Gradient Works Docs
ProductDynamic BooksPricingRequest Demo
  • Welcome
  • ACCOUNT RESEARCH
    • Overview
      • Features
    • Market Map
      • Account Import
        • Salesforce
        • HubSpot
      • Salesforce Integration
        • How to Install Similar Accounts Component
      • CRM Export
        • Salesforce
        • HubSpot
      • FAQs
        • Attributes in Market Map
    • AI Researcher
      • How to create & configure an AI Researcher
      • Writing effective prompts
      • Prompt examples
      • Managed AI Researcher
    • Lookalikes
    • Credits
  • Bookbuilder
    • Overview
    • Enroll Accounts
    • Target Books
      • Target Book Report
      • Edit Reps
    • Account Coverage
      • Market Coverage
      • Rep Coverage
      • Working Activities
    • Transfer Accounts
      • Concepts
      • Account Pool
      • Distributions
      • Retrievals
      • Returns
      • Templates
      • Scheduling
      • Troubleshooting
    • How-to Guides
      • How to Rank Accounts for Distributions and Retrievals
      • How to Use the "Is In" Operator
  • Routing
    • Overview
    • Dashboard
    • Round Robin Queues
      • Create Queues
      • User Availability Status
      • User Working Hours
    • Users
    • Capacity Meters
    • Lead and Account Matching
    • Automation
      • Automation Executions
      • Log Entries
  • Automation Builder Kit (ABK)
    • Getting Started
    • Actions
      • Assignment
        • Directly Assign Items
        • Round Robin Assign Single Item
        • Round Robin Assign Multiple Items
        • Schedule and Assign Single Item
      • Dynamic Books
        • Retrieval
      • Flow Lifecycle
        • Execute Subflow
        • Failed
        • Finish
        • Resume
        • Start
      • Leads
        • Convert Lead
        • Convert Multiple Leads
      • Logs
        • Log Message
      • Matching
        • Match Account to Account
        • Match Lead to Account
        • Match Lead to Contact
        • Match Lead to Lead
      • Next Steps
        • Add Person to Campaign
        • Add Person to Sales Engagement Cadence
        • Check Person Enrollment in Cadence
        • Create Task
        • Send Single Assignment Email
        • Send Slack Message
      • Users
        • Get Used Capacity
        • Update Capacity
        • Update Weight
      • Utils
        • Evaluate Domain against Denylist
      • Advanced
        • Build Record Map from Lookup
        • Build Record Map from Field
        • Build Text Collection from Field
        • Convert ItemAssigned to Assignment
        • Execute SOQL
        • Get Record from Record Map
        • Assign Pending Items for Multiple Queues
        • Assign Pending Items for Single Queue
        • Enqueue Multiple Items
        • Enqueue Single Item
    • Models
      • AccountMatchResult
      • AccountToAccountMatch
      • Assignment
      • ConvertLeadRequest
      • ConvertLeadResult
      • DomainEvaluationResult
      • GenericSObject
      • LeadToAccountMatch
      • LeadToContactMatch
      • LeadToLeadMatch
      • QueueUserWeight
      • RecordMap
  • Integrations
    • Getting Started
    • Slack
    • Google Workspace
    • Microsoft 365
    • Salesloft
    • Outreach
  • Advanced
    • Salesforce Permissions
  • Miscellaneous
    • Changelog
Powered by GitBook
On this page
  • How to write effective prompts
  • General tips for prompts
  • Advanced tips for prompts
  • How to format outputs
  • The new GPT models
  1. ACCOUNT RESEARCH
  2. AI Researcher

Writing effective prompts

How to write effective prompts

Here are a few guidelines to writing a clear and effective prompt. Read on for more tips and examples.

  • Be crystal‑clear about “who” and “what”. Start every prompt by defining the model’s role, objective, and scope.

  • Provide plenty of examples. Show exactly how you want inputs mapped to outputs. For functions, include sample calls and responses under a dedicated “Examples” heading.

  • Specify output rigorously. Spell out exactly what you need in your results. We support the following values:

    • Boolean (true or false)

    • Number

    • Text

    • Picklist (a predefined set of options)

  • Iterate and refine. When you see hallucinations or format drift, add one clarifying sentence to correct it. Test small tweaks and watch how the model’s behavior changes.

General tips for prompts

Tip 1: Always begin by clearly stating the main task or objective you want the model to accomplish.

Objective: Your task is to assess if the provided set of companies are SOC2 compliant.

You are a market‑research analyst with access to up‑to‑date business data. Your goal is to compile comprehensive firmographics on a given company. Respond concisely, cite sources, and flag any data uncertainty.

Tip 2: Keep the main task or objective as short and crisp as possible. Adding unnecessary info would clutter the model’s understanding.

Tip 3: If there are specific conditions or custom business logic you want the model to adhere to, clearly list them under a separate heading labeled “Instructions”. This should solely focus on any specialized knowledge or business requirements you want the model to incorporate.

Instructions:

<List specific business conditions or rules here>

Tip 4: Provide additional examples under Instructions to improve the model’s performance. This part is not necessary but adding additional examples would really enforce the model to follow this pattern and it’s highly recommended for complex use cases.

Instructions:

1. (List specific business conditions or rules here)

Examples:

  • If the company follows condition_1, then classify it as category_1.

  • If the company follows condition_2, then classify it as category_2.

Tip 5: If you are requesting multiple outputs from AI Researcher make sure to provide examples and classification instructions for all the labels separately. This should be provided in the “Prompt” area as well as under Label description under “Outputs”.

Advanced tips for prompts

If you have a general idea of where the information might be generally available in a website, try adding that under the Instructions. For example, you want to find all the locations where the company operates in a particular market. You also have a general idea that this information may be present on their website on pages like /about, /locations, /contact.

Adding these mini examples could potentially guide the AI researcher to search for these patterns while browsing. This doesn’t guarantee that the model will look at these pages for all the provided set of companies but it gives a general direction/guideline that the AI Researcher could potentially follow.

Instructions:

The information that you are looking for might be present in pages like:

  • https://company.com/about

  • https://company.com/locations

  • https://company.com/contact

Note: (Sometimes this may hurt the model’s performance if this pattern is not found in majority of the sites, so be sure to experiment with this)

How to format outputs

Provide comprehensive instructions for each output label in the “Output” tab. Clearly define the meaning and purpose of each label under description specifying exactly what the model should identify or classify based on that label.

Ensure consistency by replicating the label instructions in both the “Prompt” and “Description” tabs. This need not be an entire copy paste of all the instructions; just a summarized version should be enough. This repetition strongly reinforces the conditions the model must adhere to during labeling or classification.

When selecting "Picklist" as the value type for your labels, it is strongly recommended to use advanced models such as GPT-4.1.

The new GPT models

AI Researcher now supports the latest GPT-4.1 models. GPT‑4.1 is more literal and obedient to instruction than prior models, making it extremely steerable via well‑specified prompts.

“GPT-4.1 is trained to follow instructions more closely and more literally than its predecessors, which tended to more liberally infer intent from user and system prompts. This also means, however, that GPT-4.1 is highly steerable and responsive to well-specified prompts - if model behavior is different from what you expect, a single sentence firmly and unequivocally clarifying your desired behavior is almost always sufficient to steer the model on course.”

You’ll get more reliable, controllable, and powerful outputs from GPT‑4.1 if you include:

  • Clear roles/expectations

  • Structured instructions

  • Judicious examples

  • Optional chain‑of‑thought

PreviousHow to create & configure an AI ResearcherNextPrompt examples

Last updated 23 days ago

From OpenAI on their :

guide to GPT-4.1