The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
AI-Agent Reporting Automation
Production AI-agent service that turns stakeholder requests into verified BI reports end to end: a request posted in Basecamp triggers a gated agent workflow that validates SQL against approved business logic, creates or updates the Metabase report, and verifies every write by exact read-back before replying with evidence. Containerized Node.js services (Docker Compose) with a fully offline test suite and CI. Built to cut the analytics team's ad-hoc reporting load - and to prove AI agents can be trusted with production writes when properly gated.
@Huseyn Ahmadli The exact read-back after every Metabase write is a solid safeguard. Does the offline test suite also simulate schema changes or stale approved business logic?
Good question. Those are two different failure modes, and the system treats them differently.
On schema changes: the business logic and the schema live in the same place. The service reads business rules from pinned clones of the product repositories themselves, and schema...
Solid setup. One thing that has saved me a lot in write-capable agents: log every agent turn (prompt, tool calls, outcome) to an audit table and add a replay mode — when a report comes out wrong, you can reproduce the exact run instead of debugging blind. Also worth setting a...
Both points land. Some of that is already in place: every run persists its state, prompts, payloads, and final responses to volumes, there's a /runs view for run history, and failed events support an explicit retry that reuses the original agent thread with its original context,...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
People don’t like to wait for your customer support system.
It shows that you don’t care enough for your users.
Introducing Assistia, a template for AI customer service automation platforms.
Designed specifically for SaaS companies.
It’ll reduce response times and cut support costs by up to 70%.
With its visual storytelling and social proof sections, strategic CTAs, and mobile-first design,
You can launch your website fast.
Check the comments for the links.
I’m currently building a RAG system for an e-commerce company, basically giving an AI assistant access to the company’s own knowledge and product information so it can give useful, context-aware responses instead of just generating random answers.
The interesting part isn’t just connecting an LLM.
It’s making sure the AI can:
→ Find the right information
→ Understand the user’s question
→ Retrieve relevant context
→ Give an accurate response
→ Actually be useful in a real business workflow
Still working on it, but I’m excited about where it’s going.
This is the kind of AI automation I enjoy building, systems that solve actual business problems, not just AI demos.
Building something similar? Let’s talk.
One thing that will save you a lot of time: build a small evaluation set early — 50–100 real questions with the document or product that should be retrieved for each. Before tuning prompts, measure retrieval quality (does the right doc surface in the top 3?) with it. Chunk size...
This is my AI Customer Support and Lead Generation Agent, built with n8n.
The workflow starts when a customer sends a message. The AI Agent understands the customer's request and responds automatically.
It also uses conversation memory to maintain context during the conversation.
When a customer wants to place an order, the agent collects important details such as their name, phone number, email, service, quantity, and requirements.
Finally, the customer's information is automatically saved into Google Sheets as a new lead.
This automation helps businesses handle customer inquiries and organize leads without manual work.
Agents are amazing. Building & using them is a genuine wise career choice in my opinion.
