Brendan O'Neil's Artifacts
Moments of impact from Brendan O'Neil's career
Running an NFL Weather App With a Team of AI Agents
The Boston Builder Series, from @MGMT Boston in partnership with @Trove. Brendan O'Neil isn't an engineer. He's Director of Strategic Partnerships & Alliances at @Robin , the Boston workplace platform. This fall he shipped a live product anyway, by hiring a team of bots and managing them like a crew. The product is Game Day Weather, a weekly NFL forecast board with a simple promise: "NFL weather before you lock." Every game gets a chip, FLAG, WATCH, CLEAR or DOME, so you know whether a storm might roll through in the second half before you set a lineup. The spark was last season's AFC title game, "where I had no idea there was going to be a blizzard in Denver." Pre-work: the Gell-Mann check Before Brendan built anything of his own, he did some pre-work: he measured each AI tool against his own expertise, like technology partnerships. The idea borrows from Gell-Mann amnesia, a term Michael Crichton coined in a 2002 speech and named after physicist Murray Gell-Mann. You read a story on a subject you know well, spot that it's wrong, then turn the page and trust the same outlet on everything else. "You turn the page, and forget what you know." Testing the tools on work he knows cold showed Brendan where they're sharp and where they miss. He carries that read into areas he can't judge himself, like code and weather forecasts. And where he can't judge a claim, he checks the evidence instead of trusting the source: he reviews every PR, and the site keeps a public report card. That's what lets a partnerships lead run an engineering bot. Why Grok Bot Brendan has built a couple dozen apps with tools like Replit and Lovable. For Game Day Weather he moved to Grok Bot, xAI's agent product, because it's chat-based ("it kind of looks like iMessage") and lets him run a team instead of a single assistant. Each bot gets its own virtual machine and email address. "It's like my own little Ocean's Eleven," he says. "You're hiring a group of bots to manage this for you." The crew • Sideline, the weather researcher. Pulls local forecasts from several sources, blends them, and grades every game card FLAG, WATCH, CLEAR or DOME. • Cursor Ops, the engineer. Works inside Cursor, runs a preflight check on each chip, pushes updates to the live site, and opens small PRs for UI changes. • Chief of Staff. Coordinates between research and engineering, then proofs and sends. • Comms. Handles the Buttondown newsletter and the @getGDW posts on X. Brendan's job is the one he describes as "idea guy." He gives one directive, watches the team work it out in a group chat, and the bots "raise their hand" when a pull request is ready for him to review and merge on GitHub. Merge PRs and pick ideas. That's the whole human role. The bots weigh in on product decisions too. When Brendan asked whether to add branded MCP UI cards to the app's AI-facing results, Sideline recommended a small test on one tool while keeping plain data as the main answer, since many agents only read text. Cursor Ops went off to check which chat apps actually render it before answering. The weekly loop The team runs on the NFL clock, with no out-of-cycle weather asks: 1. Research. Pull kickoff-window weather for the Thursday, Saturday international, Sunday and Monday slates. 2. Board. Grade every game and write the notes. 3. Live. Preflight, ship to the site. 4. Post. Newsletter and social, then on to the next clock. It also grades itself. The site keeps a public report card, and Week 5 came in at 9 hits, 1 partial and 0 misses. The takeaway "This has helped me learn how to build and develop an agentic-led team," Brendan says. A few weeks of shipping taught him how the team improves, and how he can work better inside that structure. You don't need to write the code to run the team. You need a clear directive, a loop, and a check on what you can't verify yourself. See it live at gamedayweather.app. The Boston Builder Series highlights people across Boston building with AI, from @MGMT Boston in partnership with @Trove.
Validated by 1MCRally · Advisor
Advisor to Rally, the Auto-Updating Video Platform for Internal Storytelling
As an Advisor during Rally's seed stage, they worked on internal company storytelling around product, vision, and enablement, with a focus on video content. Video is one of the most engaging formats for this kind of communication, but the existing approach had a real flaw: as facts and figures changed, the video content went stale fast. Teams had to re-record material constantly just to keep it accurate, which was expensive and, worse, chipped away at trust when outdated numbers slipped through. I advised as they built a new product that separated the recorded video from the data inside it. Instead of baking facts and figures directly into each video, the product let teams pull from a shared, updatable asset library, so when something changed, the video reflected it automatically instead of requiring a full re-record. We shipped the product and saw real engagement from teams at Rally, with Robin becoming a heavy user of the tool. The product was eventually sunset in 2026, but it solved the core problem it was built for: keeping internal video content accurate without the constant manual rework.
Not validated