A single-task agent
One narrow job, such as triaging invoices, scoring leads or answering routine support, with tool use and evaluations.
How it runs
Ships on its own, behind a gate, with its harness, evaluation suite and runbook.
A demo agent breaks on its first edge case. We build the dull parts that keep one working: the harness, the evaluations and the stop. Week 1 ends with a plan and a price, in writing.
We write the agent’s contract first, then build its harness, then choose the model. Models change often; the contract and the harness stay.
What it must do, what it must never do and what a run may cost, with a rule for success, refusal and escalation.
Retries, a fallback path, a cost cap on every run and a kill switch that a named person controls.
Known tasks with known answers, scored on every prompt change, plus looser checks where there is no single right answer.
Each run traced step by step, with spend, speed, success rate and an alert when behaviour starts to drift.
Pick the shape closest to the job. Week 1 settles the scope, in writing.
A single-task agent
One narrow job, such as triaging invoices, scoring leads or answering routine support, with tool use and evaluations.
How it runs
Ships on its own, behind a gate, with its harness, evaluation suite and runbook.
A multi-step workflow
An agent that plans, calls tools and joins the results across many steps, for operations, document work and research.
How it runs
Built one step at a time, with a named person approving every consequential step.
Multi-agent orchestration
Specialist agents with one job each, coordinated by a supervisor, for work no single agent can hold.
How it runs
Fixed scope and fixed cost, agreed before work begins, with a gate on every handoff.
It fits
It doesn’t fit
Every engagement runs the same method: an agent proposes, a person approves.