--- title: "Rig at Rig: investor reporting on autopilot — Rig" description: "How Rig's founder put 10 years of monthly investor reporting on autopilot — a saved skill run in Claude over Rig's context layer, with investors self-serving governed data in Slack." canonical: "https://rig.so/case-studies/rig" format: markdown --- [All case studies](https://rig.so/case-studies) Rig at Rig · Founder workflowInvestor reporting # Putting 10 years of monthly investor reporting on autopilot Rig's founder Toby has written investor reports every single month for a decade, roughly 120 updates, without fail. Good month or bad, his investors got the picture. The hard part was never the writing, it was pulling together all the data and context behind it, and finding the hours to do it well. Here's how he runs that whole process on Rig now, automatically. Built in Claude· with Rig MCPRig context layer· over the warehouse Watch ## How I do investor reporting at Rig 10 yrs Of monthly investor reports, every single month ~120 Reports written, without fail, good month or bad On autopilot Now written automatically, the night-before scramble gone ## The challenge was never the writing, it was the data and the time. Ten years and roughly 120 reports, through Lingumi and now Rig, kept a loyal group of investors with the journey through good months and tough ones. But every report meant the same uphill pull. Pulling the data together Top-line numbers, cash flow, the funnel, product usage by customer, all living in different tools and never joined up in one place. Finding the time The answer was often no. Reports got scrambled together at night, or went out below the standard Toby and his investors expect. Keeping the standard Every report needed both the numbers and the story behind them. Doing that by hand, monthly, for ten years, is relentless. Now, on autopilot ## The monthly report writes itself Rig acts as a data brain that understands the business, giving not just the top-line numbers but the story behind them. Three pieces make that work. Rig as the context & connection layer Rig ingests data from finance, contracts, product analytics, the CRM, calls and banking, then builds context, semantic metrics and usage rules on top so the data is ready for AI to use. A saved skill, run in Claude A monthly investor skill, saved on Rig so the whole team can access it, tells Claude exactly what to produce and how to process it. Toby just runs it. Numbers and the story behind them Rig pulls the usage rules, semantic metrics and live data and Claude returns the finished update: headline numbers, business summary, features and how customers are using the product. ## And investors can go deeper themselves The monthly report is the start. Investors can serve their own reporting needs and figure out how to help the business, without having to ask. Investors in a governed Slack channel Rig's investors sit in a Slack channel where they can talk to Rig directly and query internal data, with governance restrictions on what they can see. Accurate data, no founder in the loop One investor pulled pipeline status on a live deal one morning, found a way to help move it along because he knew someone there, and got accurate answers, all without Toby having to intervene. Under the hood ## The infrastructure that makes it reliable So none of this depends on babysitting a janky skill file. Rig brings the data together, governs it, and keeps the whole pipeline reliable. Step 1 Connect Bring an existing warehouse or provision one Rig manages. Connect an LLM, then connect sources: CRM, emailing tool, call recordings, banking data, HubSpot and more. Step 2 Ingest & structure Rig pre-builds the aggregations, tables, models and metrics so AI doesn't YOLO API calls, burn tokens and get joins wrong. The data is contextualized behind the scenes. Step 3 Build context A context graph maps how all the data connects and the rules for using it, down to which fields are PII or sensitive and excluded for certain users. Step 4 Apps, skills & usage rules On top, Toby builds data apps (like a funnel metric tree) and reusable skills, including the monthly investor skill that guides Claude through each update. The result: Toby runs one skill, Rig does the work behind the scenes, and the monthly update arrives prepared, along with tools investors can use to go deeper on their own. ## Want results like this? [Book a demo](https://rig.so/book-demo)[See how Rig works](https://rig.so/walkthrough) --- - [This page as HTML](https://rig.so/case-studies/rig) - [Site map for language models](https://rig.so/llms.txt) - [API and agent documentation](https://rig.so/developers)