What is the A2A (Agent2Agent) protocol?

A2A is the open protocol that lets agents built on different frameworks call each other. Agents publish an Agent Card describing their skills, and other agents read that card to decide whether and how to invoke them.

How do I make my existing agent A2A compliant?

Run super a2a adapt --entrypoint : --framework . SuperOptiX reads your agent's structure, derives its skills, and writes an A2A Agent Card plus a conformant server. Your agent code is not modified.

Which agent frameworks does SuperOptiX support for A2A?

Eight: DSPy, CrewAI, the OpenAI Agents SDK, Pydantic AI, Google ADK, the Claude Agent SDK, DeepAgents and the Microsoft Agent Framework. Adaptation works on agents written directly against those libraries, whether or not SuperOptiX built them.

How conformant is the SuperOptiX A2A implementation?

It records zero failures against the official A2A Technology Compatibility Kit. Every requirement the TCK exercises against the conformance harness passes: 73 of 73 at MUST, 7 of 7 at SHOULD, 4 of 4 at MAY. The TCK also prints a headline percentage of 77.7% at MUST, which counts 25 requirements it cannot exercise here, covering authentication, TLS, Agent Card signing and gRPC.

How do I make my agent more discoverable to other agents?

Optimize the Agent Card text. SuperOptiX scores discovery rate, invocation rate and confusion rate over a query set, then uses GEPA to rewrite skill names, descriptions and tags against that score. Agent behaviour is unchanged.

Is SuperOptiX free and open source?

Yes, under the MIT License. The A2A implementation, the adapt command, the conformance suite, the routing optimizer, the SuperSpec compiler and all eight framework integrations are in the open source package. Install with uv tool install superoptix.

Is there a live A2A agent I can call?

Yes. A SuperOptiX agent runs at https://a2a.superoptix.ai on Google Cloud Run, with its Agent Card published at https://superoptix.ai/.well-known/agent-card.json.

Who builds SuperOptiX?

Superagentic AI, which builds agentic AI infrastructure and offers support and custom engineering engagements.

📈 Weights & Biases Integration

📈

W&B

Beautiful Experiment Tracking & Visualization - Team collaboration, hyperparameter optimization, and stunning dashboards for your AI agents.

Beautiful Visualizations

Team Collaboration

Hyperparameter Sweeps

Agent-Specific Metrics

🎯 Why Weights & Biases for SuperOptiX?

W&B provides beautiful experiment tracking with native SuperOptiX integration for agent-specific metrics

Beautiful Visualizations

Stunning charts and dashboards

Experiment Tracking

Compare runs with ease

Team Collaboration

Share experiments with team

Hyperparameter Sweeps

Automated parameter tuning

Model Versioning

Track model improvements

GEPA Tracking

Optimization iterations logged

📦 Quick Start

1. Install & Login

uv pip install wandb
wandb login

2. Run Agent with W&B

# Track agent execution
super agent run my_agent --goal "Analyze data" --observe wandb

# Track optimization runs
super agent optimize my_agent --auto medium --observe wandb

# Track evaluation
super agent evaluate my_agent --observe wandb

3. View in Dashboard

# Open https://wandb.ai/your-username/superoptix

📊 What Gets Tracked

Agent Execution

Metric	Example
execution/latency	1.2s
execution/success_rate	95%
execution/token_usage	1,250
execution/cost	$0.002

GEPA Optimization

Metric	Example
gepa/generation	5
gepa/fitness_score	0.85
gepa/improvement	+0.12
gepa/population_size	20

Framework Comparison

Metric	Example
comparison/dspy	0.80
comparison/openai	0.95
comparison/crewai	0.88
comparison/pydantic-ai	0.92

🚀 Advanced Features

Hyperparameter Sweeps

# Track GEPA parameter tuning
super agent optimize my_agent \
  --auto intensive \
  --observe wandb \
  --wandb-sweep \
  --sweep-config sweep_config.yaml

Automatically find the best GEPA parameters for your agent!

Sweep Configuration

# sweep_config.yaml
program: "super agent optimize"
method: bayes
metric:
  name: "gepa/fitness_score"
  goal: maximize
parameters:
  reflection_lm:
    values: ["qwen3:8b", "llama3:8b", "gemma2:9b"]
  reflection_minibatch_size:
    distribution: int_uniform
    min: 2
    max: 8
  auto:
    values: ["light", "medium", "intensive"]

Team Collaboration

# Share experiments with team
super agent run my_agent \
  --goal "Customer support" \
  --observe wandb \
  --entity "my-company" \
  --project "customer-agents" \
  --tags ["team-shared", "customer-support"]

Multi-Framework Comparison

# Compare frameworks
super agent run sentiment_analyzer --observe wandb --tags ["dspy", "comparison"]
super agent run assistant_openai --observe wandb --tags ["openai", "comparison"]
super agent run researcher_crew --observe wandb --tags ["crewai", "comparison"]

🎯 Best Practices

📁 Project Organization

📁 W&B Projects Structure:

superoptix-agents/ (Main)
superoptix-gepa/ (Optimization)
superoptix-comparison/ (Comparisons)
superoptix-production/ (Monitoring)

🏷️ Tagging Strategy

Use consistent tags:

["framework:dspy", "tier:genies"]
["optimization:gepa", "auto:medium"]
["comparison", "metric:accuracy"]

📊 Metric Naming

Use hierarchical naming:

execution/latency
execution/success_rate
gepa/fitness_score
comparison/dspy/accuracy

Choose W&B when:

You want beautiful visualizations
You need team collaboration features
You're doing hyperparameter optimization
You want to compare experiments easily
You need research-quality tracking
You're building production systems with teams

Consider other options:

MLFlow

For model registry, deployment tracking, artifact management

LangFuse

For LLM-specific features, real-time cost tracking, A/B testing

SuperOptiX Native

For local development, no setup required, works offline

📚 Additional Resources

W&B Documentation

Official docs

W&B Dashboard

Your experiments

SuperOptiX W&B Guide

Complete integration guide

GEPA Optimization

Optimization guide

📈 Ready for Beautiful Experiment Tracking?

Start using Weights & Biases with SuperOptiX for stunning visualizations and team collaboration!