Skip to main content
Connic
Back to BlogProduct Spotlight

Composer SDK: Better Agent Development Tooling

Stop manual uploads and YAML guessing. The Composer SDK adds scaffolding, validation, cloud-backed hot-reload development, and CLI deployments.

December 27, 2025(last updated: July 19, 2026)5 min readAuthor: Connic Engineering

Connic has always let you define agents in YAML and write tools in Python. But until now, getting everything set up and deployed meant a lot of manual work: uploading files by hand, setting up project structures yourself, and hoping you didn't have a typo in your YAML. Today we're releasing the Composer SDK to fix that.

What Was the Problem?

Building agents on Connic worked, but the developer experience had friction:

  • Manual uploads: Every time you changed an agent or tool, you had to upload the files yourself
  • No scaffolding: You had to create the folder structure and boilerplate files from scratch
  • No local validation: You'd only find out about YAML syntax errors or missing tools after uploading
  • Slow iteration: The upload-test-fix cycle was tedious, especially for small changes

The SDK solves each of these with proper CLI tooling.

Build your first agent with Composer

Define agents in YAML, write tools as Python functions, and deploy by pushing to Git.

Try Connic free

What the SDK Does

Install it from PyPI:

Terminal
$ pip install connic-composer-sdk

Then you get a set of commands for the full workflow:

connic init - Project Scaffolding

No more setting up folders by hand. One command creates a complete project structure with example agents, tools, middleware, and a README explaining each piece.

Terminal
$ connic init my-agents

Initialized Connic project in /Users/you/my-agents

Created files:
  agents/assistant.yaml          (LLM agent)
  agents/invoice-processor.yaml  (LLM agent with retry)
  agents/tax-calculator.yaml     (Tool agent)
  agents/document-pipeline.yaml  (Sequential agent)
  agents/orchestrator.yaml       (Orchestrator with trigger_agent)
  agents/retrieval-agent.yaml    (Retrieval agent with RAG)
  tools/calculator.py
  middleware/assistant.py
  .gitignore
  requirements.txt
  README.md

The generated examples cover all agent types (LLM, Tool, Sequential) plus patterns like orchestration and semantic retrieval. Delete what you don't need and modify the rest.

connic lint - Local Validation

Catch errors before uploading. The SDK loads all your agents and tools locally, validates the YAML, checks that referenced tools exist, and shows you what would be deployed.

Terminal
$ connic lint

Connic Composer SDK - Validation

Discovering tools...
  Found 3 tools in 1 modules:
    calculator: add, multiply, calculate_tax

Discovering middlewares...
  Found middlewares for 1 agents:
    assistant: before, after

Loading agents...
  Found 3 agents:

  ┌─ assistant [LLM]
Description: A helpful assistant with calculator tools
Model: gemini/gemini-2.5-flash
Tools: calculator.add, calculator.multiply, calculator.calculate_tax
  └─

  ┌─ tax-calculator [Tool]
Description: Calculates tax directly
Tool: calculator.calculate_tax
  └─

  ┌─ document-pipeline [Sequential]
Description: Processes documents through extraction and validation
Chain: assistant invoice-processor
  └─

Project validation complete

If something's wrong (a misspelled tool reference, invalid YAML, missing middleware) you'll see it immediately instead of after uploading.

connic dev - Hot Reload Development

This is the big one. Start a development session and your local files sync to an isolated cloud runner. Make a change, save the file, and it's live in 2-5 seconds without a manual upload.

Terminal
$ connic dev

Watching for file changes...
  Press Ctrl+C to stop

────────────────────────────────────────────────────────────
  View and trigger your agents: https://connic.co/projects/...
────────────────────────────────────────────────────────────

[14:32:15] Detected change: assistant.yaml
[14:32:16] Files changed, uploading...
[14:32:17] Uploaded 2,847 bytes

The CLI watches your agents/, tools/, middleware/, and requirements.txt. Test using connectors in the dashboard, iterate on your code, and see changes reflected within seconds.

connic deploy - CLI Deployment

Deploy from your terminal or CI/CD pipeline without going through the dashboard.

Terminal
$ connic login              # Save credentials
$ connic deploy             # Deploy to default environment
$ connic deploy --env <id>  # Deploy to specific environment

Combine this with Git integration and a push to your repo deploys automatically. You don't need the CLI for the normal workflow.

New: Import Predefined Tools

Alongside the SDK, you can now import predefined tools into your own custom tools. That means building on top of capabilities like semantic retrieval, web search, or agent orchestration directly from your Python code.

tools/my_tools.py
from connic.tools import retrieval_query, retrieval_store

async def lookup_and_summarize(query: str) -> str:
    """Search the retrieval and return a summary."""
    # Use the predefined retrieval tool
    results = await retrieval_query(
        query=query,
        namespace="documents",
        top_k=5
    )

    # Process and return the results
    if not results:
        return "No relevant information found."

    return "\n".join([r["content"] for r in results])

Previously, predefined tools could only be used directly by agents. Now you can compose them into richer tool logic: query retrieval, process the results, make decisions, return exactly what you need.

Get Started

The SDK is available now. If you've been using Connic without it, the transition is simple: your existing YAML configs and Python tools work the same way. You just get better tooling around them.

Terminal
$ pip install connic-composer-sdk
$ connic init my-agents  # Or use with your existing project
$ cd my-agents
$ connic lint            # Validate everything locally
$ connic dev             # Start hot-reload development

Check out the quickstart guide for a complete walkthrough, or see the SDK documentation for the full reference.

More from the Blog

Product Spotlight

AI Agent Routing: Trigger Agents and Return Results

AI agent routing moves events into an agent and returns results to the right system through Connic sync routes and asynchronous outbound connectors.

August 24, 20269 min read
Product Spotlight

LLM Context Compression for Long-Running AI Agents

Connic compresses older conversation history and oversized tool results, then retries the model call, so long-running agent sessions survive context limits.

July 20, 20268 min read
Product Spotlight

Connic Tests: Catch Agent Regressions Before They Reach Production

A YAML-driven testing framework built for non-deterministic AI agents. Repeated-run pass thresholds, expression-based assertions, custom-code mocking, multimodal fixtures, and a deploy gate that blocks failed checks by default.

May 6, 20268 min read
Product Spotlight

Human-in-the-Loop AI Agents: How Approvals Work in Production

How to pause an AI agent before refunds, deletes, or external calls, route the decision to a human, and resume automatically, with a full audit trail.

April 5, 202610 min read
Product Spotlight

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

You changed the prompt and it feels better. Run a controlled experiment to find out whether it is, 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
Product Spotlight

Agent Guardrails: Real-Time Safety for Your AI Agents

Connic Guardrails intercept agent inputs and outputs in real time to block prompt injection, redact PII, and enforce topic restrictions.

March 3, 20269 min read
Product Spotlight

Connic Bridge: AI Agents for Private Infrastructure

Connic Bridge creates a secure outbound tunnel so your AI agents can reach private Kafka, databases, and internal services without opening inbound ports.

February 19, 20267 min read
Product Spotlight

Agent Observability: Track Costs, Tokens & Runs

Deploying AI agents without visibility is flying blind. Build custom dashboards, track LLM costs per model, and catch failures before users do.

January 23, 20268 min read