Building an AI Agent
Step-by-step prompting guide to build a working AI agent with Cody. Real prompts from real conversations that produced production agents.
This guide shows you exactly what to say to Cody to build a working AI agent — based on real conversations that produced production agents.
Building an AI agent sounds complex. But on CodeWords, it's a conversation. The trick is knowing what to say and in what order. This guide gives you the exact prompts, tips, and patterns that have been used to build agents now running in production.
The Conversation Flow
Every successful agent build follows the same five phases. You don't have to use these exact words — Cody understands natural language — but these templates are battle-tested.
Phase 1: Research (Optional but Recommended)
When to use this phase: Complex agents with 4+ integrations, or when you're not sure what architecture you need. Skip this for simple bots with 2-3 tools.
What to say:
"Research the best approaches to build an AI agent that can [your use case]. Look at OpenClaw, LangChain, and other frameworks, and tell me what architecture would work best on CodeWords."
What Cody does:
Searches multiple sources (documentation, GitHub repos, technical articles)
Compares frameworks and approaches
Recommends the best architecture for your specific needs
Identifies potential challenges before you start building
Example for a personal assistant:
"Research how to build a personal AI assistant that can manage my Google Calendar, read my Gmail, search the web, and remember things about me long-term. Compare approaches like OpenClaw's architecture vs. a simpler tool-calling agent. What would work best on CodeWords?"
Phase 2: Context & Requirements
This is the most important phase. The more context you give Cody, the better your agent will be on the first try.
Template — copy and customize:
"Build me an AI agent with these specs:
Platform: [WhatsApp / Slack / Telegram / API endpoint (paid plans)]
Tools it needs:
[Tool 1, e.g., Google Calendar — read and create events]
[Tool 2, e.g., Gmail — read, summarize, and draft replies]
[Tool 3, e.g., Web search — find current information]
[Tool 4, e.g., Memory — remember facts I tell it]
Personality: [Brief and casual / Professional and detailed / Friendly but concise]
Memory: [Remember my preferences / Remember my team members / Remember project details]
Trigger: [Respond to WhatsApp messages / Run daily at 8am / Listen for Slack mentions]"
Pro tip: Add a persona description for best results. Something like: "Act like a sharp executive assistant who's been working with me for years. You know I prefer morning meetings, hate unnecessary calls, and always want the TL;DR first."
What makes a great requirements prompt:
Be specific about tools — "Google Calendar" is better than "calendar"
Describe actions, not just access — "read and create events" vs. just "calendar access"
Set personality early — It's harder to change later
Mention your timezone — Agents default to UTC if you don't specify
Phase 3: Build
Once Cody understands your requirements, it's time to build. This is usually the shortest prompt.
What to say:
"Build it. Deploy it as a new service called [your-agent-name]."
What Cody does:
Creates the service code with all your integrations
Configures each tool connection (API keys, OAuth, webhooks)
Sets up the memory system
Tests each tool individually
Deploys to CodeWords' cloud
Registers triggers (WhatsApp webhook, Slack events, cron schedule, etc.)
Naming tip: Use descriptive, lowercase names with hyphens: my-assistant, team-slack-bot, support-agent. This becomes part of your service URL.
If Cody asks questions during build: That's good! It means Cody found an ambiguity in your requirements. Answer the question, and Cody will continue building.
Phase 4: Test & Fix
Your agent is deployed. Now test it and tell Cody what to fix.
What to say:
"I tested it and [describe what happened]. Can you fix it?"
Common issues and how to describe them:
Wrong timezone
"Calendar events show in UTC. I'm in [your timezone]."
Responses too long
"Keep responses under 3 sentences. Be more concise."
Missing a tool
"It can't check my email yet. Add Gmail integration."
Wrong personality
"It's too formal. Be more casual — like texting a friend."
Trigger not working
"WhatsApp messages aren't reaching the agent. Check the webhook registration."
Memory not working
"I told it my name yesterday but it doesn't remember today."
Iteration is normal. Most production agents take 3-5 rounds of testing and fixing. Each round usually takes under 2 minutes.
Phase 5: Expand
Once your core agent works, add more capabilities over time.
Feature expansion prompts:
"Add email drafting — when I say 'reply to [person]', draft a response based on the conversation."
"Add a daily briefing — every morning at 8am, send me a WhatsApp message with my calendar, unread emails, and top tasks."
"Add image analysis — when I send a photo of a receipt, extract the total, date, and vendor."
"Add a weekly summary — every Friday at 5pm, summarize what I accomplished this week based on completed tasks and sent emails."
Example Prompts That Work
These are real-world prompts (or close variations) that have been used to build production agents on CodeWords:
Personal WhatsApp assistant
"Build me a WhatsApp AI assistant that checks my Google Calendar, reads my Gmail summaries, searches the web for current info, and remembers things I tell it. Keep responses short and casual — like texting a smart friend."
Team Slack bot
"Build a Slack bot for our #general channel that answers questions about our Notion docs, can search the web for current info, and creates Linear tickets when someone says 'create ticket: [description]'."
Customer support agent
"Build a WhatsApp customer service bot that answers questions using our FAQ document, creates support tickets in our system when it can't answer, and escalates to a human when the customer asks for one."
Lead qualification bot
"Build a WhatsApp bot that qualifies leads by asking about their company size, budget, timeline, and needs. Save qualified leads to a Google Sheet with all their answers. Send me a Slack notification for hot leads."
Notice the pattern: Every great prompt includes the platform, the tools, the actions, and the personality. The more specific you are, the fewer iteration rounds you'll need.
Tips from Power Users
Do
Start simple, then expand — Get a basic agent working with 2-3 tools, then add more
Be specific about tone — "Respond like a busy CEO's executive assistant" works better than "be professional"
Test with real scenarios — Don't just say "hi" — ask it to actually check your calendar or search for something
Tell Cody about failures — "It returned an error when I asked about tomorrow's meetings" helps Cody debug faster
Don't
Don't over-specify technical details — Let Cody choose the architecture; describe what you want, not how to build it
Don't skip the research phase for complex agents — 5 minutes of research saves 30 minutes of rebuilding
Don't try to build everything at once — A focused agent with 3 great tools beats a bloated one with 10 buggy ones
Don't forget about personality — An agent that sounds robotic won't get used, no matter how capable it is
Start Building
You've seen the prompts. You know the flow. Now it's your turn.
Click below and Cody will walk you through the entire process — just fill in the brackets with your specifics:
Ready to go? The link below opens Cody with a starter prompt. Just fill in your platform and tools.
Last updated
Was this helpful?