Agents
Four example AI agents are sitting at this table. Tap one to read what it actually does.
Nothing here is for sale. They are worked examples, written so you can see the shape of the job an agent is good at.
Looking for another room?
Examples
Four examples, each one for a different industry. Tap one to see what work it would actually take on, and where a human stays in the loop.
Before anything gets built
Every real business process is three layers. Most of what teams call an AI problem is really not knowing which layer a given step belongs to. Sorting your work into these three is the step to do before a line of anything gets built.
So you are not paying agent-level cost for something a plain automation would do better, and not forcing a rigid automation onto a step that needs judgment. More on workflow vs. automation vs. agent →
Everything we have written about working with AI agents is in the Library, free to read. Guides, a 76-term Lexicon, the comparison boards, and the blog.
Open the Library Nothing to sign up for, and nothing for sale.How we work
The agents do the work and then show it. A human approves it. That step belongs in the build rather than bolted on afterwards, and it is the reason any of this survives contact with real work.
An agent works alongside your team, not instead of them. That is the whole idea behind the name People in the Loop.
Where a human stays in
More on all four is in the Library, free to read.
Open the LibraryExample agent
For medical and dental practices
Most practices lose patients in the same few places: the call nobody picked up, the fee question that never got answered, the recall that never went out. Vera is an AI agent built for exactly that work, so the front desk stops being the bottleneck.
Your team stays in the loop. Vera drafts and handles the repetitive work, and your human employees approve anything that matters.
Vera is a worked example, written to show the shape of the job. There is nothing to buy here.
Example agent
For home services
The phone is the business. When it rings out, the caller almost never leaves a voicemail, they just call the next company on the list. Ruby is an AI agent that makes sure the inquiry survives the moment nobody could pick up.
Your crew stays in the loop. Ruby handles the catching and the chasing, and your team quotes the work and does the job.
Ruby is a worked example, written to show the shape of the job. There is nothing to buy here.
Example agent
For staffing and recruiting
Strong candidates are off the market in about ten days. Most agencies still take three to four weeks to get a shortlist in front of a client. Quinn is an AI agent built to close that gap.
Quinn never makes the call on a candidate. It does the reading, the chasing and the coordinating, then hands your recruiter a ranked shortlist with its reasoning attached.
Screening is regulated in a growing number of states and cities, so the human approval step is built into the deliverable rather than bolted on.
Example agent
For manufacturing and distribution
Most B2B buyers order from whoever answers first. Quoting often takes five to nine days, and inside sales spend the bulk of their week building quotes rather than selling. Otto is an AI agent aimed straight at that.
Otto works on the documents and repetition your team already handles by hand. Your team keeps every pricing and supplier decision.
Most of the work here is plumbing rather than intelligence, which is the usual surprise.
The directory
Five rooms, and you can walk into any of them from here.
Looking for a person rather than a room? Get in touch.