Missions
A mission is a persistent goal your agent pursues over days or weeks — as opposed to a task it performs once. You state the goal; the agent plans, executes, and adapts; you keep the judgment through the brief and the autonomy level you chose. Missions live at Dashboard → Missions.
Creating a mission
State the goal in plain language, with any constraints you care about:
Book 10 demos with HVAC companies in Texas by end of month. Budget $60. Email and phone only, no social.
The agent expands this into a mission brief:
- Targets — who it will pursue and how it will find them
- Lanes — the channels it will use (email, social, SMS, voice, meet)
- Sequence — the touch cadence and follow-up plan
- Budget — the mission’s own AI budget
- Autonomy — how much it may do without asking (you set this)
Nothing runs until you approve the brief. You can edit any part before approving. When the agent needs to change the plan mid-mission (a lane underperforms, a better segment emerges), it proposes a revised brief — every revision is versioned and kept.
Autonomy levels
Per mission, choose one of four levels:
| Level | What it means |
|---|---|
per_message | You approve every outbound message before it sends. |
batch | The agent prepares batches; you approve a batch at a time. |
brief | You approved the brief; the agent sends within it without per-message approval. |
autopilot | The agent runs the mission end to end within its caps. |
Regardless of level, T3 actions — anything financial or irreversible — always require a human. Autonomy levels govern T2 sends only; the T3 gate has no override.
The task graph
Under the hood a mission decomposes into tasks: research → outreach → reply → follow_up → book_meeting → run_meeting → complete. Each task is visible in the mission detail view with its status and history, and the
funnel view aggregates them: researched, contacted, replied, booked.
Channel lanes
- Email — sent from dedicated sending domains with SPF/DKIM/DMARC configured, paced sending, reply detection, and reply-to routing back into the mission.
- Social — posts and DMs through connected social tools, with per-platform pacing.
- Voice — outbound calls place only after consent and jurisdiction checks pass, and the agent always discloses that it’s an AI. Transcripts post back to the mission log.
- Meet — when a meeting books, the agent can attend the Google Meet as a voice participant and post the transcript and outcomes back to the mission.
Lanes activate per mission; a lane the brief doesn’t include can’t be used.
Budgets
Each mission has its own AI budget on the same ladder as your plan budget: a warning as it climbs, soft-landing at 100% (the agent economizes), and a hard stop at 120% — the mission pauses and waits for you. Mission spend is metered separately so you can see exactly what a mission costs on the Billing page.
Compliance rails
These are enforced on every send, on every mission, regardless of autonomy:
- Suppression list — tenant-wide; an opt-out on any channel suppresses the contact everywhere, instantly.
- Consent + jurisdiction gates — voice calls check both before dialing.
- Cross-mission frequency cap — a hard ceiling on outbound touches per contact per rolling week, across all missions and channels, so concurrent missions can’t over-contact one person.
- Quarantine — anything the agent learned from the web or inbound mail is tainted; tainted data flowing into a send forces an approval with a visible warning.
Dry-run and practice
- Dry-run executes the mission plan without sending: you see exactly which messages would go to whom, when.
- Practice lets you converse with the agent in its outreach voice before anything is real — useful for calibrating tone before the first live mission.
Webhooks and replies
Replies flow back automatically — email reply-to, social webhooks, voice and meet transcripts — and wake the agent on arrival. A hot reply escalates to you through your channels just like a hot lead.