Skip to content
Agentic Levels

Everything starts here.

GuestLocal progress only
PreferencesSign in
01Start with one taskBest first move for beginners.02Check your LevelMeasure where you are.03Score an AI resultFind the habit to practice first.04Return to Your WorkScores, links, and checkpoints.
Start here

Begin

HomeThe main entry point.New to AIStart with one useful task.
Know where you are

Measure

Check your LevelUse this after you have tried AI.Fluency ScoreScore an AI result you can review.
Build the habit

Learn

LevelsLessonsTracks
Find the reference

Library

PromptsReferenceResourcesCompare Tools
Turn it into work

Apply

Your Next MoveChoose what AI should change next.Tool SetupGet the tools ready.
Come back later

Return

Your WorkScores, links, and checkpoints.My PathContinue from your level.Updates
Site

Site

PricingAboutFAQ & FeedbackPreferences

© 2026 Fuentes Studio

Privacy·Terms
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

AI workflows built for nurses

Nurses are the largest segment in healthcare and the most underserved by AI products. Zero purpose-built AI workflow tools exist for nursing documentation. This track addresses the five highest-friction nursing tasks with AI workflows built for how nurses actually work, not how physicians work.

Start with care plan draftingLesson 1 takes about 18 minutes
5
Lessons
1–5
Levels
~90
Minutes
💊

What you need before Lesson 1

Approved AI access, a nursing role, and about 18 minutes. No code, no terminal. Every exercise uses de-identified inputs only: age range and clinical findings, never a patient name, MRN, or date of birth. Check your employer's AI policy first; most EHR workstations block external AI tools.

Open tool setup →

Who this is for

Staff nurse writing care plans by hand

Spends 30 minutes per care plan at the end of a shift, when there is the least left to give.

Floor nurse on a high-turnover unit

Gives report from memory at the end of a long shift and worries the next nurse is missing something.

Nurse who writes discharge instructions

Hands a patient instructions, watches them nod, and already suspects they understood half of it.

Med-surg or ICU nurse with polypharmacy

Twelve hours in, scanning fourteen drugs, and the interaction they would catch fresh is the one fatigue lets slip.

Nurse on a high-acuity unit

Knows a single documentation gap can surface in a deposition years later, and wants notes that defend the care given.

Nursing manager or educator

Wants to cut documentation burden across the unit without teaching staff to trust AI output blindly.

5 Lessons · Build in order

Lesson 1
1 lesson

Diagnosis-to-framework in under a minute

Care plan drafting

PMC12195667: AI care plans in 35 seconds vs. about 30 minutes by hand (p < 0.001)

NANDA-I 2024-2026 has 267 approved nursing diagnoses. AI can draft a NANDA-compliant PES-format care plan (Problem, Related To, As Evidenced By) from a diagnosis in under a minute. This lesson teaches the care plan prompt pattern, shows a worked example with a real nursing diagnosis, and covers the one verification step that makes AI-generated care plans safe to use.

Worth knowing:The AI draft is a starting point, not a finished plan. The clinical value is in what you edit out, not what the AI generated. Knowing what to cut is the skill.
Staff nurses who write care plans manuallyNursing managers looking to reduce documentation burdenCNS and NP students learning NANDA documentation
Start Lesson 1 →
Lesson 2
1 lesson

3 minutes instead of 10

SBAR shift handoffs

SBAR reduces handoff communication errors by 75.5% (PMC12668328)

SBAR (Situation, Background, Assessment, Recommendation) is the clinical standard for shift handoffs. AI can produce a complete SBAR from a brief nurse-authored summary in under 3 minutes. This lesson teaches the handoff prompt pattern, covers HCA's finding that AI-assisted handoffs achieve 86% first-attempt accuracy, and shows what information must come from you for the output to be safe.

Worth knowing:The SBAR prompt is also a forcing function for your own clinical thinking. Structuring the input makes you notice what you do not know before the handoff.
Floor nurses on high-turnover unitsCharge nurses who receive handoffs from multiple staffAny unit working to reduce handoff-related adverse events
Start Lesson 2 →
Lesson 3
1 lesson

Grade 5.6, not Grade 12

Patient education at the right reading level

12% of US adults have proficient health literacy

Standard AHA patient education materials average Grade 12 reading level. Claude reduced them to Grade 5.6 in a NYU Langone pilot. This lesson teaches how to specify reading level, cultural context, and health literacy tier in a patient education prompt, and how to verify the output is actually readable, not just shorter.

Worth knowing:The Flesch-Kincaid score is not the full picture. A Grade 6 text with medical jargon is still inaccessible. This lesson shows the two-step check: score first, then jargon scan.
Nurses who write or review patient discharge instructionsPublic health nurses working with underserved populationsAnyone who has watched a patient nod at instructions they did not understand
Start Lesson 3 →
Lesson 4
1 lesson

AI as your second set of eyes

Medication reconciliation

81.6% of warfarin patients have an undocumented DDI at discharge

Medication reconciliation errors cause more preventable adverse events than any other nursing documentation task. This lesson teaches how to use an approved AI tool as a second-check tool for drug-drug interactions, contraindications, and dosing anomalies, and how to document the check in a way that protects the patient and your license. Includes the de-identification protocol: age range and medication list only, never a patient name.

Worth knowing:AI does not replace the pharmacist. It surfaces the questions worth asking the pharmacist. The workflow is: AI flags, nurse escalates, pharmacist confirms.
Med-surg and ICU nurses managing polypharmacy patientsNurses on units with high discharge volumesAnyone who has caught a reconciliation error after discharge
Start Lesson 4 →
Lesson 5
1 lesson

Defensible by design

Documentation that protects your patient and your license

NSO malpractice claims average $210,513; most involve documentation gaps

Defensible documentation is specific, objective, timely, and complete. AI can help with all four, but only if you give it the right inputs. This lesson teaches the documentation prompt pattern that produces legally defensible nursing notes, covers the AMREC framework (98.3% documentation accuracy in a 2025 study), and walks through a documented $9M nursing-documentation case as a failure autopsy.

Worth knowing:The documentation prompt is not a time-saver. It is a structured interview that forces you to articulate what happened before you write it. That structure is what makes the note defensible.
Nurses on high-acuity units where documentation is litigation exposureNursing managers who review documentation for completenessAnyone who has had a documentation gap brought up in a peer review
Start Lesson 5 →

What you need

This track is built for how nurses actually work. The AI is fast; your shift is not, so every workflow is a build-the-habit-once drill you run off the floor.

Approved AI access

Claude, ChatGPT, Gemini, or a workplace-approved AI tool. Follow your employer policy first.

Nursing role

RN, LPN, NP, nursing manager, CNO, or nursing student.

No coding required

All exercises use natural language prompts only.

Give the documentation back its minutes. Keep the judgment yours.

Lesson 1 is 18 minutes. By the end you can hand an approved AI tool a nursing diagnosis and get a NANDA-compliant care plan you review in two minutes instead of building from a blank page in thirty.

Start with care plan drafting