Blog
Copilot and agents in Business Central: hype vs reality
Across the 2025 and 2026 releases, Business Central has gained a steady stream of Copilot features and, more recently, autonomous agents. The marketing is breathless; the reality is more interesting and more useful. Here is our grounded take on what to adopt now, what to scope carefully, and how to avoid the two classic mistakes — ignoring the technology, or letting it run unchecked.
What is genuinely useful today
Several Copilot features have crossed from demo to daily driver. They share a trait: the human stays in control, and the AI removes drudgery rather than making the decision.
- Autofill suggests field values as you create records, so you type less and copy-paste less.
- Summarize turns a long record — a customer, a posted document, a history — into a readable paragraph.
- Tell Me / chat lets users find pages, actions and answers in natural language instead of hunting through menus.
- Bank reconciliation assist proposes matches between statement lines and ledger entries, leaving you to confirm.
Why it matters: these are low-risk, high-frequency wins. They speed up work people already do, the user reviews the output anyway, and there is no autonomous action to audit. For most clients, this is exactly where to start.
What needs careful scoping
The newer autonomous agents are a different proposition. The Sales Order Agent can read incoming order requests and draft sales orders; the Payables Agent can process vendor documents from a mailbox. These act on your behalf, across multiple steps, with far less per-action human input.
Two things deserve attention before you switch them on:
- They are billed via Copilot Studio messages. Agent activity consumes capacity, and that consumption needs modelling against expected volume — not discovered on an invoice.
- They take real actions. A drafted order or a processed payable touches your data and your process, so the audit trail and review step matter far more than with a summary.
Why it matters: the value is real, but so is the cost and the operational risk. An agent processing the wrong supplier emails, or quietly consuming more capacity than budgeted, is a problem you want to find in a pilot, not in production.
Human-in-the-loop is not optional
The most reliable pattern we have seen, and the one BC’s own tooling now supports, is human-in-the-loop: the agent prepares, a person reviews and commits. The 2026 releases added task panes, in-context review and a way to stop all agent tasks at once — precisely because oversight is what makes agents trustworthy.
Why it matters: finance and operations teams will not — and should not — hand control to an unmonitored agent. Keeping a human on every action for the first weeks builds both the audit trail and the team’s confidence.
Model the consumption before you commit
Because agents are metered, treat consumption like any other operating cost. Estimate message volume from real document counts, run a bounded pilot, measure actual usage, and only then decide where wider rollout pays off.
Why it matters: the difference between an agent that saves money and one that surprises the CFO is a spreadsheet built before go-live, not after.
Our advice: pilot small, with oversight
Turn on the assistive Copilot features broadly — they are safe and immediately useful. Approach autonomous agents as scoped pilots: one mailbox, one process, a human reviewing every action, and a clear read on consumption. Widen scope only once the audit trail and the numbers both check out.
This is neither dismissal nor hype. The technology is genuinely good and getting better with each wave. Adopted with judgement, it removes real work; adopted blindly, it adds cost and risk. The job of a good partner is to tell you, honestly, which features are in which camp for your business.
Wondering where Copilot and agents fit in your Business Central, without the hype? Tell us your story and we will give you an honest, free assessment.