Connic
Back to BlogChangelog

What We Shipped in October 2025

10 deployment regions across 5 continents, import predefined tools (trigger_agent, query_knowledge, web_search) in custom Python code.

November 3, 20254 min read

October focused on giving you more control over where your agents run and how you build custom tools.

Expanded Deployment Regions

Deploy agents in 10 regions across 5 continents:

North America
  • US West (Oregon)
  • US East (Virginia)
Europe
  • Europe West (Belgium)
  • Europe North (Finland)
  • Europe Central (Poland)
Asia Pacific
  • Asia South (Mumbai)
  • Asia Southeast (Singapore)
  • Asia East (Taiwan)
Other
  • South America (Chile)
  • Africa (South Africa)

Select your region when creating a project or change it later in Project Settings. Region changes trigger a redeployment of your agents.

Import Predefined Tools in Custom Code

All predefined tools are now importable in your custom Python tools:

tools/research.py
from connic.tools import (
    trigger_agent,      # Call other agents
    query_knowledge,    # Semantic search
    store_knowledge,    # Save to knowledge base
    delete_knowledge,   # Remove entries
    web_search          # Real-time web search
)

async def research_topic(topic: str) -> dict:
    """Combines web search with knowledge storage."""

    # Search the web for recent information
    results = await web_search(query=topic, max_results=5)

    # Store findings in knowledge base
    for result in results:
        await store_knowledge(
            content=result["snippet"],
            metadata={"source": result["url"], "topic": topic}
        )

    # Delegate summarization to another agent
    summary = await trigger_agent(
        "summarizer",
        payload={"content": results},
        wait_for_result=True
    )

    return {"results": results, "summary": summary}

This lets you build complex workflows that combine multiple capabilities in a single tool call.

Documentation Table of Contents

Longer documentation pages now have an auto-generated table of contents in the right sidebar. It highlights your current section as you scroll and lets you jump to any heading directly.

More from the Blog

Changelog

What We Shipped in April 2026

Human-in-the-loop approvals, Bridge for custom tools and private services, tool hooks, discoverable tools, AI dashboard builder, custom OpenAI-compatible providers, and live logs from your own code.

May 3, 20267 min read
Product Spotlight

Agent Approvals: Human-in-the-Loop for Production AI

AI agents that delete data, process refunds, or call external APIs need a safety net. Connic Approvals pause agent execution at critical moments, wait for human review, and resume automatically. You get control without killing autonomy.

April 5, 202610 min read
Product Spotlight

A/B Testing for AI Agents: Ship Better Prompts with Confidence

You changed the prompt. It feels better. But is it actually better? Learn how to run controlled experiments on your AI agents and let real traffic decide.

March 27, 20269 min read
Product Spotlight

Secure AI Agents: A Production Safety Checklist

Shipping AI agents without a security strategy is a liability. A practical checklist covering prompt injection, PII handling, output validation, and the guardrails you need before go-live.

March 21, 202612 min read
Tutorial

AI Agents: From Prototype to Production

Your demo works great until you have 1,000 concurrent users. A practical guide to the production requirements most teams find out about too late.

January 10, 202610 min read
Tutorial

Hidden Costs of Self-Hosting AI Agents

"We'll just deploy it on Kubernetes" - famous last words. The true cost of self-hosting AI agents vs. a managed platform.

December 18, 20257 min read