Skip to content
The agent library

Specialists for the work you actually do

Each agent is a preset built for a real role. Start from one, assign the tools it may use, publish a version — and it's ready to work, governed from the very first run.

Operations Agent

Keeps delivery moving

The flagship operator. It watches your projects and delivery work, chases what is stalling, drafts status updates and proposes the next actions — so the work stays on track without a human babysitting the board.

What it might do

  • Summarise where each project stands and flag what is at risk
  • Draft a task or comment to unblock a stalled piece of work
  • Propose a weekly delivery update for sign-off
Project & deliveryComms & email

Documentation Agent

Keeps knowledge current

Turns scattered context into living documentation. It drafts and updates internal docs, runbooks and notes from your existing sources, and surfaces what has gone stale — keeping your knowledge base trustworthy.

What it might do

  • Draft documentation from a project, thread or spec
  • Flag pages that contradict the latest changes
  • Propose an update to a runbook for review
Docs & dataProject & delivery

Research Agent

Gathers and synthesises

A read-heavy specialist that pulls together what you need to decide. It collects information across your connected tools and the web, then synthesises it into a clear, sourced brief — no side effects, just signal.

What it might do

  • Compile a briefing on an account, market or topic
  • Pull together the context behind a decision
  • Summarise a long thread or document set
CRMDocs & data

Content Agent

Drafts in your voice

Produces first drafts that sound like you. From outreach emails to posts and announcements, it prepares content grounded in your context and hands it to a human to approve before anything is sent.

What it might do

  • Draft an outreach or follow-up email for approval
  • Prepare an announcement from release notes
  • Repurpose long-form content into shorter pieces
Comms & emailDocs & data

Reporting Agent

Turns data into reports

Pulls numbers from your finance, CRM and delivery tools and assembles them into the reports your team actually reads. Consistent, on-schedule, and always traceable back to the source.

What it might do

  • Compile a monthly performance or finance summary
  • Build a pipeline or delivery snapshot
  • Draft a board-ready report from connected data
FinanceCRMDocs & data

Support Agent

Triages and drafts replies

Takes the first pass at your inbound queries. It triages incoming messages, gathers the relevant context, and drafts a reply — which a human approves before it ever reaches the customer.

What it might do

  • Triage and categorise incoming queries
  • Draft a reply grounded in your docs and history
  • Escalate anything sensitive to a human
Comms & emailDocs & data

Sales Agent

Keeps the pipeline tidy

Looks after CRM hygiene and follow-through. It keeps records up to date, drafts follow-ups, and proposes the next move on a deal — with every CRM write and outbound message gated for approval.

What it might do

  • Propose CRM updates after a meeting or thread
  • Draft a follow-up sequence for sign-off
  • Flag deals going quiet and suggest a next step
CRMComms & email

Compliance Agent

Checks against policy

A careful reviewer that holds work to your standards. It checks documents, actions and records against policy, flags what looks off, and produces an evidence trail — supporting the audit, never bypassing it.

What it might do

  • Review a document or action against policy
  • Flag records that need attention
  • Assemble evidence for an audit or review
Docs & dataFinance
Configured, not coded

From preset to production in minutes

You don't write agents from scratch. You configure them — and the governance comes built in.

Assign tools

Choose exactly which tools an agent may use. It can only ever touch what you grant it.

Publish a version

Publishing freezes the agent. That version is immutable, so its behaviour is reproducible.

Dry-run, then run

Test against real context in the sandbox before you let it act for the first time.

Whichever agent you start with, the rule is the same: it proposes, and a human approves anything that changes the outside world. See how the loop works →

Find the right agent for your team

Tell us the work you'd hand over first, and we'll show you the agent for it — running on your own tools.