Identify Key Decision Makers
Analyzes input data with an LLM to identify key decision makers like heads of sales or VPs of revenue for outreach.
What it does
You instantly identify key decision makers like heads of sales and VPs of revenue from your input data using Cloud Code and an LLM. This gives you a clear score breakdown to target the right people for outreach without manual searching.
Step by step
- Set up a Cloud Code trigger that activates when new lead data is created or updated in the database.
- Define a strict JSON schema for the output to ensure consistent extraction of role titles and names.
- Implement error handling logic to catch malformed input data before passing it to the LLM.
Where the LLM does the work
- Prompt the LLM to analyze unstructured text fields like bios or email signatures to infer decision-making authority.
- Instruct the model to distinguish between junior staff and key decision makers based on contextual cues in the text.
- Have the LLM generate a confidence score for each identified role to help prioritize outreach efforts.
Watch out for
Ambiguous job descriptions can lead to misclassification of seniority so provide clear examples of what constitutes a decision maker.
Large text inputs may exceed token limits so truncate or summarize non-essential biographical details before processing.
Inconsistent naming conventions across sources require robust normalization logic so map varied titles to standard roles.
Tools that fit
Cloud Code Service Processing and scoring data
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Identify Key Decision Makers: Analyzes input data with an LLM to identify key decision makers like heads of sales or VPs of revenue for outreach. ## Specification - What it does: You instantly identify key decision makers like heads of sales and VPs of revenue from your input data using Cloud Code and an LLM. This gives you a clear score breakdown to target the right people for outreach without manual searching. - Trigger: Run manually (Manual · on demand) - Autonomy: You stay in control - Expected setup effort: about an afternoon - Tools/services involved: - Cloud Code: Processing and scoring data - LLM: Analyzing text to identify roles like VP of Revenue or Head of Sales ## Known pitfalls, handle each one explicitly in your implementation 1. Ambiguous job descriptions can lead to misclassification of seniority so provide clear examples of what constitutes a decision maker. 2. Large text inputs may exceed token limits so truncate or summarize non-essential biographical details before processing. 3. Inconsistent naming conventions across sources require robust normalization logic so map varied titles to standard roles. ## Reference implementation https://www.youtube.com/watch?v=JqXkPlX_4gQ (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/identify-key-decision-makers/ via usecasesforagents.com
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for founders and execs who need sales handled without hiring for it.
Sales teams can plug this into their own CRM and call cadence just as easily.