{"slug": "building-an-ai-powered-research-email-assistant-with-crewai", "title": "Building an AI-Powered Research Email Assistant with CrewAI", "summary": "CrewAI, an open-source multi-agent framework, was used to build an AI-powered email assistant that automatically researches topics like the impact of 5G on smart cities and emails back a formatted report. The system uses specialized agents for request analysis, web research via Tavily Search, report writing, quality review, and email dispatch via Gmail, completing in minutes instead of hours.", "body_md": "Imagine sending an email that says:\n\n“Please research the impact of 5G on smart cities and send me a concise report.”\n\nA few minutes later, an AI system has read your request, understood exactly what you need, searched the web for real information, written a structured report, reviewed it for quality, and emailed the finished result back to you — formatted and ready to read.\n\nNo manual searching. No copy-pasting between tabs. No summarizing at 11pm. Just a clean, professional research report waiting in your inbox.\n\nThat’s what I built using **CrewAI** — a multi-agent framework that lets you orchestrate a team of specialized AI agents the way you’d manage a real team of people.\n\nHere’s the full architecture, how each piece works, and what actually happens behind the scenes when it runs.\n\nCrewAI is an open-source framework for building multi-agent AI systems. Instead of stuffing everything into one giant prompt and hoping for the best, CrewAI lets you create specialized agents — each with its own role, goal, and tools — and connect them into a flow: a structured pipeline that passes data from one step to the next.\n\nThink of it like hiring a small team:\n\nEach person is an expert at exactly one job. That’s the whole idea behind this automation.\n\nGetting a proper research report usually means:\n\nThat’s a couple of hours, easily. With CrewAI, the same pipeline runs in minutes — with real web search data behind it, not hallucinated summaries.\n\n```\nIncoming Email (sender + subject + body) │ ▼Email Request Analyzer → extracts topic & requirements │ ▼Research Analyst (Tavily) → gathers real findings │ ▼Technical Writer → writes structured report │ ▼Report Reviewer → quality checks the report │ ▼Email Dispatcher (Gmail) → sends formatted HTML report\n```\n\nOnly two external integrations are involved: **Tavily Search** for live research and **Gmail** for delivery. Everything else is pure LLM reasoning.\n\nOne of the most important ideas in CrewAI Flows is **state** — a shared structure that carries information across every step.\n\nFieldDescriptionsenderRequester's email addresssubjectEmail subject linebodyEmail body textresearch_topicExtracted topicresearch_requirementsExtracted requirementsresearch_resultStructured findingswritten_reportDraft reportreview_resultApproval status + feedbackfinal_reportApproved reportemail_statuspending / sent / failed\n\nThe key design decision: only sender, subject, and body are external inputs. Everything else is generated and passed internally. That keeps the system clean and removes the temptation to add unnecessary manual steps.\n\nReads the subject and body, identifies the research topic, and extracts requirements like length, audience, tone, and sub-topics — returned as structured JSON:\n\n```\n{ \"topic\": \"Impact of 5G on Smart Cities\", \"output_type\": \"research_report\", \"length\": \"concise\", \"audience\": \"general\", \"requirements\": [ \"How 5G enables smart-city applications\", \"Benefits for transportation and healthcare\", \"Key challenges like cybersecurity and cost\", \"Real-world examples\" ], \"is_valid_request\": true}\n```\n\nIf the email isn’t actually a research request, this agent flags it and the flow stops — no wasted compute downstream.\n\nUses the **Tavily Search API** to run targeted web searches on the extracted topic. Tavily is built specifically for AI agents — it returns clean, summarized, LLM-friendly results instead of raw search-engine clutter, which makes it a much better fit here than a general search API.\n\nThis agent is explicitly instructed to never fabricate facts — it only reports what it actually finds.\n\nTakes the research findings *and* the original requirements and turns them into a complete markdown report: title, intro, key findings, examples, conclusion — matched to the requested tone, length, and audience. It’s not allowed to invent anything beyond what the Research Analyst provided. This agent is the bridge between raw data and something a human actually wants to read.\n\nThe quality gate. It checks the report for relevance, completeness, clarity, factual consistency, and formatting, then returns a structured verdict:\n\n```\n{ \"approved\": true, \"score\": 9, \"issues\": [], \"revision_instructions\": []}\n```\n\nImportantly, the reviewer **never rewrites the report** — it only evaluates. Keeping generation and evaluation separate is one of the core architectural decisions here.\n\nConverts the approved markdown report into clean HTML (## →

, **bold** → , bullet lists → proper