---
id: post/bertverbeek-nl/1237
type: post
title: Agents in Business Central – part 2 – the prompt
summary: Building effective agents in Business Central requires well-structured prompts with clear responsibilities, guidelines, and task instructions. The post explains how to use memory, page-specific instructions, and conditional logic to guide agent behavior reliably and keep humans in control.
tier: community
language: en
tags:
  - agents
  - prompting
  - ai
  - instructions
  - memory
  - page-specific logic
  - human oversight
system: copilot
review:
  state: reviewed
  by: opus
  at: "2026-10-08T01:56:56.920Z"
  flags: []
generated:
  at: "2026-10-08T01:26:53.141Z"
  pipeline: 0.2.0
  prompts:
    extract-post: 1
  input_hash: 2ef5ce28028d8607cb58120f4c51f0a7ba6b636caa0dddf3665e781eb59dd5d4
evidence:
  - kind: blog
    url: https://www.bertverbeek.nl/blog/2026/02/16/agents-in-business-central-part-2-the-prompt/
    title: Agents in Business Central – part 2 – the prompt
    date: "2026-02-16"
    commit: null
    t: null
    quote: null
  - kind: blog
    url: https://www.bertverbeek.nl/blog/2026/02/16/agents-in-business-central-part-2-the-prompt/
    title: Agents in Business Central – part 2 – the prompt
    date: "2026-02-16"
    commit: null
    t: null
    quote: The way you guide and structure your agent's behavior determines whether it becomes a reliable assistant or a confused chatbot.
  - kind: blog
    url: https://www.bertverbeek.nl/blog/2026/02/16/agents-in-business-central-part-2-the-prompt/
    title: Agents in Business Central – part 2 – the prompt
    date: "2026-02-16"
    commit: null
    t: null
    quote: This memory model protects performance but still allows context continuity.
links:
  learn: []
  objects: []
  features: []
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
post_id: "1237"
source_id: bertverbeek-nl
source_name: Discover MS BC - Bert Verbeek
url: https://www.bertverbeek.nl/blog/2026/02/16/agents-in-business-central-part-2-the-prompt/
published_at: "2026-02-16T08:28:24.000Z"
author: Bert Verbeek
full_text: false
words: 722
quotes:
  - text: The way you guide and structure your agent's behavior determines whether it becomes a reliable assistant or a confused chatbot.
    why_it_matters: Highlights that prompt quality directly impacts agent reliability and usefulness
  - text: This memory model protects performance but still allows context continuity.
    why_it_matters: Explains the practical balance between agent capability and system performance
code_objects_mentioned: []
systems:
  - copilot
  - development
versions_mentioned: []
preview:
  embeddable: true
  frame_url: https://www.bertverbeek.nl/blog/2026/02/16/agents-in-business-central-part-2-the-prompt/embed/
  image: https://www.bertverbeek.nl/wp-content/uploads/2026/02/d365businesscentral_512x512.png
  image_alt: null
  image_w: null
  image_h: null
  site_name: Discover Microsoft Business Central - The wonderful world of Business Central
  favicon: https://www.bertverbeek.nl/wp-content/uploads/2026/02/d365businesscentral_256x256.png
  probed_at: "2026-10-07T11:50:38.505Z"
---

# Agents in Business Central – part 2 – the prompt

[Read the post](https://www.bertverbeek.nl/blog/2026/02/16/agents-in-business-central-part-2-the-prompt/) · Discover MS BC - Bert Verbeek (Bert Verbeek) · 2026-02-16 · 722 words · tier community · reviewed (checked by Opus)

> Building effective agents in Business Central requires well-structured prompts with clear responsibilities, guidelines, and task instructions. The post explains how to use memory, page-specific instructions, and conditional logic to guide agent behavior reliably and keep humans in control.

## Key points

- Agent instructions need three core components: responsibilities (scope and boundaries), guidelines (rulebook for behavior), and task instructions (concrete procedural steps)
- Agents should ask for help when data is missing or unclear, and request user review for important steps to maintain human oversight
- Agents can memorize specific actions, search results, and explicitly instructed values, but not the full state of every page
- Use page-specific instructions with conditional logic to provide detailed guidance only when needed and improve performance
- Business Central agents have context-aware tools like searching pages, selecting rows, executing actions, and setting field values

## Quotes

- "The way you guide and structure your agent's behavior determines whether it becomes a reliable assistant or a confused chatbot." (Highlights that prompt quality directly impacts agent reliability and usefulness)
- "This memory model protects performance but still allows context continuity." (Explains the practical balance between agent capability and system performance)

## Context

- Features: Agent prompting framework, Responsibility definition, Guidelines and rules, Task instructions, Memory management, Page-specific instructions, Conditional logic, Agent Tasks action with View Log Entries

Source: Discover MS BC - Bert Verbeek, community blog. Summary, key points and quotes are derived (CONTENT-NOTICE.md); read the original for the full text.