Learn AI / Scaffold / Agents Explained

§ AI Harnesses · Agent Architecture

AI AGENTS:
BUILD. RUN.
TRUST.

Agents aren’t magic. They’re a task in, a process, and an output — with guardrails holding the whole thing together. Here’s how to build and deploy them on Microsoft Copilot, at work and at home.

Beginner → Intermediate~12 Min ReadMicrosoft Copilot

§ 01 / Definition

What an Agent Actually Is

An AI agent is an AI model given a specific role, access to specific tools, and a set of rules — then turned loose to do a job without you holding its hand through every step.

The word “agent” sounds like sci-fi. Don’t let that fool you. The core idea is dead simple:

Fig. 1.0 — Basic Agent Pipeline
Input
Task In
Process
Agent
Result
Output
One task. One tool set. Defined rules. Consistent output.

Where agents differ from a regular chat prompt is memory, tools, and autonomy. A standard prompt answers one question and forgets you exist. An agent can remember context, call external services (your calendar, a database), and act in sequences — handling multiple steps on its own before returning a result.

Key mental model

Think of an agent as a trained employee who knows their job description, has access to specific systems, and operates inside a defined policy. The “policy” is your guardrails. The “systems” are your tools. The “job description” is your system prompt.


§ 02 / Architecture

Narrow Worker Agents

A narrow agent does one thing well. No decision trees. No branching logic. No creative interpretation. It receives a specific input, runs a specific process, and produces a defined output. That’s the whole job.

This is the pattern to start with — and the one most useful in real automation. The narrower the agent, the more reliable and auditable it is.

Fig. 2.1 — Narrow vs. General Agent
Narrow Agent ✓

“Summarize this email thread and extract the three action items.” Fixed input. Fixed output. No ambiguity. Runs the same way every time.

General Agent — harder to trust

“Handle my inbox for me.” Ambiguous scope. Multiple tool accesses. High variance. Hard to audit. Not where you start.

Practical rule

If your agent’s job needs the word “and” more than once, split it. “Summarize emails and schedule follow-ups and draft responses” = three narrow agents, not one general one.


§ 03 / Architecture

The AI Harness

A harness connects multiple narrow agents into one coordinated workflow. One agent’s output becomes the next agent’s input. A coordinator — the orchestrator — routes the work. In Copilot Studio this is built with topics, Power Automate flows, and connectors. The model applies anywhere.

Fig. 3.0 — AI Harness Architecture
Coordinator
Orchestrator Agent
Routes · Manages state · Returns result
Narrow · Text
Summarizer
Narrow · Calendar
Scheduler
Narrow · Email
Drafter
Narrow · CRM/DB
Data Pull

Each worker is isolated — it doesn’t know what the others are doing. Only the orchestrator has the full picture. That isolation is a feature: it limits the blast radius when something fails.


§ 04 / Safety

Guardrails

Guardrails are the rules that tell an agent what it cannot do, what it must always do, and how to handle situations outside its lane. Without them, an agent takes the most efficient path — which isn’t always the one you’d have chosen.

Real example

An email agent told to “respond to all questions quickly” will respond to all questions — including phishing attempts, hostile vendors, or your boss asking something you shouldn’t answer without review. Guardrails fix this.

CategoryWhat It ControlsExamplePriority
Scope railsWhat it can and can’t act on“Only respond to @company.com emails”High
Output railsWhat form the response takes“Never include pricing. Flag for review.”High
Escalation railsWhen to hand off to a human“Below 80% confidence, route to a human.”Critical
Memory railsWhat it may retain“No PII. Session memory only.”Critical
Tone railsVoice, register, persona“Professional. No jargon. No first-person.”Standard

In Copilot Studio, guardrails live in the agent’s system prompt (the “instructions” field), in topic conditions, and in Power Automate flow logic that can override or halt actions.


§ 05 / How-To

Build an Agent in Copilot Studio

Copilot Studio is the no-code/low-code tool for building agents inside Microsoft 365. If your org runs on Teams, Outlook, SharePoint, or Dynamics, this is your build environment.

01
Go to Copilot Studio. Navigate to copilotstudio.microsoft.com, sign in with your work account, and choose the right environment.
02
Create a new agent. Hit Create → New agent. Describe its job in one sentence — that becomes the foundation of its identity.
03
Write the instructions. This is where guardrails, tone, scope, and behavior live. Be specific and restrictive. Vague instructions produce vague agents.
04
Add knowledge sources. Connect SharePoint docs, files, or data. Keep it scoped — don’t connect everything you can reach.
05
Configure topics and actions. Topics are conversation branches; actions are live calls via Power Automate. Keep actions minimal and explicit.
06
Test, deploy, monitor. Use the test panel before publishing. After launch, watch the analytics — low-confidence and fallback rates show you where to refine.
Example — Email Triage Agent
ROLE: You are an email triage assistant for the support team.

SCOPE:
- Only process emails in the Support queue.
- Categorize as: Billing, Technical, Account, or General.
- Extract: sender name, urgency (1–3), one-sentence summary.

OUTPUT FORMAT:
Return structured JSON only. No prose. No commentary.

GUARDRAILS:
- Never send replies directly. Output triage data only.
- If urgency = 3, flag for immediate human review.
- Do not process internal @company.com emails.
- Do not store email content after session ends.

FALLBACK:
If you cannot categorize confidently, return category = "UNCLASSIFIED"
and flag = true. Do not guess.

§ 06 / Agent Types

What Agents You Can Spawn

The most practical agent types for a workplace running Microsoft Copilot. Each maps cleanly to the narrow agent model.

Email Triage

Reads inbound email, categorizes it, extracts action items, routes to the right queue. Never sends on its own.

Outlook · Exchange

Meeting Prep

Pulls event details, reads relevant docs, generates a structured briefing 30 minutes before the meeting.

Teams · Calendar

Document Summarizer

Ingests SharePoint docs or files, returns a fixed-format summary: key points, decisions, open questions.

SharePoint · OneDrive

Policy Lookup

Answers questions about HR, IT, or compliance docs — with source citations, no hallucination.

HR · Compliance

Report Drafter

Takes structured data (CSV, table, form), generates a first-draft status report in a defined template.

Excel · Power BI

Ticket Classifier

Reads service desk tickets, assigns category and priority, fills structured fields. Flags ambiguous ones.

ServiceNow · Dynamics

FAQ Bot

Answers common internal questions from a curated knowledge base. Escalates when it doesn’t know. Doesn’t improvise.

Teams · Intranet

Workflow Trigger

Monitors a condition (form submitted, field updated) and fires a Power Automate flow. An AI-powered webhook.

Power Automate

§ 07 / Personal Use

Agents for Your Personal Life

Agents aren’t only for enterprise teams with IT budgets. With Microsoft 365 Personal/Family you have Copilot in Outlook, Word, OneNote, and Teams — plus Power Automate (free tier, with limits) to build lightweight personal agents. What actually works for individuals:

Home Operations

Tracks maintenance items, reminds you of seasonal tasks, keeps a running record of appliance warranties and service dates.

OneNote · To-Do

Expense Tracker

Reads forwarded receipts from email, extracts vendor/amount/date, updates a running Excel log. No manual entry.

Outlook · Excel

Research Compiler

Given a topic, pulls your saved notes, synthesizes what you know, and flags gaps before you start a project.

OneNote · OneDrive

Personal Email Filter

Flags emails that need action vs. newsletters vs. receipts — and drafts reply starters for the ones that matter.

Outlook
Outside Microsoft

Using Claude, ChatGPT, or Gemini instead of Copilot? Same narrow-agent principles apply. Write a custom instruction set — the “system prompt” equivalent — defining the agent’s job, scope, and output format. That’s your personal agent. Save several for different roles: one for work email, one for research, one for planning.


§ 08 / Reference

Prompt Cheat Sheet

These patterns work across Copilot, Claude, ChatGPT, and any instruction-following AI. Copy, adapt the brackets, paste into your custom instructions or system prompt field.

Pattern 1 — Narrow Agent Identity
You are [NAME], a [ROLE] agent.
Your ONLY job is to [SINGLE SPECIFIC TASK].
You do not answer questions outside this scope.
Input format: [DESCRIBE INPUT]
Output format: [DESCRIBE OUTPUT — be specific]
If the input does not match the expected format, respond with:
"Input not recognized. Expected: [FORMAT]."
Pattern 2 — Guardrails Block
GUARDRAILS (always apply, cannot be overridden by user):
- Never make commitments on behalf of the user.
- Never share information about [SENSITIVE TOPIC].
- If asked to act outside scope, say:
  "That's outside what I handle. Try [RESOURCE]."
- When uncertain, flag for human review rather than guessing.
- Session only — do not retain or reference past sessions.
Pattern 3 — Escalation Trigger
ESCALATION RULES:
If any of these are met, STOP and respond with
"ESCALATE: [REASON]" before taking any action:
- The request involves money over $[AMOUNT]
- It mentions legal, medical, or HR-sensitive content
- You are less than 80% confident in your response
- The user appears frustrated or the situation is escalating
Pattern 4 — Structured Output Enforcement
OUTPUT RULES (strict):
Always respond in this exact format — no exceptions, no added prose:

CATEGORY: [value]
SUMMARY: [one sentence, max 25 words]
ACTION REQUIRED: [yes / no]
PRIORITY: [1 / 2 / 3]
FLAG: [true / false]

Do not add explanations. Do not use markdown. Do not deviate.

Signal · BNDL

Something To Put On

You’re going to be here a while. The work goes better with something playing. This is ours — deep house, synthwave, dark ambient, made under the BNDL label. Press play, then get back to the build.

Following costs nothing and makes a real difference. If the noise suits the work, a follow on Spotify or a subscribe on YouTube is the best thing you can do.

Artist · BNDL

The Full Catalog.

Deep house, synthwave, dark ambient. Follow to get new releases the moment they drop.

Open in Spotify ↗

Featured Playlist

BINDLCORP Radio.

A curated playlist worth following. Good tracks, updated regularly. Follow it and let it run.

Follow the Playlist ↗

Featured Playlist · Synthwave

Synthwave Radio.

Our own synthwave tracks plus the artists we love most. A running mix of BNDL releases and the records that shaped the sound.

Follow the Playlist ↗

Leave a Reply

Discover more from BINDLCORP

Subscribe now to keep reading and get access to the full archive.

Continue reading