Skip to content

complete execice on lab1 #1566

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
baylina wants to merge 1 commit into
base: main
Choose a base branch
from
Open

complete execice on lab1 #1566

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
145 changes: 132 additions & 13 deletions 1_foundations/1_lab1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -90,9 +90,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Next it's time to load the API keys into environment variables\n",
"# If this returns false, see the next cell!\n",
Expand Down Expand Up @@ -137,7 +148,15 @@
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"OpenAI API Key exists and begins sk-proj-\n"
]
}
],
"source": [
"# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
"\n",
Expand All @@ -153,7 +172,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -166,7 +185,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -342,20 +361,120 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"A strong pain point in **healthcare administration** that is especially ripe for an Agentic AI solution is:\n",
"\n",
"## Prior authorization delays and manual follow-up\n",
"\n",
"### Why this is painful\n",
"Prior authorizations are required by insurers before certain medications, imaging, procedures, or treatments can be approved. In practice, this process is often:\n",
"\n",
"- **Highly manual**\n",
"- **Time-consuming**\n",
"- **Spread across multiple systems**\n",
"- **Prone to delays and errors**\n",
"\n",
"Administrative staff often have to:\n",
"\n",
"- gather clinical notes from the EHR,\n",
"- check payer-specific requirements,\n",
"- fill out different forms for different insurers,\n",
"- submit via portal, fax, or phone,\n",
"- monitor status over days or weeks,\n",
"- respond to requests for more information,\n",
"- and escalate urgent cases to clinicians.\n",
"\n",
"### Why this is such a serious problem\n",
"This creates several business and operational issues:\n",
"\n",
"- **Delayed patient care** \n",
" Patients may wait days or weeks for treatment, imaging, or medication.\n",
"\n",
"- **Staff overload** \n",
" Teams spend large amounts of time chasing approvals instead of doing higher-value work.\n",
"\n",
"- **Revenue leakage** \n",
" Missing documentation or delayed submissions can lead to denials or lost reimbursement.\n",
"\n",
"- **Poor patient experience** \n",
" Patients often don’t understand the delay and call repeatedly for updates.\n",
"\n",
"- **Clinician frustration** \n",
" Providers are pulled into paperwork and peer-to-peer reviews instead of care delivery.\n",
"\n",
"### Why it is a good fit for Agentic AI\n",
"This problem is well-suited for an agent because it requires more than simple automation. It involves:\n",
"\n",
"- **multi-step task execution**\n",
"- **collecting data from different sources**\n",
"- **understanding payer rules**\n",
"- **preparing documents**\n",
"- **submitting through tools or portals**\n",
"- **tracking status over time**\n",
"- **following up automatically**\n",
"- **escalating exceptions to humans when needed**\n",
"\n",
"### What an Agentic solution could do\n",
"An agent could:\n",
"\n",
"1. detect that a prior auth is needed,\n",
"2. pull relevant patient and clinical data from the EHR,\n",
"3. determine the payer’s requirements,\n",
"4. draft or complete the authorization package,\n",
"5. submit it through the correct channel,\n",
"6. track deadlines and status,\n",
"7. respond to routine requests for additional documentation,\n",
"8. notify staff only when a decision, exception, or escalation is needed.\n",
"\n",
"### Why this could be commercially attractive\n",
"The ROI is relatively easy to prove:\n",
"\n",
"- fewer hours spent per authorization,\n",
"- faster turnaround times,\n",
"- fewer denials from incomplete submissions,\n",
"- improved patient throughput,\n",
"- better staff productivity,\n",
"- and potentially faster revenue realization.\n",
"\n",
"If you want, I can next turn this into:\n",
"1. a **startup idea**, \n",
"2. a **problem statement + target customer**, or \n",
"3. a **full Agentic workflow design**.\n"
]
}
],
"source": [
"# First create the messages:\n",
"\n",
"messages = [{\"role\": \"user\", \"content\": \"Something here\"}]\n",
"messages = [{\"role\": \"user\", \"content\": \"pick a business area that might be worth exploring for an Agentic AI opportunity\"}]\n",
"\n",
"# Then make the first call:\n",
"\n",
"response =\n",
"response = openai.chat.completions.create(model=\"gpt-5.4\", messages=messages)\n",
"\n",
"# Then read the business idea:\n",
"\n",
"business_area = response.\n",
"business_area = response.choices[0].message.content\n",
"\n",
"# And repeat! In the next message, include the business area within the message\n",
"\n",
"message2 = [{\"role\": \"user\", \"content\": f\"Here is the business area: {business_area}. Please present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.\"}]\n",
"\n",
"response2 = openai.chat.completions.create(model=\"gpt-5.4\", messages=message2)\n",
"\n",
"pain_point = response2.choices[0].message.content\n",
"\n",
"# And repeat! In the next message, include the business area within the message"
"print(pain_point)"
]
},
{
Expand All @@ -366,9 +485,9 @@
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": ".venv-cursor (Python 3.12)",
"language": "python",
"name": "python3"
"name": "agents-cursor-venv"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -380,7 +499,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.12"
"version": "3.12.8"
}
},
"nbformat": 4,
Expand Down