I have been building AI Agents in production for over an year. If you want to learn too, here's a simple tutorial (hands-on):
Today, we'll build and deploy a Coding Agent that can scrape docs, write production-ready code, solve issues and raise PRs, directly from Slack. Tech stack: - Claude Code for code generation - @xpander_ai as the Agent backend - @firecrawl_dev for scraping Let's begin!
For context... xpander is a plug-and-play Backend for agents that manages scale, memory, tools, multi-user states, events, guardrails, and more. Once we deploy an Agent, it also provides various triggering options like MCP, Webhook, SDK, Chat, etc. Check this👇
Moreover, you can also integrate any Agent directly into Slack with no manual OAuth setups, no code, and no infra headaches. Let's build our Coding Agent next and connect it to Slack!
To begin, we build an Agent: - We name it "Coding Agent" - We specify the runtime env. - We specify its instructions We are using the UI builder here, but you can use any framework like LlamaIndex, CrewAI, etc., and deploy it via xpander. I'll cover it soon. Check this👇
Next, we add tools to this Agent: - Firecrawl to scrape docs provided by the user. - Claude Code for code generation, review, etc. - GitHub tools to raise a pull request, list PRs, etc. With that, our Coding Agent is deployed and ready. Check this 👇
Moving on, we connect our Agent to Slack in two steps: - Select Slack as a Task source. - Add the Agent to the Slack workspace. Check this integration👇
Let's test it! Below, I asked it to solve a GitHub issue on my repo, gave some reference docs if needed, and asked it to raise a PR. It worked perfectly. Check this interaction👇
One good thing is that this Slack Agent natively supports messages with audio, images, PDFs, etc. Check this demo 👇
That's how you can build any production-grade Agent and even connect it to Slack in a few steps. You can find more details at Product Hunt: https://www.producthunt.com/pr... (don't forget to upvote ⬆️ )
That's a wrap! If you found it insightful, reshare it with your network. Find me → @_avichawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.