dlivrd Academy

Sign in to continue

dlivrd Academy · dlivrd Technology Inc.

Play. Learn. Apply.

Welcome to dlivrd Academy

Let's set up your profile before we get started. This only takes a minute.

Choose your avatar
?
Good to see you

Welcome back

🔍
Course

Artificial Intelligence

Master Claude AI: prompt like a pro, automate your work, and qualify for your Claude seat.

dlivrd × Claude More coming soon
Course

Google Workspace

Master the full Google Workspace: Gemini AI and Google Sheets to work faster and smarter every day.

dlivrd × Gemini dlivrd × Google Sheets
Course

Mindfulness

Wellbeing, breathing techniques, and resilience practices for the dlivrd team.

Box Breathing Body Scan Focus Reset
Course

dlivrd Playbook

Principles from the world's best books, applied to your work at dlivrd. Start with Atomic Habits and Deep Work.

Atomic Habits Deep Work More coming soon
Foundations · TED
Foundations Series
Mindset · Grit · Conversations · Resilience · Apply
New →
👑
Course · Coming soon

DTI Leaders Masterclass

Leadership development, strategic thinking, and executive skills for dlivrd leaders.

Email
Department
Company
dlivrd Academy

All Courses

Choose a course to get started or continue where you left off.

🤖
AI Tools

dlivrd × Claude

AI Access Qualification Program. Complete 13 steps to earn your Claude seat.

14 steps ~1.5 hrs
Not started
Google AI

dlivrd × Gemini

Gemini AI Foundations Program. Master Google AI across Gmail, Docs, Sheets, and beyond.

4 modules ~1 hr
Not started
📊
Google Workspace

dlivrd × Google Sheets

Master Google Sheets from fundamentals to advanced data analysis. Includes a real dlivrd operations project reviewed by AI.

3 modules + project ~4 hrs
Not started
🛠️
DTI Tools
Coming Soon

DTI Tools Mastery

ClickUp, HubSpot, Slack workflows, and the full dlivrd tech stack. Launching separately.

🧘
Wellness

dlivrd Wellness

Simple mindfulness practices to reset, refocus, and show up as your best self at work.

3 modules ~45 min
📚
dlivrd Playbook

dlivrd Playbook

Atomic Habits and Deep Work — two frameworks that will change how you work forever.

2 books ~2 hrs
Foundations Series
TED · Premium

Foundations Series

World-class TED Talks on mindset, grit, and real-world thinking. Short, impactful, and built for how you actually work.

5 lessons ~45 min
New ✦
+
More programs coming soon
Check back for new training

dlivrd Academy · dlivrd Technology Inc.

🛠️
DTI Tools · dlivrd Technologies
DTI Tools Mastery
Master the tools that power dlivrd every day.
1
Module 1: ClickUp for Operations
Tasks, workflows, and team coordination in ClickUp
What you will learn
How dlivrd uses ClickUp to manage operations, track driver issues, escalate tickets, and run cross-team projects. You will learn how to create and assign tasks, use the correct workspace (ID: 9017073530), set priorities, and communicate through task comments instead of Slack for traceable decisions.
Key skills
Task creation and assignment · Priority levels · Status workflows · Comments vs Slack · Dashboards for your team · Time tracking
📌 Coming soon
Video lessons and an interactive ClickUp simulation are being built for this module. Check back soon.
2
Module 2: HubSpot CRM
Client management, pipelines, and deal tracking
Contact management · Deal pipelines · Email sequences · Reporting dashboards · Integration with dlivrd ops
🔒 Unlocks after Module 1
3
Module 3: Slack Workflows
Communication standards and automation at dlivrd
Channel structure · Notification etiquette · Workflow builder · Connecting Slack to ClickUp and HubSpot · When to use Slack vs email vs ClickUp
🔒 Unlocks after Module 2
4
Module 4: The dlivrd Tech Stack
How all the tools connect and the bigger picture
Stripe · Google Workspace · FULFLLD · The dlivrd app · How data flows between systems · What to use when and why
🔒 Unlocks after Module 3
DTI Tools Mastery is actively being built.
Module 1 content launches first. You will be notified when new modules go live.
Foundations Series · TED Talks
Foundations Series
World-class thinking, built for how you actually work.
These are not lectures. They are short, powerful talks from the world's leading researchers on how humans think, grow, and perform. Watch, reflect, and apply.
1
Growth Mindset
Carol Dweck · TED Talk · ~10 min
TED
Core Insight
The word "yet" is more powerful than it sounds. Students who believe abilities can be developed don't just try harder — their brains literally form new connections under challenge. Fixed mindset runs from difficulty. Growth mindset runs toward it.
What to take into your work
1.When something feels hard, that's your neurons building new connections — not a sign you can't do it.
2.Add "yet" to any limiting belief. "I don't know how to do this" becomes "I don't know how to do this yet."
3.Praise process over results — in yourself and in your team. Effort, strategy, and improvement matter more than the outcome.
2
Grit
Angela Duckworth · TED Talk · ~6 min
TED
Core Insight
Across West Point, spelling bees, and inner-city classrooms — the single biggest predictor of success wasn't IQ or talent. It was grit. Passion and perseverance for long-term goals. Living life like a marathon, not a sprint.
What to take into your work
1.Talent without follow-through is just potential. The data is clear — gritty people outperform talented people who quit.
2.Identify one long-term goal you are committed to regardless of how slow the progress feels right now.
3.Failure is not permanent. Growth mindset is the bridge between falling short today and succeeding long-term.
3
10 Ways to Have a Better Conversation
Celeste Headlee · TED Talk · ~12 min
TED
Core Insight
A conversation requires a balance between talking and listening — and we've lost that balance. Headlee's 10 rules are simple but most people violate most of them every single day. The most important: actually listen, not to reply, but to understand.
The 10 rules — applied to dlivrd
1. Don't multitask — be fully present in every Slack call or 1:1
2. Don't pontificate — enter every team conversation ready to learn
3. Use open-ended questions with drivers, clients, and teammates
4. Go with the flow — let ideas come and go, stay present
5. If you don't know, say so — credibility is built on honesty
6. Don't equate — their experience is theirs, not yours
7. Don't repeat yourself — say it once, clearly
8. Stay out of the weeds — people care about you, not the details
9. Listen — the most important rule, full stop
10. Be brief — respect people's time and attention
4
3 Secrets of Resilient People
Lucy Hone · TED Talk · ~16 min
TED
Core Insight
Lucy Hone is a resilience researcher who lost her 12-year-old daughter in a car crash. She used her own research to survive. Her message: resilience isn't a fixed trait only some people have. It requires ordinary processes — and the willingness to try them.
The 3 strategies — applied to dlivrd
1. Suffering is part of life
When a campaign fails, a client churns, or a launch goes wrong — that is not discrimination. That is work. Everyone on this team will face setbacks. Knowing this in advance is not pessimism, it's preparation.
2. Choose where you focus your attention
In a hard week, your brain will find all the things going wrong. Train it to also find what is going right. One team win, one piece of good feedback, one problem you solved. Don't lose what you have to what you have lost.
3. Ask: is this helping or harming me?
Scrolling through a frustrating email thread at midnight. Replaying a difficult conversation. Avoiding feedback you need. Ask the question. The honest answer puts you back in the driver's seat.
5
Application Lesson
Put it into practice at dlivrd · ~15 min
Apply
What this lesson does
You have watched the research. Now apply it. You have watched the research. Now apply it. This lesson brings together Growth Mindset, Grit, Better Conversations, and Resilience into how you actually show up at dlivrd every day.
Reflection prompts
💭 Where in your current role do you notice fixed mindset showing up — tasks you avoid, feedback you deflect, challenges you label as "not for me"?
💭 What is your one long-term goal at dlivrd right now? Is your daily effort aligned with it?
💭 Think of a recent failure or setback. What would Angela Duckworth say about how you responded to it?
G-Suite Course · dlivrd × Gemini
Gemini AI Foundations Program
4 modules to master Google AI across Gmail, Docs, Sheets, and beyond.
Module 0: Introduction to Gemini
Module 1: Gemini in Gmail and Docs
Module 2: Gemini in Sheets and Slides
Module 3: Advanced Gemini Workflows
G-Suite Course · dlivrd × Google Sheets
Google Sheets Mastery Program
3 modules and a real dlivrd operations project reviewed by AI.
Module 1: Sheets Fundamentals
Module 2: Intermediate Sheets
Module 3: Advanced Sheets
Mindfulness Course · dlivrd Wellness
dlivrd Wellness
Simple practices to reset, refocus, and show up as your best self at work.
1
Module 1: Box Breathing
A simple reset technique for stress and anxiety
What you just learned
Box breathing is a 4-step reset
Inhale for 1-5 seconds, hold, exhale for 1-5 seconds, pause. Repeat 7-10 times. That's it. No equipment, no quiet room required. You can do this in a parking lot before a hard call.
Two types of benefits
Physiological: reduces blood pressure and heart rate, increases oxygen. Psychological: the repetition pulls your attention away from the stressor and anchors it to your breath.
Why this matters at dlivrd
Operations moves fast. When a route breaks, a driver goes dark, or a client escalates, your nervous system reacts before your brain does. Box breathing gives you a 60-second tool to get back in control before you respond. One round before a difficult conversation can change how it goes entirely.
When to use it
Before a client call you're nervous about · After getting a stressful Slack message · Midday when you feel your focus slipping · Before giving feedback to someone on the team
Practice: Box Breathing

Inhale 4 counts, hold 4, exhale 4, hold 4. Click Start to guide one full session.

Ready
Press start to begin
2
Module 2: Daily Calm Body Scan
A 10-minute guided body scan to release tension
What you just learned
Your body holds stress before your mind notices it
Tension in your shoulders, jaw, or back is often stress you haven't consciously registered yet. The body scan teaches you to notice it early, which means you can address it before it affects your decisions and your interactions with people.
The amygdala and why stress clouds judgment
When you're under stress, your amygdala fires and makes it harder to think clearly and make good decisions. Meditation doesn't eliminate stress, it reduces the amygdala's grip so you can access your rational brain again. That's the science behind why "taking a breath" actually works.
Why this matters at dlivrd
The best time to do this is before you hit overwhelm, not after. If you use the 10-minute body scan at lunch or before the end of your shift, you're maintaining your capacity to perform rather than trying to recover from burnout. Preventative beats reactive every time in this kind of work.
The technique in brief
Head → face → jaw → neck → shoulders → arms → hands → chest → back → abdomen → pelvis → legs → feet. At each stop: observe, breathe into it, soften. Don't force. Don't judge.
3
Module 3: Focus Reset
A 5-minute intention setting session
What you just learned
Intentional reflection changes the rest of your day
Even 5 minutes of intentional stillness mid-day resets your direction. The practice asks you to name one thing that made you smile today and one small thing to look forward to. That's it. It's not about productivity — it's about reminding yourself why the work matters.
Your breath is your anchor
When your mind wanders during any mindfulness practice — and it will — the breath is always there to return to. You don't fail at meditation by getting distracted. You practice it by noticing you got distracted and coming back. That noticing is the skill.
Why this matters at dlivrd
You are a priority. Not in a motivational-poster way — in a practical way. A team member who is burned out, reactive, and running on empty makes worse decisions, communicates less clearly, and is harder to work with. Taking 5 minutes for a focus reset is not time away from the work. It is investment in the quality of the work you do after.
Build the habit
Set a recurring 5-minute block on your calendar for midday. Label it whatever you want. The goal is consistency over perfection — three times a week for two weeks and you'll feel the difference.
Playbook Course · dlivrd Principles
dlivrd Playbook
Best-book principles distilled into videos, PDFs, and quizzes — applied to your work at dlivrd.
Book 1
Atomic Habits
James Clear · 8 min summary
Key principles for dlivrd
The habit loop: Cue, craving, response, reward. Every habit follows this pattern.
Make it obvious: Design your environment so good behaviors are visible and easy.
Make it easy: Reduce friction. Lower the barrier to starting.
Never miss twice: Missing once is an accident. Missing twice starts a new bad habit.
Habit tracker: Don't break the chain. Consistency beats intensity.
🎯
Book 2
Deep Work
Cal Newport · 15 min summary
Key principles for dlivrd
🎯 Deep vs shallow: Email and meetings are shallow. Strategic thinking is deep. Know the difference.
🎯 Attention residue: Every task switch leaves part of your brain behind. Minimize it.
🎯 Schedule distractions: Don't take breaks from distraction. Take breaks from focus.
🎯 Shutdown ritual: Review tasks, plan tomorrow, say your shutdown phrase out loud.
🎯 Embrace boredom: Focus is a skill built through practice, not willpower.
More books coming
The Lean Startup · Never Split the Difference · Thinking Fast and Slow
Access temporarily locked

Scenario quiz locked for 7 days.

A failed attempt was recorded. You need to wait 7 days before retrying.

Use this time to prepare:
✦ Re-watch the dlivrd briefing video in Step 12
✦ Review the prompting cheat sheet in Step 8
✦ Practice with the Operations Coach in Step 10
✦ Email sam.hart@dlivrd.io if you need support
Time remaining
Calculating...

Questions? sam.hart@dlivrd.io

Welcome back

Pick up where you left off.

Your progress has been saved.

Your progress
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Claude
dlivrd

dlivrd is adopting AI.
Here's what that means for you.

We're rolling out Claude, an AI assistant by Anthropic, to help our teams work smarter. This isn't about replacing people. It's about giving our best people better tools.

~45
Minutes
4
Quizzes
80%
To pass
You can pause and resume anytime. Progress is saved automatically so you never lose your place.
Why now?
AI is changing how work gets done across every industry. dlivrd is being intentional, so we move fast, without moving recklessly.
Why Claude?
Claude is built by Anthropic, one of the world's leading AI safety companies. It's designed to be helpful, honest, and safe, with enterprise-grade privacy controls.
Why selective access?
Access is earned, not given. We want people who understand Claude and have a real use case. That's what this program is for.
Your 9-step journey to Claude access
Step 1, Welcome & overview (you are here)
Step 2, Video modules & prompting cheat sheet
Step 3, dlivrd usage policy + policy check
Step 4, Learning module (5 lessons)
Step 5, Foundation quiz
Step 6, Register for access
Step 7, dlivrd scenario briefing
Step 8, Scenario quiz (90% to pass)
Step 9, Use case submission
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 2 of 13, Video modules
Watch these first.

3 video modules covering Claude foundations, Co-work, and prompting. Complete all 3 in order, each one unlocks the next.

1
Module 1, Claude foundations & interface
2 videos · Official intro + beginner to pro crash course
1
Claude foundations
The official Anthropic intro: prompting framework, models, Projects, Artifacts, and Research mode.
Watch on YouTube if video doesn't load ↗
2
Full beginner guide to Claude
Models, sidebar, Projects and memory, Connectors, Co-work intro, mobile app, and free vs Pro vs Max.
Watch on YouTube if video doesn't load ↗
2
Module 2, Claude Co-work deep dive
1 video · 20 Co-work concepts from beginner to advanced
1
20 Claude Co-work concepts
Workspace folder, Claude.md, memory, Projects, Skills, Connectors, scheduled tasks, sub-agents and more: beginner to advanced.
Watch on YouTube if video doesn't load ↗
3
Module 3, Prompting techniques
1 video · Framing, context, and getting great results from Claude
1
Claude in practice
Real examples of Claude being used in professional workflows, not just demos.
Watch on YouTube if video doesn't load ↗
Bonus, Prompting styles cheat sheet
Reference guide · 8 prompting techniques with examples

There's no single "right" way to prompt. Different tasks need different techniques. Bookmark this, it's your go-to reference when Claude isn't giving you what you need.

01
Role prompting
When: you need expert-level depth or a specific perspective
"Act as a senior logistics operations manager with 15 years of last-mile delivery experience. Review this SLA and flag any clauses that are unrealistic for urban routes."
Why it works: assigning a role shifts Claude's vocabulary, assumptions, and depth of analysis immediately.
02
Few-shot (show examples)
When: you need Claude to match a specific format, tone, or style
"Here are two examples of how we write update emails to clients: [Example 1] [Example 2]. Now write one for this week's delay situation: [context]."
Why it works: examples remove ambiguity. Claude reverse-engineers your pattern and replicates it precisely.
03
Chain of thought
When: the task involves logic, decisions, or multi-step analysis
"Think through this step by step before answering: We have 3 delivery routes, each with different cost and time tradeoffs. Which should we prioritize for peak season?"
Why it works: asking Claude to reason before concluding dramatically reduces errors on complex problems.
04
Constraint-based
When: you need tight, usable output, not a wall of text
"Summarize this partner agreement in exactly 5 bullet points. Each bullet must be under 20 words. Focus only on obligations and penalties."
Why it works: constraints force prioritization. Claude can't ramble when you've defined the box it must fit into.
05
Audience targeting
When: the same content needs to land differently for different readers
"Explain our new tracking feature. Version A: for a non-technical operations manager. Version B: for an engineer integrating our API."
Why it works: Claude adjusts vocabulary, assumed knowledge, and framing based on who's reading.
06
Iterative refinement
When: the first draft is close but not quite right
"Good start. Now make it 30% shorter, change the tone from formal to direct, and move the risk section to the top."
Why it works: Claude holds context within a conversation. You don't rewrite, you redirect.
07
Devil's advocate
When: you need to stress-test a plan or decision
"Here's our Q4 expansion plan. Argue against it as strongly as possible. What would a skeptical investor say? What could go wrong?"
Why it works: Claude is excellent at steelmanning opposing views. Use it to find holes before your critics do.
08
Structured output
When: the output needs to slot into a doc, system, or template
"Extract the key information from this email thread and return it as a table with 4 columns: Action item | Owner | Deadline | Priority."
Why it works: defining the exact output structure makes Claude's response immediately usable.
💡 Pro tip, combine techniques
The best prompts stack multiple styles. Role + chain of thought + constraint = a very powerful combination.
🎉 All modules complete
Great work. Next: read dlivrd's Claude usage policy.
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 3 of 13, Video quiz · 80% to continue
QUESTION 1 OF 10
Score: 0/0
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 4 of 13, dlivrd policy

dlivrd Claude Usage Policy

Read the full policy. Scroll to the bottom, open the document, confirm all checkboxes, then pass a 3-question policy check before continuing.

dlivrd Technology Inc.
Artificial Intelligence Usage Policy
Effective: July 2025 · Applies to: All dlivrd employees, contractors, and program participants
1. Why This Policy Exists
dlivrd is adopting AI deliberately and responsibly. Claude gives our teams a powerful tool to work faster, think more clearly, and deliver better results. But that power comes with responsibility. This policy protects our clients, protects dlivrd, and protects you.
2. Scope & Who This Applies To
This policy applies to every person who accesses Claude through dlivrd's AI Access Program, including full-time employees, part-time staff, contractors, vendors, and interns. Access is personal, role-specific, and non-transferable.
3. What You Can Use Claude For
  • Written communications, drafting, editing, and improving emails, Slack messages, client updates, partner communications, and internal memos
  • Document work, summarizing reports, meeting notes, proposals, contracts (non-confidential), and operational documents
  • Operational analysis, analyzing non-confidential route data, SLA performance, delivery metrics, and process inefficiencies
  • Engineering support, writing, reviewing, and explaining code; drafting PR descriptions; generating test cases
  • Project management, turning meeting notes into action items, drafting project briefs, building timelines
  • Research & synthesis, gathering market intelligence, summarizing industry trends, comparing vendor options
  • Content creation, writing internal documentation, training materials, templates, and marketing copy
  • Strategic thinking, brainstorming, stress-testing plans, generating alternatives
4. What You Must Never Do
  • Input confidential client data, no client names, addresses, delivery volumes, pricing agreements, or SLA terms without written approval from your manager and IT Security
  • Input employee or HR data, salaries, performance reviews, disciplinary records, or any PII about dlivrd staff
  • Input system credentials or security data, passwords, API keys, access tokens, database connection strings
  • Submit output without review, never send, publish, or act on Claude's output without reading and verifying it yourself. No exceptions, even under deadline pressure
  • Share your login or access, your Claude seat is assigned to you personally. Zero exceptions
  • Use Claude for personal commercial work, dlivrd's subscription exists for dlivrd business only
  • Attempt to bypass Claude's safety guidelines, no prompt injection, jailbreaking, or role-play exploits
  • Present AI output as original human work, in legal filings, regulatory submissions, investor materials, or certifications, you must disclose AI assistance
5. Data Privacy & Confidentiality
dlivrd accesses Claude through Anthropic's enterprise-tier API. Prompts are not used to train Anthropic's models. However, enterprise protection does not change your obligation to handle data responsibly. Treat every prompt as a professional communication that could be reviewed by your manager or Legal. When in doubt, leave it out, contact sam.hart@dlivrd.io before proceeding.
6. Human Accountability, No Exceptions
Claude is a tool. Every piece of content, every analysis, every communication that flows from your use of Claude is your professional responsibility, not Anthropic's, not dlivrd's AI program's, and not Claude's.
"Claude generated it" is not a defense. If you send a client an incorrect SLA summary that Claude wrote and you didn't verify, that error belongs to you.
7. Understanding Claude's Limitations
  • Hallucination, Claude can generate factually incorrect information with complete confidence and fluency. Never treat its output as ground truth
  • Knowledge cutoff, Claude's training has a cutoff date. It cannot access current events, live delivery data, or current regulations
  • No memory between sessions, Unless you are using a configured Project, Claude starts each conversation fresh
  • No judgment, Claude cannot assess whether an action is right for dlivrd's relationships or strategic context
  • No legal or financial authority, Claude's output on legal, tax, or financial matters is informational only
8. Quality Standards for Claude Output
  • Read the entire output, not just the first paragraph
  • Verify any specific facts, numbers, dates, names, or statistics against a primary source
  • Confirm the tone, framing, and content are appropriate for the audience
  • For client-facing content: have a second team member review before sending
  • For legally sensitive content: route through Legal before use
9. Access Management
  • Steps 1,5, Complete the foundation training: videos, policy, learning module, and foundation quiz
  • Steps 6,9, Register, watch the dlivrd briefing, pass the scenario quiz, and submit a use case
  • Access granted, Upon approval, your Claude seat is activated within 1,2 business days
Access may be suspended or revoked for policy violations, extended inactivity, or a role change. A significant change in responsibilities requires resubmission of your use case.
10. Reporting Violations
Reports go to sam.hart@dlivrd.io. All reports are treated confidentially. If you are unsure whether something is permitted, ask before acting.
dlivrd Technology Inc. · AI Usage Policy · Version 1.0 · July 2025 · Owner: Samantha Hart
Scroll to read
Confirm you have read and understood dlivrd's Claude Usage Policy.
Claude
AI Course · dlivrd × Claude
Step 5 of 14, Policy quiz · 5 questions · 80% to pass
QUESTION 1 OF 3
0 / 0
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 6 of 13, Learning module 0 / 5 complete

Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 7 of 13, Lessons quiz 0 / 0 correct
QUESTION 1 OF 10
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 8 of 13, Prompting cheat sheet

8 techniques for better prompts.

Read all 8 techniques. A 10-question quiz follows before you can continue.

01
Role prompting
When: you need expert-level depth or a specific perspective
"Act as a senior logistics operations manager with 15 years of last-mile delivery experience. Review this SLA and flag any clauses that are unrealistic for urban routes."
Why it works: assigning a role shifts vocabulary, assumptions, and depth of analysis immediately.
02
Few-shot (show examples)
When: you need Claude to match a specific format, tone, or style
"Here are two examples of how we write client update emails: [Example 1] [Example 2]. Now write one for this situation: [context]."
Why it works: examples remove ambiguity. Claude reverse-engineers your pattern and replicates it precisely.
03
Chain of thought
When: the task involves logic, decisions, or multi-step analysis
"Think through this step by step before answering: We have 3 delivery routes with different cost and time tradeoffs. Which should we prioritize for peak season?"
Why it works: asking Claude to reason before concluding dramatically reduces errors on complex problems.
04
Constraint-based
When: you need tight, usable output, not a wall of text
"Summarize this partner agreement in exactly 5 bullet points. Each bullet must be under 20 words. Focus only on obligations and penalties."
Why it works: constraints force prioritization. Claude cannot ramble when you have defined the box it must fit into.
05
Audience targeting
When: the same content needs to land differently for different readers
"Explain our new tracking feature. Version A: for a non-technical operations manager. Version B: for an engineer integrating our API."
Why it works: Claude adjusts vocabulary, assumed knowledge, and framing based on who is reading.
06
Iterative refinement
When: the first draft is close but not quite right
"Good start. Now make it 30% shorter, change the tone from formal to direct, and move the risk section to the top."
Why it works: Claude holds context within a conversation. You redirect, not rewrite.
07
Devil's advocate
When: you need to stress-test a plan or decision
"Here's our Q4 expansion plan. Argue against it as strongly as possible. What would a skeptical investor say? What could go wrong?"
Why it works: Claude is excellent at steelmanning opposing views. Use it to find holes before your critics do.
08
Structured output
When: the output needs to slot into a doc, system, or template
"Extract the key information from this email thread and return it as a table with 4 columns: Action item, Owner, Deadline, Priority."
Why it works: defining the exact output structure makes the response immediately usable, no reformatting needed.
Pro tip: combine techniques
The best prompts stack multiple styles. Role + chain of thought + constraint is a very powerful combination: "Act as [role]. Think step by step. Answer in [format] under [limit]."
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 9 of 13, Cheat sheet quiz · 80% to continue
QUESTION 1 OF 10
Score: 0/0
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Foundation complete

Foundation complete.

You've watched all modules, read the policy, passed the policy check, completed 5 lessons, and passed the foundation quiz. Steps 1,5 are locked in.

YOUR FOUNDATION RECORD
Videos completed4 / 4
Policy read & acknowledged
Policy check passed
Lessons completed5 / 5
Foundation quiz score,

Steps 6,9 are next, register, watch the dlivrd briefing, pass the scenario quiz, and submit your use case to earn your Claude seat.

';">Continue to Step 10, Register →
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 10 of 14, Prompting practice · Write your best prompt
Live AI Exercise

Practice with the dlivrd Operations Coach

You are a dlivrd operations coordinator preparing for a weekly performance review meeting. Using the prompting techniques you just learned: framing, context, criteria, tone: write a prompt that gets Claude to help you with something real from that situation.

Techniques to use
Role prompting Framing Context Constraints Criteria
The dlivrd Operations Coach is ready. Write your prompt below and submit it to see how Claude responds and get feedback on your technique.
0 / 50 minimum characters
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 11 of 14, Register for access

Register your application.

Enter your details below. Only approved roles can proceed to Steps 7,9.

10
Register
Your name, email, and role, only approved roles can proceed
11
dlivrd briefing
Timed slides on how we specifically use Claude, must read each one
12
Scenario quiz
10 scenario questions, 90% to pass, randomized every attempt
13
Use case
Describe a real task in your role, vague answers are rejected

Claude isn't available for your role yet.

Wave 1 is open to PMs, Engineers, EAs, and Marketing. Here are free resources to get you started with Google Gemini in the meantime.

Gemini for Beginners, 25 min
Kevin Stratvert · Free · Gmail, Drive, Docs productivity
Free Gemini Course with Certificate
Great Learning · Free · No coding required
Notify me when Wave 2 opens

Questions? sam.hart@dlivrd.io

Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 11, dlivrd briefing
8
This isn't a tool rollout. It's a shift in how dlivrd works.

Claude is being introduced to help our best people work at a higher level, faster drafts, better analysis, clearer communication. This briefing covers exactly how dlivrd uses Claude, what we expect from you, and what access means in practice.

dlivrd use cases by role
8
Here's what approved dlivrd teams actually do with Claude.
What access looks like
8
Your Claude seat gives you a personal workspace. Here's how it works at dlivrd.
Your own Claude account
Access via claude.ai using your dlivrd email. Never share your login, each seat is assigned to one person.
Use Projects for recurring tasks
Claude Projects let you give Claude persistent context, your role, tone, and preferences, so you don't have to re-explain every time.
Weekly team sessions
dlivrd holds weekly Claude sessions where teams share what's working. Bring your best prompts and learn from colleagues.
Usage is monitored
dlivrd tracks Claude usage at an account level. Unusual activity or policy violations will be flagged and reviewed.
Your accountability
8
Access at dlivrd comes with non-negotiable rules.

Violations may result in immediate access revocation. Questions go to sam.hart@dlivrd.io.

dlivrd data boundaries
8
These data types never go into Claude. No exceptions, no workarounds.
Client data
Names, addresses, delivery volumes, contracts, SLA terms, pricing, or anything received under NDA
Employee data
Salaries, performance reviews, disciplinary records, personal contact information, or immigration status
System credentials
Passwords, API keys, tokens, database strings, or internal IP addresses
Expedite driver data
Driver personal information, earnings, performance data, or operational assignments from the dlivrd platform
What good looks like
8
The dlivrd standard for using Claude well.
Draft with Claude, verify before sending
Use Claude to create the first version. Then read it yourself, check facts, and edit before it leaves your hands.
Be specific in your prompts
Role + task + format + constraints = great output. Vague prompts produce vague results. Put in context, get back usable work.
Share what works
Weekly sessions are where dlivrd builds institutional knowledge. Your best prompt saves everyone time. Bring it.
Flag anything unusual
If Claude produces something unexpected, harmful, or wrong in a way that matters, tell your manager and Sam Hart.
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 13 of 14, Scenario quiz · 90% to pass
QUESTION 1 OF 10
Score: 0/0
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program
Step 14 of 14, Use case submission

Prove your intent.

Describe a specific, real task in your current role where Claude would save meaningful time or improve quality. Sam Hart reviews every submission personally.

WHAT GETS REJECTED
Rejected: too vague
"I could use Claude to help with my work and save time on various tasks."
Rejected: no specifics
"Claude would help me write emails and summarize things faster."
WHAT GETS APPROVED
Specific, real, and role-grounded
"Every Monday I spend 2 hours compiling our weekly ops report from 6 Slack threads and 3 spreadsheets. Claude could help me structure and draft the narrative in 20 minutes from my bullet notes. I'd then verify it against raw data before sending to leadership."
YOUR SUBMISSION MUST INCLUDE:
1. What is the specific task you will use Claude for at dlivrd?
2. How will you verify Claude's output before using it?
3. What is the business impact if this works well?
0 / 50 words minimum
Claude
AI Course · dlivrd × Claude
AI Access Qualification Program

Score
Role
Status

Questions? sam.hart@dlivrd.io

Claude
AI Course · dlivrd × Claude