Is it a problem if our processes aren't documented?

Not at all — that's literally why Fenrir Labs exists. We specialise in capturing undocumented knowledge from your best people and turning it into scalable Human + AI systems. You don't need documented processes to start.

We tried AI before and it didn't stick. Why would this be different?

Most AI pilots fail because they're bolted on instead of woven in. Fenrir Labs embeds AI into your actual workflows with training, adoption tracking, and ongoing support — so it becomes how work gets done, not a side project that fades after launch.

What happens after you leave?

Everything is fully documented and your team is trained to own the system. We don't drop a tool and disappear — we help you roll out, train, and refine so new workflows become 'how we work here' and your advantage compounds over time.

Won't this just make our output feel like AI?

The opposite. We design systems where AI handles the first pass using your standards, and your team applies the human judgment that makes your work uniquely yours. The result is your best work, scaled — not generic AI output.

How long does a typical engagement take?

AI Discovery starts with a 1-2 week assessment with no commitment beyond that. Design, Build & Integrate engagements vary in scope — agreed before we start. Monthly retainers provide ongoing support.

What if our team doesn't adopt it?

Adoption is built into our process. We train your team, embed new habits, and track adoption metrics. Workflows only create value if people use them, which is why our Enablement phase ensures AI becomes part of your operating system.

Lead Enrichment with Attio + n8n: An AI-Powered Research Pipeline

Jan 29, 2026

A modern CRM workflow that gathers data from multiple sources, processes it through AI agents, and delivers actionable insights automatically — no manual research required.

The Problem

Lead enrichment is one of those necessary tasks that just takes time. Clean data is locked away in APIs. Sites where you'd find the right info won't let you scrape them. And even when you get the data, it's scattered across sources with no clear way to turn it into something your sales team can actually use.

We wanted to fix that.

The Approach

Our solution breaks lead enrichment into three stages that run automatically once triggered:

1. Gather. Pull data from APIs and services that have already done the hard work of collecting company information.

2. Process. Massage raw data into structured formats. Let AI agents summarize and extract what matters.

3. Verify & Deliver. Have a critic agent validate claims, then push clean, actionable insights into your CRM.

The key insight: we don't scrape websites. We leverage databases and API services that have already aggregated the data we need. Each source provides a different angle on the company.

System Design

The pipeline flows through four stages. Here's how each one works.

Stage 1: Gather Data from Multiple Sources

We pull from three complementary data sources, each providing a different lens on the target company:

Apollo.io provides company data, contacts, and recent news. LinkedIn gives us company posts and leadership profiles. News articles surface recent coverage and announcements.

Each source fills a gap the others can't. Apollo gives you the structured firmographic data. LinkedIn shows you how the company presents itself and what leadership is talking about. News coverage reveals what's happening externally.

Stage 2: AI Agents Summarize in Parallel

Raw data from Stage 1 feeds into three specialized AI agents, each focused on extracting specific insights relevant to sales conversations:

The News Summary Agent extracts key talking points from recent articles and announcements. The Company Activity Agent analyzes LinkedIn posts to understand current positioning. The Leadership Agent uses employee activity and posts on LinkedIn to create hypotheses on leadership behaviours and priorities.

These agents run in parallel, so enrichment stays fast even as you scale the number of leads.

Stage 3: LLM-as-Judge Validates Claims

Before anything hits your CRM, a critic agent reviews the output. It flags outdated info, verifies facts, and suggests corrections.

This "LLM-as-Judge" pattern is critical. The critic reviews all agent outputs against current data, uses web search to verify claims are accurate as of today, and returns a verification status with recommended updates. Without it, you risk pushing hallucinated or stale information into your CRM — and your sales team loses trust in the data.

Stage 4: Structured Output to Attio

The final agent synthesizes everything into structured fields that map directly to your CRM. Company records and leadership contacts get updated automatically.

The fields we populate in Attio include Current Positioning (how the company presents itself today based on public activity), Key Conversation Points (1–3 specific talking points to open a sales conversation), and Leadership Conversations (hypotheses on leadership behaviours based on employee activity and public engagement).

Example: Miro

Here's what the output looks like for a real company. When we ran this pipeline against Miro, here's what landed in Attio:

Positioning

Miro positions itself as an innovation workspace for distributed teams, centered on visual collaboration and increasingly augmented by AI capabilities embedded directly in the board experience. The emphasis is on helping teams move from ideation to alignment and execution faster, while signaling an enterprise-ready posture around governance, trust, and control for AI adoption.

Conversation Points

AI for collaborative work (not just individual productivity). Explore where teams lose momentum today — workshop prep, synthesis, planning — and how AI inside a shared canvas could reduce manual admin and speed alignment.

Adoption and governance. Discuss what guardrails they need for AI in a collaborative tool (permissions, admin controls, data handling, compliance requirements) and how they evaluate vendor trust.

Use-case mapping across teams. Identify the highest-value workflows — product discovery and planning, cross-functional alignment, facilitation/workshops, lightweight prototyping — and define what "success" looks like so AI features are deployed purposefully, not as a novelty.

Leadership Conversations

Leadership signals a strong focus on navigating AI-driven change and positioning Miro's evolving AI capabilities as a competitive differentiator. Based on social engagement summaries, the CEO's activity suggests interest in change management in the AI era; the CPO's engagement aligns with themes of personal growth and transitions; and the CMO's interactions indicate enthusiasm for product features that help teams recap, summarize, and present work in curated, visual formats.

For outreach, treat these as hypotheses to validate in discovery rather than firm indicators of intent.

What Your Team Gets

Hours saved on manual research per lead. Consistent enrichment quality across all leads. Verified, up-to-date information in your CRM. Ready-to-use conversation starters for sales.

The combination of parallel AI agents, fact-checking through an LLM critic, and structured CRM output means your sales team spends less time researching and more time having meaningful conversations.

Why Attio CRM?

I'm always a fan of a lightweight and flexible system, and sometimes flexibility can create complexity. Attio makes it stupidly simple to manage records and update via an API. Its own enrichment process works really well alongside your own.

If you're looking for a CRM that plays nicely with automation workflows, Attio is worth a look.