An agent is AI that can do things for you, and we’re almost there. There’s just one core concept missing: instructions, also known as “system prompt” for those who want to sound fancy. Instructions are sent at the same time as your first message so the agent understands its purpose and how it should respond.
Let’s take a simple example: giving your agent a name. Without any instructions, a Gumloop agent will tell you that it is, well, a Gumloop agent here to help. But if we add instructions that say “You are Yoda, answer in Yoda speak,” now our agent has a new identity. Same prompt, same tools, different response.
Why? Because instructions are sent to the large language model alongside your message. They’re what help the agent understand what it should do. They’re its roadmap.
You can use instructions to give step-by-step guidance on a workflow, or what you expect the agent to do. “To prepare me for meetings, start by looking at my calendar and grabbing the next invite. Then find CRM information and recent news. Package that into a nice email and send it to me.”
You can use them to guide how it responds. Something like “be concise” or “always respond in French.” Help it understand what to do in edge cases: “ignore internal meetings.” Give it a specific output and format you expect: “The report should be a beautiful HTML email sent directly to my inbox.”
Instructions are where you take your agent and really make it yours. Perfect for your workflow, your team, and your way of working.
Now we can really use the word “agent,” because these three things together, the right model, guided by good instructions, with the right set of tools, that’s when you’ve got a sidekick that can actually start doing work for you.
And with that, those are the basics you need to start building your own agent. From here, check out the Build Your First Agent course for concrete, step-by-step instructions on creating your first Gumloop agent.
What Are Instructions?
How system prompts shape AI behavior — identity, workflow logic, boundaries, and output format — and why instructions are the key to a genuinely useful agent.
Instructions are the missing piece between “AI that can access my tools” and “AI that actually helps me.”
You’ve learned that models process your messages and tools let AI take action. But without instructions, your agent has no idea what you actually want. It’s like hiring someone with all the right skills but never telling them the job.
How Instructions Work Under the Hood
When you chat with an agent, your message isn’t the only thing the model sees. Instructions get prepended to every single conversation. The model reads them first, before it ever sees what you typed.
This means instructions aren’t a one-time setup. They’re active context that shapes every response your agent gives. Change the instructions, and you fundamentally change how the agent behaves.
You’ll hear both terms used interchangeably. “System prompt” is the technical name. “Instructions” is what we call them in Gumloop because that’s what they are: you’re instructing your agent on how to behave.
The Four Things Instructions Control
Instructions can shape almost every aspect of agent behavior. Here’s how to think about what to include:
- Identity and persona: name, tone, communication style. Example: “You are Aria, a friendly customer support agent. Be warm but professional.”
- Workflow logic: steps to follow, order of operations, decision points. Example: “First check inventory levels. If stock is below 10 units, flag for review before confirming the order.”
- Boundaries and exceptions: what to refuse, edge cases, escalation triggers. Example: “Never share pricing without checking the latest price sheet. Escalate to a human if the customer mentions legal action.”
- Output format: how results are delivered and structured. Example: “Respond with bullet points. Keep responses under 100 words. End with a clear next step.”
Why Instructions Matter
Instructions are where your expertise lives. You know things about your business that no AI model was trained on. You know that “urgent” from Client A means “sometime this week” while “urgent” from Client B means “drop everything.”
Instructions let you transfer that knowledge to your agent. Without them, you’re asking a very capable system to guess at context it doesn’t have. Two teams can use the exact same model, connect the exact same tools, and get wildly different results. The difference is instructions.
You can’t instruct your way out of missing tools. If your agent needs CRM data and you haven’t connected your CRM, no instruction will fix that. Instructions guide behavior within the boundaries of what’s possible.
The Agent Formula
At this point, you have the complete picture:
| Component | Role |
|---|---|
| Model | Processes language, reasons through problems |
| Tools | Gives access to your systems and data |
| Instructions | Shapes behavior, encodes your process |
All three working together is what makes an agent actually useful.