Every agent lists exactly what it does, which tools it may call, what it needs from you and who has to approve the result. Status is derived from live integration health checks — never hard-coded.
Conceptual visualization only
Agents published
15
Live now
0
Demonstration ready
15
With human approval gates
13
Open any card for the full agent profile, workflow, tools, limits and audit behaviour.
Answers customer conversations from your approved knowledge base, resolves routine tickets and escalates anything outside policy to a human.
Approval required for sensitive tasks
Qualifies inbound leads against your criteria, keeps pipeline records current and drafts the next follow-up for a rep to send.
Approval required for sensitive tasks
Plans campaign structure, drafts channel copy variants and reports on audience and performance metrics you supply.
Approval required for sensitive tasks
Collects evidence from approved sources, compares findings side by side and produces citation-backed research you can audit.
Approval required for sensitive tasks
Reads uploaded contracts, invoices and forms, extracts the fields you define and validates them against your rules before release.
Approval required for sensitive tasks
Screens applications against documented job requirements, drafts interview packs and answers policy questions for employees.
Human approval always required
Analyzes authorized financial data, identifies trends and variances and prepares reviewable decision-support reports.
Human approval always required
Compares supplier quotations line by line, checks them against your specification and prepares an award recommendation for sign-off.
Human approval always required
Tracks milestones and dependencies from your plan, flags slippage early and drafts the status report with an evidence trail.
Approval required for sensitive tasks
Profiles datasets, detects missing, duplicated or inconsistent values and produces a remediation report with prioritised fixes.
Approval required for sensitive tasks
Processes spatial datasets, performs approved geoprocessing operations and generates traceable maps and statistics.
Approval required for sensitive tasks
Extracts and validates information from drawings, specifications and technical documents, flagging conflicts between them.
Human approval always required
Checks activity and documents against your written rules, records every check performed and keeps a defensible audit trail.
Human approval always required
Indexes your documents and answers questions with grounded, quoted passages, refusing to answer when the source is missing.
No human approval required
Summarises long threads and meeting notes, extracts owners and deadlines and drafts the follow-ups for you to send.
No human approval required
Backend and required tools passed their health checks.
A sample-data demonstration workflow is available. Live execution needs more configuration.
Connect an approved AI provider and the required tools to enable execution.
A required integration health check failed. Runs are blocked until it recovers.
Pick an agent to see its own process: trigger, validation, approved tools, human approval gate and deliverable. No two agents share the same workflow.
From an inbound customer message to an approved reply and a monitored resolution.
Saved with the run so the recorded execution trail shows what was asked. Demonstration runs use sample data. They do not touch your systems.
Public visitors can preview the structure and inspect every node. Labelled demonstrations and live runs require a signed-in account with configured providers.
Approval gate: Escalate if required. Deliverable: Report.
| Template ID | Nodes | Approval node | Output type | Preview | Demo | Live | Mobile test |
|---|---|---|---|---|---|---|---|
| customer-support-agent | 9 | Yes. Policy: always | Report | Available | Available (signed in) | Available via Studio · requires ai_provider | Verified at 390px |
| sales-assistant | 9 | Yes. Policy: always | Table | Available | Available (signed in) | Available via Studio · requires ai_provider | Verified at 390px |
| marketing-agent | 9 | Yes. Policy: always | Report | Available | Available (signed in) | Available via Studio · requires ai_provider | Verified at 390px |
| research-agent | 8 | Yes. Policy: always | Report | Available | Available (signed in) | Available via Studio · requires ai_provider | Verified at 390px |
| document-analysis-agent | 8 | Yes. Policy: always | Dataset | Available | Available (signed in) | Available via Studio · requires ai_provider | Verified at 390px |
| hr-assistant | 6 | Yes. Policy: always | Table | Available | Available (signed in) | Available via Studio · requires ai_provider | Verified at 390px |
Demonstration runs are stored and replayed from recorded events. Live runs execute server-side in the Studio and only start when the listed integrations report healthy.
Real run records from this platform, anonymised.
Anonymised agent runs from the last 40 executions, refreshed every 15 seconds.
Share your objective and constraints. A specialist reviews every request before any recommendation is issued.
