An agent is AI that can do things for you. 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 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 LLM 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: “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.”
Use them to guide how it responds: “Be concise” or “Always respond in Québécois 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, 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. From here, check out “Build Your First Agent” for
concrete, step-by-step instructions on creating your first Gumloop agent.
