Agents that do the work, not just talk about it

A chatbot converses: it takes a question and returns text. An agent executes: it takes a goal, decides which steps to take, uses tools to query or modify your systems, evaluates the result and corrects. A chatbot tells you an order’s status; an agent notices the order is late, notifies the customer, reschedules the shipment and logs all of it.

LangGraph for most production cases, because it models the flow as a graph with durable state, allows pausing for human approval, retrying a single step and replaying a full run for debugging. For simple flows n8n with model calls is sometimes enough, and that is what we propose.

It depends how wrong. Sensitive actions — those that move money, write to systems of record or talk to a customer — go through configurable human approval. The rest is bounded by permissions and by step, time and cost limits. And everything lands in an audit trail, so when something goes wrong you can reconstruct exactly what happened.

Yes, as long as they expose an API or an accessible database. We have integrated inventory systems, payment platforms, CRMs and in-house databases. When several systems are involved we usually expose them as MCP servers, which standardizes access and prevents every new agent from needing bespoke integrations.

It depends on volume and how many steps each run takes. For a mid-market company it usually lands between USD 150 and 900 per month in model and infrastructure consumption. We estimate it with concrete numbers in the proposal, and task-based routing exists precisely to keep that figure low.

In practice, almost never. The agent takes the mechanical work — classifying, searching, copying between systems, following up — and the person keeps what requires judgment, which is usually where the bottleneck was. If your goal is different and you do want to shrink the team, say so on the first call: it changes what has to be documented and how much the agent has to handle unsupervised.

Four to six weeks for a single workflow, counting from when we have access to the information and systems. The prior exploration takes one to two weeks more and exists so we do not build on assumptions.

That is what we recommend. The exploration reviews one concrete workflow, evaluates whether an agent adds value, and delivers the design with its estimate. If we proceed, it is credited against the project. It is the cheapest way to find out whether this makes sense in your operation before committing a quarter.