Elicon
← ALL REFERENCE ENGAGEMENTS
REFERENCE ENGAGEMENT
Sales & Marketing

Prospect Research Agent for a B2B Sales Team

A typed, sourced research dossier for every prospect, written straight into the CRM.

  • TypeScript
  • Node
  • LangGraph
  • OpenAI
  • CRM API

Reference engagements illustrate how Elicon would approach a project of this kind — the problem, the architecture and the decisions. They are examples, not accounts of past client work.

THE SITUATION

The problem.

A B2B sales team that spends a large part of each day researching prospects before writing a single email. The engagement builds an agent that assembles a typed dossier per prospect — company summary, fit against the ideal customer profile, recent trigger events with sources, talking points and prior contact — and writes it back to the CRM where the team already works.

Research quality depends on tenure, prior contact is easy to miss, and enrichment data answers who a prospect is but not why now.

  • ·Experienced reps know which signals predict a reply; newer reps fall back on boilerplate.
  • ·Accounts a colleague already worked are contacted again because checking takes effort nobody spends under quota pressure.

APPROACH

How we'd run it.

  1. 01Build a constrained agent over web search, public filings, news and CRM history.
  2. 02Return a validated, typed dossier rather than free text.
  3. 03Enforce per-run and daily cost budgets in code, with a cheaper model path when a budget is crossed.
  4. 04Trigger runs from the CRM workflow and from a browser extension, writing to the same record.

ARCHITECTURE

What gets built.

Agent graph

A LangGraph state machine rather than an open-ended loop: plan, gather in parallel, reconcile, score, write. A failed tool degrades the dossier instead of derailing the run, and every step can be inspected afterwards.

Typed dossier

A validated schema: summary, fit score with reasoning, trigger events each with a source URL and date, talking points and a prior-contact section. Anything failing validation is retried once, then written as partial with the gaps marked.

Cost governor

Per-run and daily token budgets enforced in code. Crossing the per-run ceiling switches remaining steps to a cheaper model; crossing the daily ceiling queues runs and alerts.

DECISIONS

The trade-offs.

A constrained state graph instead of an autonomous agent loop

The research task has a known shape. Letting a model choose its own control flow makes cost, latency and failure unpredictable for no gain.

TRADE-OFFLess improvisation on unusual prospects, in exchange for bounded time and cost per run.

Every trigger event carries a source and a date

Quoting stale news on a call is worse than no research. Sources and dates make staleness visible.

TRADE-OFFFewer triggers make it into the dossier, because unsourced ones are dropped.

Write into the CRM instead of building a separate research tool

Adoption follows the path of least resistance, and the team's day already runs through the CRM.

TRADE-OFFCRM field limits shape the dossier format, and API limits require batching.

STACK

Typical stack.

RUNTIME
TypeScriptNodePostgresRedis
AI
LangGraphOpenAIStructured outputsModel fallback path
INTEGRATIONS
CRM APIWeb searchPublic filingsNews search
SURFACES
Browser extensionCRM workflows

Work of this shape usually runs as AI Product Launch →

SIMILAR PROBLEM?

Tell us what you're dealing with.

One conversation with an engineer is usually enough to tell whether this is a few weeks of work, a few months, or something you shouldn't build at all.

Talk to an engineer →