Weco AI Functions - Text-to-Agent Dev Tool

TL;DR

TL;DR: Weco AI Functions turns plain-English prompts into deployed REST API endpoints — structured output, web-search ready, and multimodal in seconds.

Source and Accuracy Notes

⚠️ This section is MANDATORY. All links must be verified from actual source, not guessed.

• Project page: aifunction.com
• Docs: aifunction.com/docs
• Pricing page: aifunction.com/pricing
• HN launch thread: news.ycombinator.com/item?id=42636927
• Author: Zhengyao (via HN)

What Is Weco AI Functions?

Weco AI Functions is a text-to-agent development tool that converts a one-sentence idea into a live, production-ready AI function endpoint. Each generated function is structured, fast, web-search-ready, multimodal, and built to scale via REST API.

The product targets developers building AI-powered products who want to skip the boilerplate: instead of wiring up an LLM, choosing a provider, writing prompts, and handling output parsing — you type what you want and get a deployed endpoint.

Key capabilities described on the landing page:

• Text-to-function generation from plain-English prompts
• Structured JSON output with schema validation
• Web search integration (built-in)
• Multimodal support (vision-capable)
• REST API access from any language or platform
• Python client library for direct integration
• Google Sheets add-on for no-code usage
• Up to 1,000 requests per minute on the Professional Plus plan

Setup Workflow

Step 1: Create a Free Account

Sign up at aifunction.com and claim the free tier — up to 10 functions, 100 requests per minute, and $1 in inference credits monthly.

Step 2: Describe Your Function

Use the prompt interface on the landing page. Type a one-sentence description of what you want, for example:

• “Classify this email as spam or not spam”
• “Extract key insights from this article”
• “Summarize this meeting transcript”

Pre-built templates include Insights Creator, Data Analyzer, Email Classifier, Spam Filter, and Summarizer.

Step 3: Review and Edit the Generated Schema

Weco generates the function schema automatically. You can edit the function up to 20 times per month on the free plan (unlimited on paid plans) before deploying.

Step 4: Call the API

Once deployed, call your function via REST:

curl -X POST https://api.aifunction.com/v1/functions/[your-function-id] \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": "your text here"}'

The Python client:

from wecoai import WecoClient

client = WecoClient(api_key="YOUR_API_KEY")
result = client.functions.call("your-function-name", input="your text here")
print(result)

Step 5: Embed in Google Sheets

Install the AI Function Builder add-on in Google Sheets. Apply AI functions directly to cells without writing any code:

=AI_FUNCTION("classifier", A2)

Pricing

Three tiers are available:

| Plan | Price | Functions | Editing | RPM | Inference Credits | |---|---|---|---|---|---| | Free | $0 | Up to 10 | Up to 20/mo | 100 | $1/mo | | Professional Plus | $29/mo | Unlimited | Unlimited | 1,000 | $10/mo | | Enterprise | Custom | Unlimited | Unlimited | Custom | Custom |

Enterprise includes on-premise deployment and technical support.

Practical Evaluation Checklist

• Landing page loads and prompt interface is functional
• Docs page accessible at /docs with quickstart guide
• Pricing page shows three tiers with clear feature differentiation
• Pre-built function templates visible in the UI (Insights Creator, Data Analyzer, Classifier, Spam Filter, Summarizer)
• REST API endpoint format confirmed
• Python client library referenced in docs
• Google Sheets add-on confirmed as an integration option

Security Notes

• API key authentication is required for all function calls
• Inference credits are consumed per request on usage-based billing
• On-premise deployment available for Enterprise customers with data sovereignty requirements

FAQ

Q: Do I need a credit card to start? A: The free tier requires no payment method. The Professional Plus plan at $29/month requires payment info.

Q: What LLM providers does Weco use? A: The product abstracts the provider layer. The exact models used are not explicitly listed in the public docs.

Q: Can I self-host Weco AI Functions? A: On-premise deployment is available on the Enterprise plan only.

Q: What does “web-search-ready” mean? A: Generated functions can optionally incorporate live web search results as context for their responses, according to the landing page.

Q: Is there a rate limit on the free plan? A: Yes — up to 100 requests per minute, and up to 10 functions total.

Conclusion

Weco AI Functions targets developers who want a shortcut from “I need an AI feature” to “it’s live.” The free tier is generous enough to evaluate the core workflow without commitment, and the $29 Professional Plus plan unlocks unlimited functions and higher throughput for serious projects. If you are tired of wiring up the same LLM boilerplate for every new AI feature, this is worth a look.

The product is at aifunction.com.