ModelRefs / Account Research — Canonical Workflow

Account Research — Canonical Workflow

Account Research: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.

Overview

Account research synthesises a one-page briefing for any target account by pulling from public company filings, recent news, LinkedIn activity, prior CRM interactions and product usage signals. A RAG pipeline retrieves the most relevant excerpts, a summarisation model composes the narrative, and every factual claim is cited back to its source document with a confidence flag. The briefing covers company context, key stakeholders, recent triggers and a recommended approach, and can be regenerated on demand as new signals arrive.

Implementation profile

Categoryllms
Implementation maturityproduction
Primary use casesrag, summarization
Deployment optionsmanaged-api, hybrid
Architecturesserverless-api, managed-container, hybrid-private-cloud

Candidate models with published references

Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.

Benchmarks relevant to this workflow

  • Chatbot Arena ELO — LMSYS crowd-sourced pairwise preference leaderboard across open and closed models.
  • MT-Bench — LMSYS multi-turn chatbot benchmark across 8 categories, GPT-4 graded 1–10.
  • MMLU — Massive Multitask Language Understanding — 57 academic and professional subjects.

These are the benchmarks whose task shape bears on this workflow. Each one only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Account Research — Canonical Workflow.