.svg)
Helios Logistics was losing pipeline to manual admin work. We automated their lead engine — enrichment, CRM cleanup, and follow-up cadences — so reps could focus on selling.
Helios Logistics moves freight across 14 states. Their sales team was spending six hours a day on manual lead enrichment, CRM data entry, and follow-up scheduling. The pipeline was leaking because reps were doing admin work instead of selling.
They came to Soch with a hypothesis: most of this was rule-based and could be handed off to systems. We agreed, but only after auditing where the real bottlenecks lived.
Reps were drowning in low-leverage work. Lead enrichment took 20 minutes per contact. Follow-ups slipped because no one owned the cadence. The CRM had stale data in 60% of records, which meant outreach was going to wrong people at wrong companies.
We shadowed three reps for a week to map every manual touchpoint. We identified 11 tasks that could be fully automated and 4 that needed human judgment but could be assisted.
We built a lead-routing pipeline in n8n that enriches contacts from three sources, scores them against an ICP model, and writes to HubSpot automatically. Reps now get pre-qualified leads with full context.
We stayed for four weeks after launch to watch real data, fix edge cases, and train the team. Documentation lives in their Notion. The system has run without intervention for 90 days.
“Soch did not just hand us a workflow. They built the thing, watched it run, and made sure our team actually used it. The follow-through is what made the difference.”
Marcus Hale, Head of Sales, Helios Logistics
Let us audit your operations and show you exactly where to start.
Get your free auditClearwater Intelligence was drowning in manual research. We replaced their entire monitoring process with an AI agent that scrapes, classifies, and routes intelligence around the clock — with no human input per cycle.
Clearwater Intelligence tracks competitor activity, compliance updates, and lead signals across dozens of sources. Their analysts were spending the majority of each week doing this manually — visiting websites, reading documents, pulling data, and classifying findings into internal systems. The process worked when the source count was manageable. It stopped working when the business grew.
They came to Soch with a clear hypothesis: most of what the analysts were doing was pattern-based, and pattern-based work belongs to a system. We agreed, but we started with a process audit before touching any tools. We needed to understand where the research logic actually lived before we could automate any of it.
Analysts were spending 20+ hours a week on research that produced inconsistent outputs. Several key sources had no API, making standard automation unworkable. Classification depended on whoever had time that day, which meant the same information got labelled differently depending on the week. The CRM was always behind.
We shadowed two analysts for a week to document every source, every classification rule, and every edge case in the process. We identified which decisions required genuine judgment and which were rule-based enough to give to a machine. This became the architecture blueprint.
We built a scheduled n8n workflow using Puppeteer and Browser Use to scrape sources with no available API, including ERP and CRM platforms that required RPA-style navigation. An OpenAI-powered classification agent reads each result, applies the correct category, and routes it to the right table in Airtable. PDF documents are detected, extracted, and processed in a dedicated parallel branch.
We connected the classification output to an automated daily digest that compiles, deduplicates, and distributes findings each morning. Error logging runs in parallel and flags any failures without silently breaking the pipeline. Documentation covers every decision point in the system. It has run without intervention since launch.
Manual research hours eliminated. The system runs on a schedule with zero human input per cycle.
Reduction in information processing time. Multi-hour sessions now complete in minutes.
More sources monitored simultaneously than the previous manual process could cover.
We used to brief analysts on what to look for and hope the output was consistent. Now the system does it and the structure is always the same. The team moved to higher-value work within the first month.