BuccoCapital Bloke Profile picture
Feb 15 6 tweets 8 min read Read on X
People were curious, so here's how I'm using Deep Research. I'll walk through the prompting and then an example:

1. First, I used O1 Pro to build me a prompt for Deep Research to do Deep Research on Deep Research prompting. It read all the blogs and literature on best practices and gave me a thorough report.

2. Then I asked for this to be turned into a prompt template for Deep Research. I've added it below. This routinely creates 3-5 page prompts that are generating 60-100 page, very thorough reports

3. Now when I use O1 Pro to write prompts, I'll write all my thoughts out and ask it to turn it into a prompt using the best practices below:
______
Please build a prompt using the following guidelines:

Define the Objective:
- Clearly state the main research question or task.
- Specify the desired outcome (e.g., detailed analysis, comparison, recommendations).

Gather Context and Background:
- Include all relevant background information, definitions, and data.
- Specify any boundaries (e.g., scope, timeframes, geographic limits).

Use Specific and Clear Language:
- Provide precise wording and define key terms.
- Avoid vague or ambiguous language.

Provide Step-by-Step Guidance:
- Break the task into sequential steps or sub-tasks.
- Organize instructions using bullet points or numbered lists.

Specify the Desired Output Format:
- Describe how the final answer should be organized (e.g., report format, headings, bullet points, citations).
Include any specific formatting requirements.

Balance Detail with Flexibility:
- Offer sufficient detail to guide the response while allowing room for creative elaboration.
- Avoid over-constraining the prompt to enable exploration of relevant nuances.

Incorporate Iterative Refinement:
- Build in a process to test the prompt and refine it based on initial outputs.
- Allow for follow-up instructions to adjust or expand the response as needed.

Apply Proven Techniques:
- Use methods such as chain-of-thought prompting (e.g., “think step by step”) for complex tasks.
- Encourage the AI to break down problems into intermediate reasoning steps.

Set a Role or Perspective:
- Assign a specific role (e.g., “act as a market analyst” or “assume the perspective of a historian”) to tailor the tone and depth of the analysis.

Avoid Overloading the Prompt:
- Focus on one primary objective or break multiple questions into separate parts.
- Prevent overwhelming the prompt with too many distinct questions.

Request Justification and References:
- Instruct the AI to support its claims with evidence or to reference sources where possible.
- Enhance the credibility and verifiability of the response.

Review and Edit Thoroughly:
- Ensure the final prompt is clear, logically organized, and complete.
- Remove any ambiguous or redundant instructions.
So here's how it works with an example. I did this in 5 minutes. I'd always be way more structured in my context, inputting more about my hypothesis, more context etc. I just did this for fun for you all

Prompt:

Use the best practices provided below and the intial context I shared to create a deep research prompt on the following topic:

Context:
I am an investor who wants to better understand how durable DoorDash’s business is. My hypothesis is that they have a three sided network between drivers and riders and restaurants that would be incredibly hard to replicate. Additionally, they built it when interest rates were low so it would be hard to create a competitor today. I need you to make sure you deeply research a few things, at least, though you will find more things that are important -
- doordash’s business model
- how takeout is a part of the restaurant business model, and the relationship restaurants have with delivery networks. Advantages, risks, etc
- the trend of food away from home consumption in America, how it has changed in the last decade and where it might go
- Doordash’s competitors and the history of their competitive space

I need the final report to be as comprehensive and thorough as possible. It should be soundly rooted in business strategy, academic research, and data-driven. But it also needs to use industry blogs and other sources, too. Even reviews are ok.
Here's the prompt it gave me. I added a few other things and inputted it into Deep Research. I'll share the raw output though so people can see it:

Deep Research Prompt on DoorDash’s Business Durability
1. Objective:
Provide a comprehensive, data-driven report evaluating the long-term durability of DoorDash’s business model. The central hypothesis is that DoorDash’s three-sided network—connecting drivers, diners, and restaurants—creates a competitive advantage that is difficult to replicate, especially given it was built during a low-interest-rate period. This report should leverage both quantitative and qualitative sources to determine the resilience and growth potential of DoorDash’s model in the face of changing economic and market conditions.
2. Provide Adequate Context and Background

Context:
DoorDash is a leader in on-demand food delivery, connecting consumers with restaurants and drivers via a digital platform.
The business thrives on network effects: the more restaurants and drivers it has, the more appealing it becomes to consumers, and vice versa.
The company scaled aggressively during a period of low interest rates, raising capital more cheaply than might be possible today.

Background:
Takeout and delivery are increasingly integral to restaurant operations; however, high commission fees and reliance on third-party platforms bring potential risks and benefits to restaurants.
U.S. consumers have steadily increased food-away-from-home spending, but emerging trends—like “ghost kitchens” and shifting consumer preferences—could reshape the landscape.
DoorDash faces competition from companies like Uber Eats, Grubhub, and emerging players, each with varying strategies and market shares.

3. Use Specific and Unambiguous Language
Key Terms & Clarifications
- Three-Sided Network: A platform connecting three distinct user groups—drivers, diners, and restaurants.
- Network Effects: The increased value of a service as more people use it.
- Durability: The ability of DoorDash’s business model to maintain market leadership and profitability over the long term.

4. Detail Step-by-Step Instructions
Business Model Analysis
- Describe DoorDash’s revenue streams, unit economics, and how its three-sided platform operates.
- Discuss how the low-interest-rate environment influenced its growth, fundraising, and capital expenditures.

Restaurant Takeout Dynamics
- Investigate the role of takeout in a restaurant’s overall business model.
- Analyze advantages (e.g., expanded customer reach, off-premise revenue) and risks (e.g., high commission fees, reliance on third-party platforms) for restaurant partners.

Market Trends:
- Food Away From Home: Present historical data (covering at least the last decade) on how Americans are shifting spending patterns from in-home cooking to food-away-from-home options.
- Forecast potential changes in consumer behavior (e.g., after COVID-19, economic downturns, or technological shifts).

Competitive Landscape
- Examine DoorDash’s major competitors, their historical evolution, and strategic pivots (e.g., Uber Eats’ global reach, Grubhub’s early market presence).
- Evaluate each competitor’s strengths and weaknesses relative to DoorDash.

Additional Factors
- Identify any other relevant influences, such as new legal regulations (e.g., caps on delivery commissions), consumer sentiment about gig work, or macroeconomic shifts.

Critical Analysis & Recommendations
- Apply at least three established business strategy framework (e.g., Porter’s Five Forces, SWOT) to synthesize findings.
- Propose an overall evaluation of DoorDash’s market durability and key strategic recommendations (e.g., product diversification, partnerships, or geographic expansion).

5. Guide the Desired Output Format
Structure Your Report With Clear Headings:
Introduction & Executive Summary
DoorDash Business Model Analysis
Restaurant Takeout & Delivery Network Dynamics
Food-Away-From-Home Trends
Competitive Landscape
Synthesis: Strategic Framework Application
Conclusion & Recommendations
References & Sources

Include Data Visualizations:
Where possible, embed charts or tables to illustrate market share, historical growth, or consumer behavior changes.

6. Balance Detail with Flexibility
While this outline provides clear research directions, remain open to exploring additional subtopics or emerging angles that become apparent during your investigation. For instance, you might delve deeper into specific technological innovations (e.g., AI-driven route optimization) if they significantly impact DoorDash’s durability.

7. Incorporate Iterative Refinement
Draft, Review, Refine:
- Draft the report based on the step-by-step instructions.
- Review for any gaps or ambiguities.
- Refine by adding any missing context, improving clarity, and ensuring logical flow.

8. Use Proven Techniques (Chain-of-Thought Prompting)

Reasoning Approach:
- Clearly show intermediate reasoning steps in each section. For example, when discussing competition, explain the logical process used to rank or evaluate different companies.

9. Employ Role Prompting
Role: Act as a seasoned financial and business strategy analyst. Provide authoritative, well-reasoned insights aimed at informing an investor’s perspective on DoorDash’s long-term prospects.

10. Demand Justification and Source References

Evidence & Citations:
Support every major claim or data point with references (e.g., “according to [industry report]” or “as found in [peer-reviewed study]”).
Incorporate insights from academic journals, business strategy publications, industry blogs, and even user reviews where relevant.

11. Review and Edit Thoroughly
Final Quality Check:
Before submitting the final report, proofread for logical flow, completeness, and correctness of data citations.
Ensure your conclusions and recommendations directly tie back to your hypothesis regarding DoorDash’s durable competitive advantage.
I made sure to prompt Deep Research to ask me additional questions before it went on it's way. Here's what it asked me:

Before starting the deep research on DoorDash’s business durability, I’d like to clarify a few key points to ensure the report aligns perfectly with your needs:

1. Scope of Financial Data: Do you want a deep dive into DoorDash’s financial statements (e.g., revenue growth, profitability, cash flow trends, and debt levels), or should the focus be more on strategic positioning and market dynamics?
2. Geographical Scope: Should the research focus solely on DoorDash’s U.S. market, or should it also include international expansion efforts and potential global competition?
3. Competitor Benchmarking: Are there any specific competitors or alternative food delivery models you’d like a deeper comparison on (e.g., Just Eat Takeaway, Deliveroo, regional players)?
4. Macroeconomic Considerations: How much emphasis should be placed on broader economic factors like inflation, interest rates, or shifts in consumer discretionary spending?
5. Primary vs. Secondary Research: Should this report rely entirely on publicly available data, or would you like insights from surveys, interviews, or expert opinions?
6. Time Horizon: Should the durability analysis focus on the next 3-5 years, or would you like a longer-term perspective (e.g., 10+ years)?
7. Regulatory Environment: Would you like an in-depth analysis of labor laws, gig economy regulations, and government policies impacting delivery platforms?
8. Technological Innovations: Should the research explore potential technological disruptors (e.g., autonomous delivery, AI-driven logistics) that could impact DoorDash’s long-term competitiveness?
Let me know your preferences on these aspects, and I will tailor the research accordingly.
It generated a 65 page report.

It was...pretty excellent as a survey of everything you'd want to consider if you were evaluating DoorDash's competitive position and durability of their moat

Some excerpts on macro risk, impact of emerging technology, and regulatory outlook (each of these sections was 10 pages itself, so way more in depth)Image
Image
Image
The crazy part is you can then run all the subsequent deep research reports you want:

- regulatory risks for gig economy companies
- how discretionary spending has been impacted by recessions
- Restaurant unit economics with a focus on delivery
- scaling multi-sided networks
- interest rate impact on competitive intensity

Etc. could even export, throw them in a folder and query the outcomes. In like 30 minutes

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with BuccoCapital Bloke

BuccoCapital Bloke Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @buccocapital

Jun 5, 2024
It's unfair to say Zoom fumbled the bag

Simply put: COVID pulled forward their future, eating their runway. It alerted competition to the opportunity. Now Zoom is fighting for their life

A bit more about why this has been so tough for the companies who should have won:
In normal times, growth businesses are deliberate about expansion. They spend up to a decade building a strong core product w/ sticky user base and go-to-market muscles like sales and customer success

They use their strong core to fund their next oppty

COVID fucked that all up
COVID fucked up things for tech companies in two ways:

1) It created massive demand, alerting competitors to a market opportunity
2) It pulled forward their future. They started eating through their end market. Investors wanted to know - What's next? Tell us. NOW
Read 6 tweets
May 3, 2024
1. I’ve been lucky to work with some incredible people throughout my career

I’ve randomly posted the great advice they’ve shared, but thought it was worth consolidating them all

Maybe some folks will find these helpful. I certainly have…
2. On Success

“Beyond a certain point, a “successful” career is a selfish pursuit. The sooner you embrace this, the better your relationships will be

It’s ok for your career to be about making you happy. Pretending it’s for other people is the dangerous game”
3. On Building Relationships

Need to build a working relationship with someone new, quickly? Ask for their advice/feedback on something you’re working on

It’s an immediate sign that you respect and trust them. They’ll match that
Read 14 tweets
Apr 20, 2024
Some random observations from our implementation of generative AI for scaled customer support

Who knows, maybe people will find it interesting:
1. Ticket deflection opportunity is real:

Pretty immediately AI is able deflect 20% of support queries. It’s pretty shocking when you dig in on a case-by-case basis how many questions are “known” vs “unknown” + bugs

40% deflection seems reasonably attainable
2. Gen AI is automating product development

Every undeflected query is a “gold nugget”. For prod team there are 3 types of nuggets:
1) Feature request
2) Self-service opportunities (requires human assistance today but shouldn’t)
3) Agent actions (do something for me)
Read 8 tweets
Dec 30, 2023
Appreciate everyone sharing their favorite reads from 2023

Paying it forward, here are 10 books I really enjoyed reading this year. A mix of books I read for the first time and some re-reads, too.

Hope everyone finds something they might like, and here’s to 2024…
1. I re-read Christensen’s Innovators Solution. The predecessor gets all the hype, but IMHO this one is better

The stuff in here about integration vs modularity should be required reading for every operator and investor Image
2. McPhee is the OG of long-form non-fiction journalism. He has been a staff writer for the New Yorker since 1965 and is also a Professor of Journalism at Princeton.

The first story here, Atchafalaya, is one of the finest essays I have ever read Image
Read 11 tweets
Dec 27, 2023
(1/8) Yesterday I said it was wild how many talented people struggle to sell themselves during interviews

Lots of people asked how to do it

I've interviewed 100's (if not 1,000's) of ppl, and done a bunch interviewing myself, so here are 5 simple elements of selling yourself
(2/8) Some notes before we begin:

This won't cover basic advice like Be Confident or Look Your Interviewer in the Eye

It also won't cover the skills to do the job in question

While some will say the suggestions below are obvious, doing them puts you ahead of 90% of candidates
(3/8) Craft a Career Narrative:

What drives you? Passion? Values? Skills? If it doesn't exist, make it up. Make it compelling

What’s the 1-liner for each new role? Think “moving toward” vs “away from”

1-2 min pitch. Practice, pref w/ someone. Record it. Create bullets
Read 9 tweets
Sep 8, 2023
Random shit I’m hearing/seeing from tech talent market

- Companies turning up heat via reviews/higher standards. Rise to occasion or leave
- Attrition is down. Managers must fire low performers, replace in open mkt
- Hard to get hired. Thousands of apps per role
- Growth, Eng roles opening up. Ruthless prioritization in Customer Success, Marketing, IT outsource/contract where possible
- Backfills not on autopilot. Must re-justify role
- De-layer your org. Minimize middle management, increase span of control
It’s funny talking to all sides of the job market. Hiring managers, finance, employees, job seekers

Across the board, finally feels like recognition the ZIRP era is over.

RIP Good Times. Businesses gotta make money now. Employees have to drive *quantifiable* impact
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(