tracing_an_agno_agent.ipynb•7.98 kB
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<center>\n",
" <p style=\"text-align:center\">\n",
" <img alt=\"phoenix logo\" src=\"https://raw.githubusercontent.com/Arize-ai/phoenix-assets/9e6101d95936f4bd4d390efc9ce646dc6937fb2d/images/socal/github-large-banner-phoenix.jpg\" width=\"1000\"/>\n",
" <br>\n",
" <br>\n",
" <a href=\"https://arize.com/docs/phoenix/\">Docs</a>\n",
" |\n",
" <a href=\"https://github.com/Arize-ai/phoenix\">GitHub</a>\n",
" |\n",
" <a href=\"https://arize-ai.slack.com/join/shared_invite/zt-2w57bhem8-hq24MB6u7yE_ZF_ilOYSBw#/shared-invite/email\">Community</a>\n",
" </p>\n",
"</center>\n",
"<h1 align=\"center\">Tracing an Agno Policy Research Agent</h1>"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install -q agno duckduckgo-search newspaper4k lxml_html_clean openinference-instrumentation-agno openinference-instrumentation-openai openai arize-phoenix"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Connect to Phoenix"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"For this example you'll use a hosted version of Phoenix - if you don't already have an account, you can create one for free [here](https://app.phoenix.arize.com/). If you'd prefer to self-host Phoenix, then follow the [instructions here](https://arize.com/docs/phoenix/self-hosting)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from getpass import getpass\n",
"\n",
"if \"OPENAI_API_KEY\" not in os.environ:\n",
" os.environ[\"OPENAI_API_KEY\"] = getpass(\"🔑 Enter your OpenAI API key: \")\n",
"\n",
"if \"PHOENIX_API_KEY\" not in os.environ:\n",
" os.environ[\"PHOENIX_API_KEY\"] = getpass(\"🔑 Enter your Phoenix API key: \")\n",
"\n",
"if \"PHOENIX_COLLECTOR_ENDPOINT\" not in os.environ:\n",
" os.environ[\"PHOENIX_COLLECTOR_ENDPOINT\"] = getpass(\"🔑 Enter your Phoenix Collector Endpoint\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from openinference.instrumentation.agno import AgnoInstrumentor\n",
"from openinference.instrumentation.openai import OpenAIInstrumentor\n",
"\n",
"from phoenix.otel import register\n",
"\n",
"tracer_provider = register(project_name=\"agno\")\n",
"AgnoInstrumentor().instrument(tracer_provider=tracer_provider)\n",
"OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Building your Agno Agent"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from textwrap import dedent\n",
"\n",
"from agno.agent import Agent\n",
"from agno.models.openai import OpenAIChat\n",
"from agno.tools.duckduckgo import DuckDuckGoTools\n",
"from agno.tools.newspaper4k import Newspaper4kTools\n",
"\n",
"policy_research_agent = Agent(\n",
" model=OpenAIChat(id=\"gpt-4o\"),\n",
" tools=[DuckDuckGoTools(), Newspaper4kTools()],\n",
" description=dedent(\"\"\"\\\n",
" You are a senior policy analyst who advises G20 governments on the\n",
" governance of advanced AI systems. Your expertise spans: 🌐\n",
"\n",
" • Comparative regulatory analysis (EU AI Act, U.S. EO, China’s draft regs)\n",
" • Risk taxonomy & mitigation frameworks (NIST, ISO, OECD)\n",
" • Multi‑stakeholder negotiation and diplomacy\n",
" • Economic impact modelling and labour‑market studies\n",
" • Standards‑setting processes (IEEE, ISO/IEC)\n",
" • Enforcement mechanisms and audit requirements\n",
" • Rights‑based and ethics‑based approaches to AI governance\\\n",
" \"\"\"),\n",
" instructions=dedent(\"\"\"\\\n",
" 1. Discovery Phase 🔍\n",
" – Gather at least 12 authoritative sources: legislation, white‑papers,\n",
" peer‑reviewed studies, think‑tank reports, and reputable news.\n",
" – Prioritise the most recent versions / amendments (≤ 12 months).\n",
" – Identify divergent regional approaches and key stakeholders.\n",
"\n",
" 2. Comparative Analysis 📊\n",
" – Map each region’s regulatory scope, risk tiers, and enforcement powers.\n",
" – Cross‑reference impact assessments and economic forecasts.\n",
" – Highlight areas of convergence and friction (e.g., foundation‑model audits).\n",
"\n",
" 3. Recommendation Draft ✍️\n",
" – Craft a concise, actionable brief for policymakers.\n",
" – Include trade‑offs, implementation timelines, and anticipated market effects.\n",
" – Use bullet points and tables where clarity improves.\n",
"\n",
" 4. Validation & Quality Control ✓\n",
" – Verify every cited statute / article for publication date and authenticity.\n",
" – Ensure balanced representation of civil‑society and industry viewpoints.\n",
" – Flag any major uncertainties or data gaps.\n",
" \"\"\"),\n",
" expected_output=dedent(\"\"\"\\\n",
" # {Short, Punchy Headline on AI Governance Landscape} 🌐\n",
"\n",
" ## Executive Summary\n",
" {One‑paragraph snapshot of regulatory momentum and stakes}\n",
"\n",
" | Region | Current Status | Key Provisions | Enforcement Timeline |\n",
" |--------|---------------|----------------|----------------------|\n",
" | EU | ... | ... | ... |\n",
" | U.S. | ... | ... | ... |\n",
" | ... | ... | ... | ... |\n",
"\n",
" ## Comparative Findings\n",
" - **Risk Classification:** {...}\n",
" - **Testing & Audit Requirements:** {...}\n",
" - **Penalties & Incentives:** {...}\n",
"\n",
" ## Strategic Implications\n",
" {Market, innovation, and compliance impacts for enterprises}\n",
"\n",
" ## Policy Recommendations\n",
" 1. **Short‑Term (0‑12 mo):** {...}\n",
" 2. **Medium‑Term (1‑3 yrs):** {...}\n",
" 3. **Long‑Term (>3 yrs):** {...}\n",
"\n",
" ## Sources\n",
" {Numbered list, each with publication date and 1‑line relevance note}\n",
"\n",
" ---\n",
" Prepared by AI Policy Analyst · Published: {current_date} · Last Updated: {current_time}\n",
" \"\"\"),\n",
" markdown=True,\n",
" show_tool_calls=True,\n",
" add_datetime_to_instructions=True,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"policy_research_agent.print_response(\n",
" \"Analyze the current state and future implications of artificial intelligence regulation worldwide\",\n",
" stream=True,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## View your Traces in Phoenix!\n",
"\n",
""
]
}
],
"metadata": {
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}