. Anything that leaves the building waits for your approval, and every run leaves evidence.

7-day trial with a card on file and 300 usage credits. Then $49.99/month unless you cancel.

Review last week's results for our example client, check their competitor's pricing page, and draft the weekly report.
Read attributionBrowser run · read-onlyDrafted report · not published
I read verified results for the period and visited the competitor page in a sandboxed browser. The report draft is saved under the client. Nothing was sent or published.

Follow-up email · waiting for approval

Exact content
Review & approveEdit draft
Ask the agent…Sonnet 5.5 · High
Illustrative example of the workspace. No real client data.

How it works

From request to reviewed delivery

The agent does the legwork. You stay in charge of what goes out and what clients see.

  1. 1

    Set up clients and connections

    Add the clients you serve, invite staff with scoped roles, and connect a mailbox or LinkedIn. Credentials are entered in secure forms, never in chat, and stored encrypted per organization.

  2. 2

    Ask for the work in a thread

    Threads keep context per client and project. Pick the model and reasoning effort for each thread: OpenAI GPT models or Claude Haiku, Sonnet and Opus.

  3. 3

    Approve what leaves the building

    Emails, review requests, interactive browser actions and code runs wait for explicit approval of the exact content. Editing a draft resets its approval.

  4. 4

    Deliver and measure

    Publish reports to a client portal with the run evidence behind them, and tie results to verified receipts rather than estimates.

Capabilities

What the agent can do today, labeled honestly

Each capability shows its real status, so you know what works now, what needs your own account, and what is still coming.

Live
released and verified in production
Needs your account
works after you connect your own provider account
Test mode
runs end to end, but no real money moves
Not yet available
on the roadmap, not available today

Agent threads and projects

Live
One agent that knows your clients, with pinned threads, projects and saved history.

Research profiles

Live
Company and person profiles with sources and confidence, saved to the right client.

Content studio

Live
Social, blog, email, ad and landing-page drafts plus image generation, kept as reviewable drafts.

Sandboxed browser runs

Live
Real Chromium in an isolated sandbox. Read-only by default; interactive steps need approval.

Approved code execution

Live
Calculations and data work in a sandbox, approved run by run.

Schedules

Live
Recurring research and report drafts with pause, resume, run-now and a budget per run.

Client reports and portal

Live
Draft, review and publish reports that clients see in their own scoped portal.

Email outreach

Needs your account
Send from your own mailbox over direct SMTP/IMAP with approval, caps and opt-out handling.

Optional reply handling

Needs your account
Off by default. Manual, AI drafts, a fixed acknowledgement or tightly bounded AI replies.

Review requests

Needs your account
Neutral requests with the same public review link for every rating. No review gating.

Performance fee statements

Test mode
Percentage-of-verified-revenue agreements, audits and statements. Payments run in test mode.

Ad and social publishing

Not yet available
Direct posting to ad and social platforms, plus SMS and WhatsApp delivery, are not available yet.

Accountability

Built so you can stand behind the work

  • Exact-content approval for outgoing email, review requests, interactive browser steps and code runs.
  • Six roles (owner, admin, member, auditor, client admin, client viewer), with staff restricted to the clients they serve.
  • Browser runs keep steps, visited URLs and screenshots. Reports can cite that evidence.
  • Credits are reserved before costly work and settled on measured usage. Unused holds are returned.
  • Interrupted or uncertain actions are flagged for review and never silently replayed.

What we don't claim

  • Versabot is not an all-in-one CRM, funnel builder and phone-system replacement.
  • Attribution counts verified receipts only. It does not prove causal lift or every offline conversion.
  • Posting directly to ad and social platforms, SMS and WhatsApp are not available yet.
  • Google Business review monitoring and reply posting are not connected yet.
  • Performance-fee collection runs in test mode. No real money moves through it today.

Who it's for

For teams that deliver work for clients

Marketing and growth agencies

Run research, content, outreach and reporting for many clients from one workspace, with client-scoped access for your team.

Independent operators

Consultants and fractional marketers who need an extra pair of hands for recurring client work, without giving up review.

Service businesses with an in-house team

Keep review requests, follow-up email and competitor checks moving with a clear record of what ran and what it cost.

Models and keys

Your choice of model. Usage measured, not guessed.

Pick the model per thread

Live
OpenAI GPT models, or Claude Haiku 5.5, Sonnet 5.5 and Opus 5.5 routed through OpenRouter, each with selectable reasoning effort that carries into scheduled work.

Bring your own key

Live
Add a validated provider key to your workspace and LLM usage costs zero platform credits. There is no silent fallback to our key. Browser, voice and outreach costs still apply.

Assistants still included

Live
Existing Versabot assistants and their chat, voice and plugin setups remain available as a tool inside the workspace.

Pricing

Start with a trial. Pay for measured usage.

One credit equals $0.01 of usage, measured from actual token and provider cost. New accounts start on Personal with a 7-day trial.

Personal

$49.99/month

500 usage credits per paid month

Pro

$99.99/month

1,500 usage credits per paid month

Business

$399.99/month

10,000 usage credits per paid month

Full pricing, trial terms and BYOK details →

FAQ

Common questions

Is Versabot a chatbot builder?

Not anymore at its core. The central product is an agent workspace: you work with one agent in threads, and it uses tools such as research, content, sandboxed browser and code runs, schedules, outreach and reporting. Versabot's original assistants are still available as one of those tools.

Will the agent send emails or publish anything on its own?

Not by default. Outgoing email and review requests require approval of the exact content, and reports stay drafts until someone publishes them. Automatic replies exist only if you turn them on for a specific connection, with named senders, a daily cap and an expiry.

How is usage priced?

Hosted AI usage is measured from actual token and provider cost and charged in credits, where one credit is $0.01. New accounts start with a 7-day, card-required trial that includes 300 credits, then $49.99/month unless canceled. With your own model API key, LLM usage costs no platform credits.

Can Versabot prove the results we deliver?

It can show a traceable chain from a verified receipt back to a conversion, lead and tracked click, and it excludes anything it cannot verify. It does not claim causal lift or automatically prove every offline or offsite conversion. Payment collection for performance fees currently runs in test mode.

Put the agent to work on one client first.

Connect what you already use, ask for the work in plain language, and approve what leaves the building.

7-day trial with a card on file and 300 usage credits. Then $49.99/month unless you cancel.