My Daily AI Playbook: Use Cases, Tools and Prompts

A rundown of my daily AI use cases to lead teams, create, and strategise, including tools and prompts.

A recent MIT report spooked investors because it said 95% of all AI pilots are failing.

Now, I'm going to do a separate post on how to make your AI pilots successful.

But, for this post, I wanted to do a day in the life of a busy exec (me) and how they use AI to get s**t done to show regardless of what that report says, AI is a huge driver of increased productivity.

No hype, actual use cases.

Here's a quick snapshot of the AI use cases we'll cover.

Let's dive in.

Morning - Start with Clarity and Focus

1. AI Chief of Staff (ChatGPT)

→ Start the day by getting focused and driving clarity across priorities

Outcome: Prioritise the most important work e.g. blockers, KPI gaps, initiatives tracking behind schedule.

How: Here's the setup

a. Create a ChatGPT Project for each critical initiative.

b. Add docs, updates, and meeting notes.

# Key docs are those tracking KPIs, blockers and deliverables

c. Add these instructions to the project (these are mine, you can adapt for your likes)

You are my AI Chief of Staff.

• Be clear, concise, and insightful: Keep responses to the point, but ensure you provide enough context to support your conclusions. Prioritize clarity, but don't sacrifice depth where nuance matters.

• Ground recommendations in evidence: When referencing internal documentation, cite the exact document name or source clearly (e.g., "2024 Q3 GTM Strategy Doc"). If relevant, include specific excerpts or page numbers.

• Actively surface blind spots: Don't just respond to the prompt — proactively identify risks, missed opportunities, or potential second-order effects I may not be considering.

• Challenge my thinking respectfully.: If my assumptions or logic appear flawed, offer a better alternative. Explain why your reasoning diverges, with a constructive tone and supporting evidence.

• Bring in external perspective where valuable: Use real-world case studies, industry benchmarks, or competitive insights to strengthen recommendations or broaden strategic thinking.

• Think long-term and systemically: When possible, connect individual tasks or problems to larger strategic goals, org-wide implications, or patterns across projects.

• Prioritize actionability.: End with clear next steps, questions to consider, or options to move forward — especially when the path isn't obvious.

d. Now you can run prompts like the below to prioritise your work

Summarize all key blockers from {add month}, tell me if a migation plan was cited, if not, suggest one based on the context you have about the workstream where the blocker has occured.

Summarize all key metrics that were missed in {add month}. Give me the reasons given for the miss and tell me if this is a consistent pattern for this workstream.

Highlight any mentions of critical or urgent risks from the past week of meeting notes.

Here’s some example outputs with fake data:

• This shows blockers across a strategic project I should focus on:

• This shows workstreams that are missing KPIs along with the trend for each KPI

Note: I did an entire breakdown of my AI-powered growth OS for paid users here, it goes through the above and WAY more on how I use AI to manage large teams in a growth orientated way.

2. Executive / Board Update (ChatGPT)

→ Prepare all exec comms that need to be sent out

Outcome: Get any exec-level updates out in the morning when I'm going through status of projects with chief of staff.

How: Create a custom-GPT that is trained on the formats required for your different updates.

a. Create a Custom-GTP and give it instructions (example below, you'd replace with your own formats)

Instructions:

You are my Executive Update Assistant.

- Turn raw notes and metrics into concise, executive-level updates.

- Always prioritize clarity, brevity, and impact.

- The user will specify the format:

(1) 2-Page Exec Briefing (bullets + metrics)

(2) Exec Slide Outline (deck-ready).

- Highlight risks, blockers, and key decisions required.

- Use plain language — no jargon.

Here is the example outputs to follow:

1. 2-Page Briefing

Page 1: Metrics & Progress

- Revenue: +12% QoQ

- Pipeline Coverage: 3.2x target

- Customer NPS: 47 (up from 42)

Page 2: Blockers & Decisions

- Blocker: Integration delays with Partner X (ETA: 3 weeks)

- Decision: Need board alignment on Q3 hiring freeze

- Next Steps: Expand beta rollout, finalize pricing model

2. Slide Outline (deck-ready).

You are my Executive Update Assistant.

- Turn raw notes and metrics into concise, executive-level updates.

- Always prioritize clarity, brevity, and impact.

- The user will specify the format:

(1) 2-Page Briefing (bullets + metrics)

(2) Slide Outline (deck-ready).

- Highlight risks, blockers, and key decisions required.

- Use plain language — no jargon.

b. You can now add docs, metrics you'd like to craft into the exec level -update. Let's go with a deck because Execs love decks. We'll bring this to life with GenSpark after all the morning work with ChatGPT is complete, so you'll see the actual deck below.

Late Morning - Thinking Big

You’ve gotten focus and clarity, let’s move onto finishing critical comms and starting to strategise on the blockers and KPI gaps you uncovered.

4. Deck Designer (GenSpark)

→ Turn above comms into professional looking decks for execs

Outcome: Professional looking decks for internal comms

How: Remember your exec comms assistant above, we've created the following slide outline from that custom GTM (this is a very basic example of what an update would look like) - we can now take that and ask GenSpark to create a deck.

"Slide 1 — Q2 Metrics Snapshot

• Revenue: $18.6M (↑ vs. $17M target)

• New ARR: $4.2M (↓ from $5.1M in Q1)

• Pipeline Coverage: 2.7x (vs. 3x target)

• Churn: 7% (↑ from 5% last quarter)

• NPS: 46 (vs. 44 last quarter)

• Gross Margin: 74% (target: 75%)

Slide 2 — Key Wins

• Closed Acme Corp. ($1.2M ARR) → biggest logo of quarter

• Launched AI workflow tool beta (200 customers onboarded)

• Added 3 senior AEs in EMEA → pipeline building quickly

• Strong visibility: TechCrunch coverage + Forrester "leader to watch"

Slide 3 — Risks & Blockers

• Partner X integration delay → pushed from Q2 to Q3

• Customer support backlog → avg. response time slipped 4h → 9h

• Finance pushing Q3 hiring freeze (impact on growth if implemented)

Slide 4 — Decisions Needed

• Hiring freeze: Board alignment for Q3

• Beta expansion: Approval to scale from 200 → 500 customers

• Partner Y: Green light to accelerate partnership"

The above is a straightforward format for illustration purposes only. GenSpark can do great internal decks perfectly mapped to your formats. Here’s what it produced.

4. Strategy Sparring (Your ChatGPT Red-team)

→ Start working through the most critical blockers, problems and opportunities to solve

Outcome: Surface blind spots and stress test ideas

How: Run the following prompt (preferably with GPT-5 thinking)

Red-team this idea: [brief].

Return:

1. Top 5 counter-arguments (with likely evidence).

2. Hidden assumptions + how to test them.

3. A pre-mortem: what could go wrong + early warning signals.

It gives you some incredible results to help you think critically about the blockers, problems, opportunities you’re focused on.

Afternoon: Creativity, Experiments & ideas

Time to move on to practising the craft. How you practise the craft can be different from day to day, but here are a couple of use cases that can be re-used in many ways.

5. Claude (Creative Writing Assistant)

→ Move onto creative tasks, start generating influence across your audience

Outcome: In todays marketing world, it's critical to build influence, you can use Claude to avoid the dreaded blank page problem.

How: You can run the following prompt. You should have an audience profile. I've showed how to build this in previous posts if you don't - see the Grok use case below.

Here's my audience profile: [paste].

Topic: [topic].

For this Topic to be interesting to my audience generate:

- 7 unique takes (ranked)

- 5 counterpoints (with rebuttals)

- 3 punchy debate framings.

6. Lovable / Replit (Demo > Memo)

→ Start bringing ideas to life through MVPs and pilots

Outcome: Working prototype > theory

How: I can't give you a prompt here, as you could be prototyping anything. Quick plug, I talked to Anton, founder of Lovable, on Marketing Against the Grain. I showed him a lead magnet I built with Lovable. Tune in to get that episode next week to an example of me using it.

Side note: I have an app being launched soon that was coded in Lovable, Claude Code and Replit. I’ll be doing a deep dive here so you’ll see the kind of apps I’m working on.

7. NotebookLM (Memo → Podcast)

Time to catch up on some all my project updates

Outcome: Podcast-style overview you can listen to

How: Do the following in NotebookLM

a. Create a Notebook in NotebookLM.

b. Add all updates (docs, meetings etc)

c. Generate an audio overview → you can ask the audience overview questions e.g. like a dial-in show where you’re the only caller

#NotebookLM now allows you to do video updates, diving into some of the new features soon, and will do a whole post on NotebookLM. It's a great tool.

Evening: Wrap & Fun

8. xAI / Grok (ICP Content Research)

→ Grok is a great tool for researching your ICP, in particular for refining your ICP’s content consumption traits.

Outcome: Clear picture of what your ICP is actually engaging with

How: Run the following prompt

Analyze these ~20 ICP handles [paste]. 

Look at last 90 days. 

Return: top topics, formats (thread/video/link), linked domains, engagement patterns, posting cadence. 

Output 5 "make-this-next" briefs.

9. Veo3 (Bring Ideas to Life)

→ This is just for fun now, working on a couple of fun videos

Outcome: Fun video creation

How:

• Use ChatGPT to riff on a script.

• Feed it into Veo3.

• Use Flow to stitch multiple Veo3 videos together, because a single video can only be 8 seconds.

Here’s an intro to a short 5-min video I’m working on called “Marketing Through Time”. It’s INCREDIBLY rough right now and I was mostly testing how to get character consistency across scenes, but you can see how good it is.

---

Ok, the above hopefully gives you an insight into some of my use cases. Obviously the reality of my work is everyday is different. It’s not structured into such neat daily use cases. But, I do think the morning routine is a great way to get clarity and focus on the most important priorities.

Until Next Time,

Happy AI’fying,

Kieran