In the cloud
Run Aether in the cloud, aligned with your infrastructure and deployment needs.
From process to production. Faster.
Aether brings skills, rules and integrations together to get agents into production faster. Choose cloud or on-premises deployment, or let us deliver a managed service for your team and end customers.
From first call to a working agent
A focused process, from defining the job to testing and launch. Timing depends on your integrations and deployment requirements.
You tell us the work
One process your team repeats, and the rules it follows today.
We build the agent
Connected to the systems that work already lives in: your help desk, inbox, files and business systems.
We tune it to your rules
Your policies, tone of voice and limits, with anything outside them sent to your team.
You go live in your portal
Your team sees the agent's work and decides who can see what.
We keep it tuned
When your rules change, we release a new version with a note of what changed.
Choose where it runs. Choose who runs it.
Hosting and operational support should fit your business, whether agents serve your team or your customers.
On-premises
Bring Aether into your own environment when your business requires local hosting.
As a managed service
Let us host, run and maintain the agents, including services delivered to your end customers.
We agree the hosting environment, integrations and operational responsibilities with you before launch.
What you bring, and what we do
You bring
- Someone who knows the process and how it should go
- Your policies, and the cases you'd never let an agent decide alone
- Help from IT to give the agent access to the systems involved
We do
- Design the agent with you, around one clear job
- Connect it to your systems
- Calibrate it to your rules, tone and hand-offs
- Try it on examples of your real work before it goes live
- Deploy it in the cloud, on-premises, or as a managed service
- Update it whenever your rules change
What your agents can do
Each agent has one clear job, and uses these abilities to do it.
Answer customers
- Reply to messages from chat, your help desk or email, in your tone of voice, at any hour.
Read documents
- Pull the details out of PDFs, spreadsheets, forms and scans, and turn them into clean records.
Update your systems
- Look things up, create and change records in the systems your team already works in.
Work on a schedule
- Run checks every morning, reconcile records on Fridays, or send a report on the first of the month.
Remember what matters
- Pick up a customer's conversation where it left off, for as long as your privacy rules allow.
Hand off to your team
- Send anything outside your rules to the right person, with everything they need to decide.
What it connects to
Agents work inside the tools your team already uses. If a system can be reached through an API or a database connection, an agent can work with it.
For the thinking, we use AI models from OpenAI, Anthropic and Google, choose the right one for each job, and can switch an agent to a better one without rebuilding it.
- Help desks and chat tools that can pass messages on to another system
- Email, sent through your own mail server
- Business systems with an API: CRM, ERP, order, claims and finance systems
- Databases your team gives the agent access to
- Files: PDF, Excel, CSV, scans and more
- Your website, through the CLiP widget
The three parts behind every agent
You only ever work in the top one.
Your portal
CLiP
Where your team works with its agents: each project's agents in one place, and who can see what, set by role.
About your portalSkills and Playbooks
Skills and prompts
A versioned library of reusable skills and prompt templates that workflows can share.
Explore Skills and PlaybooksThe engine
AiR
Runs your agents securely, connects them to your systems, and keeps a record of every step they take.
How it works
Questions about getting started
Do we need technical staff to use Aether?
No. We build and maintain the agents. You need someone who knows the process and its rules, and help from IT to give the agent access to the systems it works in.
How long does it take to get an agent live?
Aether combines reusable skills, configurable rules and integrations to help get agents into production faster. The launch timeline depends on your process, connected systems and hosting requirements; we agree a plan with you before work begins.
What happens if an agent gets something wrong?
Every action is recorded, so you can see exactly what happened and why. We correct the rule or instruction behind it and release a new version. Decisions you never want an agent to make alone, like a large refund, can always go to a person.
Which AI models do the agents use?
Aether uses models from OpenAI, Anthropic and Google and picks the right one for each job. We can move an agent to a different model without rebuilding it, and give it a backup model in case one provider has an outage.
How does an agent know our policies?
We write your policies, tone of voice and process steps down with you and keep them in Calibration, the part of Aether that holds your rules. The agent works within them, and when they change we release a new version so every agent follows the update.
Ready to put your first agent into production?
Bring us one process. We’ll map the skills, rules and integrations, and help you choose cloud, on-premises or a managed service.