Build Your First Agent
The goal is not to create the most powerful agent. The goal is to create one agent that does one useful job reliably.
Choose your build path
HiveMind
Describe your agent in plain English. HiveMind (our AI assistant) generates the agent definition for you.Best for: Non-technical builders, rapid prototyping
Visual Builder
Configure your agent step-by-step through the UI. Set instructions, tools, memory, and schedules without writing code.Best for: Operators who want control without code
HiveLang
Write agent behavior in HiveLang v5. Full expressiveness, version-controllable, CI/CD-deployable.Best for: Developers and technical teams
Step 1 — Write the agent brief
Before touching the builder, write out your agent brief:Step 2 — Write behavior rules
Good rules make the agent consistent. Weak rules get ignored.Good Rules
- “Ask one clarifying question when the request is missing account details.”
- “Use short paragraphs and concrete steps.”
- “When a tool fails, explain what failed and how to retry.”
- “Never invent integration results.”
- “Keep responses under 150 words unless more detail is requested.”
Weak Rules
- “Be smart.”
- “Be friendly.”
- “Do everything the user needs.”
- “Use tools when helpful.”
- “Be accurate.”
Step 3 — Connect tools carefully
Tools let an agent act. They also introduce risk. Before connecting any tool, ask:
Example tool plan:
Step 4 — Configure memory
What to store in memory
What to store in memory
- Customer company name
- Preferred language or tone
- Recurring issue type
- Current project context
- Previous troubleshooting steps taken
What NOT to store in memory
What NOT to store in memory
- One-time secrets or auth codes
- Payment card details
- Another user’s private data
- Raw API responses
- Ephemeral session data that isn’t useful next time
Step 5 — Test with realistic cases
Step 6 — Deploy one surface first
Don’t deploy everywhere at once. Start with one channel:- Hosted web link — fastest to share, great for demos
- Telegram — if your users are already there
- API — if your SaaS backend needs to call the agent
Step 7 — Improve from traces
After real users interact with your agent, open the Runs tab and look for:- Repeated user confusion → Fix your instructions
- Slow tool calls → Check integration health
- Wrong tool selected → Add specificity to instructions
- Missing context → Add a
before inputhook in HiveLang - Hallucinated claims → Add explicit “never claim X unless Y confirms it” rules
Full HiveLang v5 example
Common mistakes
Giving the agent too many jobs
Giving the agent too many jobs
One agent, one responsibility. Agents that try to do everything do nothing well.
Connecting tools before instructions are clear
Connecting tools before instructions are clear
Define what the agent should do before deciding which tools it needs. Don’t work backwards from tools.
Skipping failure tests
Skipping failure tests
Real usage always hits edge cases. Test what happens when a tool fails before you’re in production.
Deploying before observability shows useful traces
Deploying before observability shows useful traces
A trace that shows nothing meaningful is worse than no observability — it gives false confidence. Make sure traces show the context, tools called, and any errors.
Using vague instructions
Using vague instructions
“Be helpful and accurate” is not an instruction. “When the user’s request is missing their email, ask: ‘Could you share your account email so I can look that up?’” is an instruction.