Build Guide / Step 05

Deep Dive · Step 05 of 06
[ GUARDRAILS ]

SET THE
GUARDRAILS.

An agent without guardrails takes the most efficient path — which isn’t always the one you’d choose. This step builds the rules that decide when an agent acts, when it stops, and when it hands a problem to a human. Skip this and your agents fail silently. That’s worse than no agent.

~35 MinCopilot Studio + FlowsCritical

The Three Layers

Where Guardrails Live

01
In the instructions. The “RULES” and “YOU NEVER” sections of each agent’s prompt. First line of defense.
02
In the flow logic. Power Automate conditions that can halt or redirect before anything reaches a person or system.
03
In the escalation path. A defined route for “I don’t know” — so uncertainty becomes a flagged hand-off, not a confident wrong answer.
Build It

The Escalation Block

Add this to your lead agent’s Instructions, below the routing rules. It defines exactly what triggers a stop-and-escalate. Adapt the bracketed thresholds to your team.

OPS_LEAD — Escalation block (append to instructions)
ESCALATION RULES (these override everything else):

Stop and respond with "ESCALATE: [reason]" — taking no other action —
if ANY of the following are true:

- The request involves money over $[AMOUNT].
- It touches legal, medical, HR, or compliance matters.
- A worker returns an error or an incomplete result twice.
- You are less than [80]% confident in the right route.
- The person seems upset, or the situation is escalating.
- The request asks you to act outside your listed workers.

WHEN YOU ESCALATE:
- Name the reason in one plain sentence.
- Summarize what you understood, so the human has context.
- Do not apologize repeatedly or stall. Hand off cleanly.
Make It Real in the Flow

A Condition That Stops the Line

Instructions guide behavior, but a flow condition enforces it. In your handoff flow, add a check on the worker’s output before it goes anywhere.

Power Automate — condition step
Condition: if workerOutput contains “flag: true” YES → post to Teams channel “Needs Review” → notify a human, do not auto-send NO → return result to lead agent as normal
The principle

A good agent system is loud when it’s unsure. Every guardrail you write is really answering one question: “What happens when this goes wrong?” If you can answer that for each agent, you’ve built something trustworthy. If you can’t, you’ve built a liability with good intentions.

Test the Failure

Try to Break It

In the Test panel, feed the lead something it shouldn’t handle — a legal question, an angry message, a request outside its workers. Confirm it escalates instead of improvising. An agent you’ve watched refuse correctly is one you can actually trust to run.


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