Get Job Alerts
One email when a teaching platform opens hiring or a new AI training project drops. No weekly filler.
Job alerts
Get Job Alerts
One email when a platform on this site starts hiring, checked by hand. No spam, leave any time.
Small business clients want a smart assistant they can talk to and actually do things, not just answer questions. This AI automation gives you a deployable chatbot prototype wired to live data sources that you can hand over, extend, and bill for.
What This Automation Does
- Accepts natural language questions from a user via a chat interface and routes them to an AI agent powered by Google Gemini
- Fetches real-time weather forecasts and pulls the latest headlines from any RSS feed based on what the user asks
- Remembers recent conversation turns so the agent handles follow-up questions without losing context
- Accepts additional integrations like email or calendar as paid upgrade modules, making it a repeatable upsell vehicle
Tools Used
- Google Gemini
- n8n
Where to Get Hired for This Skill
On Contra, top freelancers across this stack have earned 75 combined verified reviews from real client projects.
Source: Contra freelancer search · refreshed 26 May 2026
Start Earning as a Freelancer on Contra
Contra is a commission-free professional network for independents. Browse live AI automation work and keep what you earn.
Join Contra Free →How To Build It
Secure a free Google Gemini API key
Create a free API key at Google AI Studio so the agent has a live language model powering its reasoning and conversation, which takes under two minutes and costs nothing to start.
Connect the language model credential
Attach the Google Gemini API key to the AI agent so it can process user messages, decide which tool to invoke, and compose accurate, context-aware replies.
Wire the weather and news data sources
Link a live weather forecast endpoint and an RSS feed reader to the agent as callable tools, so it independently decides when to pull real-world data rather than guessing from training data.
Configure the agent system message for the client
Write a short set of instructions that define the agent's personality, scope, and tone so the delivered product feels custom-built for that specific business rather than a generic demo.
Validate the full conversation loop end to end
Send a sequence of follow-up questions through the chat interface to confirm the memory layer retains context across turns, tools return accurate live data, and the agent responds coherently before handing it to the client.
Pitfalls
- Google Gemini API keys created on free-tier projects have rate limits that will cause the agent to fail silently under moderate usage, so flag this clearly in your delivery scope and document the upgrade path to a paid tier.
- RSS feeds from news sources change URLs or go offline without warning, which breaks the news tool and makes the agent appear broken to the client even though the core automation is fine. Build in a fallback or monitoring step.
- Conversation memory is window-based and drops older turns, so clients who test long multi-step workflows may think the agent has forgotten critical context it was never designed to retain. Set the right expectations upfront in your handover documentation.
FAQ
Can I build this without coding?
Yes. The entire setup involves pasting an API key and adjusting a text field for the agent's instructions. No code is written at any point, which also means clients with no technical background can maintain it after handover.
How long does it take?
Initial setup runs under five minutes once you have the Google Gemini API key. Factor in another 30 to 60 minutes if you are customising the system message, swapping in a client-specific RSS feed, or documenting the handover package.
What can I charge?
Pricing is your call based on your market and positioning. What this workflow gives you is a fast-to-deliver, easy-to-demo prototype that naturally opens the door to higher-value follow-on work adding integrations like Gmail, Google Calendar, or a CRM.
Which tool is required vs optional?
Google Gemini is required as the language model driving the agent's reasoning. The weather and news tools are included as demonstrations and can be swapped out or removed entirely. Any other integrations, such as email or calendar, are optional extensions you can sell separately.
This is original DigiNo analysis. The underlying automation pattern is a community workflow template – view the original on n8n.
Get Job Alerts
One email when a teaching platform opens hiring or a new AI training project drops. No weekly filler.
Job alerts
Get Job Alerts
One email when a platform on this site starts hiring, checked by hand. No spam, leave any time.
Generate AI videos from Google Sheets and publish to YouTube