Building guardrails for agents

What you'll do

Guardrails are permissions, confirms, and tool limits. In AshnaAI the builder asks for connector access before the agent can use those tools.

This guide walks through AI agent guardrails in AshnaAI. You stay in chat. You do not need a separate desktop of buttons for each file job.

Before you start

Open AshnaAI and start a new chat.

How to AI agent guardrails

Follow the steps below in order. Confirm in chat before AshnaAI sends, posts, or writes to Tally.

Step 1. Read the definition

Guardrails are permissions, confirms, and tool limits. In AshnaAI the builder asks for connector access before the agent can use those tools.

Step 2. Open AshnaAI

Sign in at https://app.ashna.ai and start a chat, or open the agent builder.

Step 3. Try the job

Open the agent builder and review tool permissions before the first run.

Step 4. What to expect

A prompt that says 'be careful' is not a guardrail.

Keep in mind

A prompt that says 'be careful' is not a guardrail.

Related guides

Also read create and use agents.

Also read designing hitl workflows.

More AI glossary how-tos live on What is RAG, hallucination, and prompt engineering.

Try it now

Open app.ashna.ai and run this job in a new chat. New accounts can start from app.ashna.ai/signup.