Putting AI agents to work
Plain answers for business leaders handing work to AI agents: what they can do, how they follow your rules, how you stay in control, and what to ask before you start.
Guides
Longer reads for teams deciding what to hand off. All articles
- Ten questions to ask before you hand work to an AI agentBefore an AI agent touches your customers or your systems, ask these ten questions: what it will do, whose rules it follows, what it does when unsure, and more.
- How much should an AI agent remember about your customers?An AI agent should remember just enough to serve the customer and no more. How to choose between remembering nothing, a day, or a full history.
Frequently asked questions
22 short answers, grouped by topic. Read the FAQ
Glossary
The AI agent terms you'll hear, in plain words. Full glossary
- AI agentAn AI agent is software that does a task for you: it reads a request, decides what to do, uses your systems to do it, and checks the result before it answers.
- Managed AI agentsManaged AI agents are AI agents a provider builds, runs and maintains for you, so your business gets the work done without building or operating the technology.
- AI agent calibrationAI agent calibration is setting an agent up to work the way your business does: your policies, tone of voice, process steps and the cases it must hand to a person.
- AI agent portalAn AI agent portal is where a business sees and manages the AI agents working for it: what they did, which projects they belong to, and who on the team can see what.
- Human in the loopHuman in the loop means an AI agent hands a decision to a person when it should not make it alone, such as a large refund, a complaint or an unusual case.
- AI agent memoryAI agent memory is what an agent keeps from earlier work, such as a customer's previous messages, and how long it keeps it: one task, a day, or until you delete it.
- Audit trail for AI agentsAn audit trail for AI agents is the step-by-step record of what an agent did on each task: what came in, what it looked up, what it decided and what it sent back.
- AI guardrailsAI guardrails are the limits that keep an AI agent safe to use: what it may do, what it must never do, how long it may work on a task, and what it can and cannot reach.
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.