Decide what the agents do alone, and what waits for you.
For each decision type, choose Autopilot, Approve or Off. Anything on Approve goes to a reviewer queue until a person signs it off. Every AI action is logged with who asked for it, the data it used and the rule it followed, and decisions made on Autopilot can be undone.
No credit card. 500 free execution actions to start.
By signing up you agree to graph8's Terms and Privacy Policy.
You pay execution credits for what the agents run, not per seat.
What Control and Safety Layer includes
Each feature works in the app. Where supported, your team can also use it through the MCP server or the CLI.
Autopilot, Approve or Off
Pick one for each decision type. Autopilot runs it, Approve waits for a person, and Off keeps it manual.
Reviewer queues
Send sequences, content, contract drafts or any other AI output to a reviewer before it goes out.
Audit log
Every agent action, content edit, sequence change and access event is logged.
Undo and pause
Undo a decision the agents made on Autopilot. Pause a sequence while it is sending.
Compliance scoring
A compliance score for each AE and each team, against your playbook and stage requirements.
Brand compliance check
AI-written content goes through brand-voice and legal review before it is published.
Consent rules by region
EU consent policies, retention windows you set, and limits for each channel.
Decision attribution
Each AI decision records the user who asked for it, the data it used and the rule it followed.
Forecast variance audit
When a forecast misses, the log shows which signals fed into it.
Related parts of graph8
Workflows, Skills and Routines
Build the automations the agents run: triggers, steps, approvals and schedules.
Explore In AI AgentsYour Twin
A twin of each rep, trained on their own mail, calls and LinkedIn.
Explore In AI AgentsCRO Copilot
Forecasts pipeline, flags at-risk deals, drafts the weekly review.
Explore In AI AgentsSDR Agent
Builds territory lists, drafts sequences, routes replies.
Explore In AI AgentsCSM Agent
Watches usage, flags churn, drafts renewal briefs.
Explore In AI AgentsDeal Agent
Proposals, redlines, pricing comparables, case studies.
Explore In AI AgentsSEO and AEO Agent
Drafts pages for search and tracks citations in AI answers.
Explore In AI AgentsContent Agent
Articles, ads, landing pages, enablement, on brand.
Explore In AI AgentsPersonalized Content
Dynamic web and email content per account.
ExploreWhat is AI agent governance?
AI agent governance is the system of policies, approvals, audit trails, and recovery controls that determines what an AI agent may do. graph8 applies those controls to revenue work: for each decision type, the team chooses Autopilot, Approve or Off, so an action runs on its own, waits for a person, or stays manual.
- Set each decision type to Autopilot, Approve or Off.
- Attribute each action to the user, data, policy, and agent that produced it.
- Keep an audit log of every action, and undo decisions made on Autopilot.
- Apply regional consent and brand-compliance rules before execution.
What does AI agent governance control?
It controls permissions, approval requirements, data access, audit retention, policy checks, and recovery paths for agent actions.
Can graph8 require a human review before an agent acts?
Yes. Set a decision type to Approve and the action waits in a reviewer queue until a person signs it off. Autopilot runs it without review, and Off keeps it manual.
Are graph8 agent actions auditable and reversible?
Yes. Every action is logged with the user, data and rule behind it, and decisions made on Autopilot can be undone. Sequences can also be paused while they are sending.
The agents these controls apply to
Each agent has one job. They all work from the same data, and every one of them follows the Autopilot, Approve or Off setting you choose.
Research
Researches each account and buyer before anyone reaches out.
Signals
Watches for intent, site visits, hiring and job changes.
Enrichment
Fills in missing contact and company data.
Messaging
Writes the emails, messages and call scripts.
Outbound
Runs the outbound campaigns and moves on to the next account.
Scheduling
Books meetings and handles reschedules.
Reporting
Reports replies, meetings and pipeline.
RevOps
Keeps pipeline stages, fields and the pipeline model correct.
You pay for what the agents run. Every user is included on the Team plan.
Execution credits send, call, and run agents. Contact credits reveal and enrich the people you target. Three ways in.
A free entry point to the full platform. No credit card.
- 1,000 contact reveals to start
- 500 execution actions free
- Full platform access, no card
- Then $0.05 per credit
Unlimited contact data, in the tools you already use.
- Unlimited contact data, fair use
- 2,500 execution credits a month
- Priced per user, not per org
Unlimited users and data. Every app, one bill.
- Campaigns, dialer, AI voice, and AI workflows
- Meetings routed and booked for you
- 10,000 execution credits a month
- Unlimited users, no seat fees
- 7-day free trial, no credit card
Everything in the Team plan
$99 / mo, all includedThe $99 Team plan is the full platform: everything below, for the whole org. MCP Unlimited and Pay as you go are lighter entry points with usage and seat limits.
What the agents run
10,000 credits included- Campaigns and sending infrastructure Mailboxes, domains, and deliverability run for you, end to end.
- 5-channel sequencer Email, phone, LinkedIn, SMS, and WhatsApp in automated sequences.
- Dialer and AI voice agents Reps call from the built-in dialer. AI voice answers inbound calls, makes outbound ones and books the meeting.
- AI inbox Every inbound email, LinkedIn message and reply sorted, drafted and answered.
- Meeting routing and booking Route leads to the right rep and book the meeting automatically.
- CRM, pipeline, and quotes Deals, quotes, and each rep's daily list in My Desk.
- Studio content engine Brand, newsletters, landing pages, ads, and campaign content.
- AI agents and workflows Operator and Executor agents for RevOps, deal reviews, and SDR work.
Contact data
Included- MCP Unlimited for every user A $25 per user value, included for the whole org on the Team plan.
- No monthly cap on contact data Reveals, lookups, enrichments, and exports run org-wide, every seat.
- Buying signals Visitors, intent, hiring, and job-change signals on every account.
- Waterfall enrichment Third-party providers, pay on match or bring your own keys.
- Free search and browse Your whole team explores 700M+ contacts and 100M+ companies.
For the whole team
Always on- Unlimited users, no seat fees Invite everyone. Pricing never scales with headcount.
- Every feature unlocked No tiers gating voice, enrichment, sequencer, campaigns, or desktop.
- Built-in CDP and integrations Warehouse, 500+ connectors, two-way CRM sync included.
- Month-to-month, no contracts Cancel anytime.
- Fair-use rate limits Limits apply on all plans. They guard against scraping, not real GTM work.
Execution credits send, call, and run agents. Contact credits reveal and enrich the people you target.
Set your rules, then turn the agents on
Sign up free, with no card, and choose Autopilot, Approve or Off for each decision type before the agents run. You start with 500 execution actions and 1,000 contact reveals.