FeaturedEducation & Learning#Academic Research#Literature Review#Research Assistant#Citation Matrix#Brave Search MCP#Education

Academic Literature Review Research Agent

Search public scholarly sources, build a citation matrix, and email a literature review brief with gaps and follow-up questions.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#Academic Research#Literature Review#Research Assistant#Citation Matrix#Brave Search MCP#Education

Click a node to select it — same as the Heym editor; the panel shows its settings.

6 nodes · Free & source-available

Academic Literature Review Research Agent

This research workflow template is built for students, faculty, and research teams who need a repeatable literature review process. It uses an agent with web research tools to gather sources, group findings, and create a citation matrix.

What this workflow does

  1. ResearchQuestion captures topic, field, and inclusion criteria
  2. LiteratureReviewAgent uses Brave Search MCP to find candidate sources
  3. BuildCitationMatrix maps claims, methods, and source notes
  4. SaveLiteratureMatrix stores the research brief
  5. EmailResearchBrief sends the review packet
  6. LiteratureReviewResult returns the synthesis

Setup

Add a Brave Search API key to the MCP connection, connect an LLM credential, and review sources before using the brief in academic writing.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym