Prompt Engineering Best Practices

Best practices on crafting your questions to AlphaSense Generative Search

This article outlines tips and tricks around prompt engineering in AlphaSense's natural language interface, Generative Search.

• What is Prompt Engineering?
• Optimizing Your Generative Search Prompts
• Example Prompts for Generative Search
• How to Search for Specific Content
• How to Access Generative Search
• Searching Internal Content
• Advanced Prompt Engineering Tactics
• Current Unsupported Prompts within Generative Search

What is Prompt Engineering?

Prompt engineering is the process of designing and refining instructions (prompts) for generative AI to produce accurate and useful results.

In the context of AlphaSense, it means carefully crafting the questions you ask within our Generative Search tool so the model can surface the most relevant insights and information you’re looking for..

Optimizing Your Generative Search Prompts

Generative Search is a powerful tool for finding and synthesizing information, but the quality of its output depends on the clarity of your input. By applying some basic prompt engineering tactics, you can structure your queries to get more precise and relevant results.

Question Structure:

• It's best to ask a single question at a time, rather than asking Gen Search multiple questions in a single prompt
  • "What is the forecasted impact of the Trump presidency on the cryptocurrency market?
  • "Summarize the highlights from Nvidia's latest earnings call."
• Rather than asking Gen Search questions with a single keyword with no clear intent, ask complete questions
  • "What is the market investment in BNPL technologies?"
• Provide formatting instructions to your Gen Search query
  • "Summarize in five bullets..."
  • "In less than 500 words, explain..."
  • "Provide the response in a table format."
  • "Bold mentions of CAGR..."

Timeframe:

• By default, Generative Search indexes the last 12 months. To adjust the timeframe, simply use natural language in your query. For example:
  • "...in the last 3 years"
  • "In Q2 of this year...",
  • "...last month..."

Companies & Industries:

• Use the Company & Industries filter to select the companies and industries you're wanting to search for - this is a great avenue if you're unsure how to structure your query to isolate a specific entity/industry.
• You can also search for companies by using the company name or ticker in the prompt.
  • "How did Nvidia perform..."
  • "...guidance from WFC?"
  • "What factors are affecting Stripe, Inc in...."
• If searching for small private companies that have names shared with other brands (i.e. "The Standard" is the marketing name for Standard Insurance Company, but also the name of popular hotel chain, etc), we encourage you to add context or use the official company name to help out Generative Search in interpreting the question.
  • "What did Standard Insurance Company say..."
  • "...affect The Standard hotel chain?"
• For Industries, we recommend using clear and specific terms when searching for industries.
  • Searching "electric vehicle industry" is more optimal compared to "electric vehicle space"
  • This removes uncertainty from the Generative Search algorithm and provides a more targeted answer

Keywords/Themes:

• When possible, it's best to use keywords that will activate smart synonyms
  • "What R&D updates in the GenAI industry..."
  • "...the TAM of semiconductors?"

Watchlists:

• Filter your Gen Search question to a specific watchlist you've created in AlphaSense. This helps narrow the focus to select companies you regularly search against.
  • "What is the revenue of companies in my [watchlist name] watchlist ?"

Example Prompts for Generative Search

Company Research

• "What strategic initiatives is [COMPANY] implementing to address the profitability and growth issues it has experienced?"
• "How are changes in regulatory environments and trade policies affecting [COMPANY]’s global operations and market strategies?"
• "Give me a brief overview of [COMPANY]."

Industry Research

• "What is the TAM for [INDUSTRY] in North America?"
• "What are the key factors driving capital investment in [INDUSTRY] over the next 5 to 10 years?"
• "What do industry experts say about major factors affecting the [INDUSTRY] industry?"

Comparison

• "Compare the broker view of [COMPANY]'s competitive positioning with expert views."
• "Compare and contrast bull and bear views on [COMPANY/TOPIC]."
• "Compare R&D pipelines of [COMPANY 1] vs. [COMPANY 2]"

Event Summarization

• "Summarize the expert view on [COMPANY]'s growth potential over the next 5 years."
• "Summarize the broker view of [COMPANY]."
• "Summarize [COMPANY]'s latest investor presentation."

Change Over Time

• "How have broker forecasts for [COMPANY] earnings changed?"
• "How have expert opinions on opportunities and challenges for the [INDUSTRY] sector evolved?

Please note that prompts are limited to a maximum of 16,000 characters.

How to Search for Specific Content

When beginning a prompt with Generative Search, you can select the source category directly from the search bar before initiating a query - this is great if you're unsure how to properly isolate a specific content set within the context of your question.

NOTE: Source filters applied at this level will override your default content sets, even if the source you're selecting from below is turned off by default when running a Document Search.

Content Types and Example Prompt Language

The following dictionary provides examples of how to start your prompts for each content type.

How to Access Generative Search

There are 2 different avenues available for you to access and launch Generative Search:

1. Directly launch Gen Search from the left hand navigation panel
2. Dive into Gen Search after you've run a traditional Document search

When you begin your search with Generative Search [Option 1], it accesses your default sources with no content filters applied. This allows you to search wide and use natural language to filter for various sources and content.

If you launched Generative Search after running a Document search [Option 2], Gen Search will carry over any content filters applied to those searches into your chat. If you need to clear any filters, either, select "Clear Chat" or start a new session with Gen Search.

Example:

A search is run for "R&D strategy" and "PFE", as well as a content filter for Expert Insights is applied. If you open Gen Search from this query, the summaries will only be generated from Expert Insights content.

Searching Internal Content

If you're an Enterprise Intelligence customer, AlphaSense Generative Search is extended to your internal content within AlphaSense.

Using Pronouns

Use pronouns instead of your company name to ask questions specific to your internal content:

• "What are the semiconductor investment targets that we identified?"
• "Synthesize our internal research on edge computing trends."

Searching Colleagues

You can prompt what specific authors have said about a particular topic to isolate that particular voice. Make sure to use both First and Last Name.:

• "What has [COLLEAGUE'S NAME] said about EV growth levers in our internal content?"

Uploading Documents to Generative Search

If there's a particular document/set of documents you'd like to focus your Gen Search query against, you can upload them into AlphaSense using Generative Search. Currently, you can upload up to 100 documents, with each document a max of 100MB

Internal Content Filters

Using terms like "our", "my", and "we" will direct generative search to filter content specifically to any internal content you've added to AlphaSense. Using the specific source in your prompt will filter for that particular content set.

• Example: "In our Uploads...", "In FileSync...", "Our content in Box..."

Example Prompts for Internal Content

Company Research

• "According to our research, what are [COMPANY]'s key growth drivers?"
• "Summarize our investment thesis for [COMPANY]."
• "Summarize the motivations behind [COMPANY]'s acquisition of [COMPANY] according to our research."

Industry Research

• "Create a market landscape of the [INDUSTRY] based on our internal content."
• "Synthesize our internal research on [INDUSTRY]."
• "What has the historical growth trajectory of [INDUSTRY] looked like per our internal documents?"

Comparisons

• "Compare our view of [COMPANY]'s competitive positioning with external views."
• "Evaluate our outlook on [COMPANY] against broker consensus."
• "Compare our view on [INDUSTRY] growth drivers against the broker view."

Event Summarization

• "Summarize key points from our management meeting with [COMPANY]."
• "What were the key points discussed at [COMPANY]'s latest investor presentation according to our internal research?

Change Over Time

• "How has our team's perspective on [COMPANY] changed overtime?"
• "What has [COMPANY]'s revenue growth looked like over the past 5 years according to our data?"

Advanced Prompt Engineering Techniques

Conversational Memory

• Interactions with our generative search are conversational, meaning that it will "remember" previous queries from that session and, by default, assume that your question is related to previous queries.
• You can start a new "conversation" by clicking the "Clear Chat" button in the upper right hand corner of the screen.

Requesting Quantitative Information

• Adding "use numbers" or “data” leads to a more quantitative answer from Gen Search.
  • "What is predicted AI investment in the industrial sector? Include numbers."
  • "What are some important growth drivers for semiconductors? Use data"

Driving More Direct Responses

• We recommend prefacing a prompt with “explain” yields a more direct response than more ambiguous prompts.
  • "What is predicted AI investment in the industrial sector? Explain why."
  • "Explain how Netflix guidance..."

Optimizing Comparison Questions

• To get the best answers from comparison questions, we recommend specifying a perspective/document type in your prompt
  • "How are analysts talking about Netflix's growth potential vs. Hulu"
  • "Compare broker's competitive positioning of PFE against former employees."

Explore Suggested Questions Following a Response

• Oftentimes, exploring the suggested follow up questions in Gen Search can help reframe the question to be more specific or direct in a way that is going to warrant a better response from the model.
• These recommendations are really great for idea generation as well

Review the Summary/Plan

• Reviewing the Summary provides insight insight into your prompt and if there are any immediate adjustments needed. Checking if the summary is showing the correct timeframe, content, keywords, etc can verify the prompt functioned as you intended it to.

Current Unsupported Prompts with Generative Search

Librarian questions:

You might want to ask Gen Search to bring relevant documents rather than respond to a question (i.e. "Bring me the last 3 earnings transcripts for GM"). Rather than using Gen Search, you should perform a traditional Document Search (i.e. company = GM, filter for earnings transcripts).

Screener questions (aka producing lists):

Generative Search will likely give a decent overview to a request like "Who are the top 5 players in biologics by market cap?", but a more exhaustive, data-driven list can be found with Companies in Search Results after completing a traditional document search.

Surfacing tables/charts:

For the time being, Image Search (after running a traditional document search) should be the way you surface tables and charts about a topic/area of interest.