Observed Signal · Nov 3, 2026 · Corporate Update · Source: Selfstorming · Impact: 2/5
Vercel's marketing team runs on markdown files and a design system. So do we.
Selfstorming analyzed Vercel's product marketing framework, highlighting how CMO Keith Messick built a centralized knowledge base and design system in markdown to power AI workflows. Selfstorming incorporates this 'Brief Zero' methodology into its own Brand Studio and MCP Connector, enabling brands to maintain consistent context across AI outputs. The framework aims to eliminate messaging drift and generic AI content through structured context curation.
This update illustrates how B2B tech marketing teams are transitioning from static documentation to centralized, structured context layers to control and scale generative AI outputs.
Track Selfstorming Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Vercel CMO Keith Messick revealed during an ElevenLabs webinar that Vercel manages product marketing positioning and brand guidelines via markdown files accessible as AI skills.
- Vercel's field marketing agent 'Iris' managed over 200 meetings at its user conference, increasing meeting output tenfold compared to roughly 20 meetings the previous year.
- Selfstorming adopted this framework as 'Brief Zero', organizing core brand assets into story, speaker, audience, voice, proof, and territory.
- Selfstorming connects this context to external AI systems such as Claude and ChatGPT through its MCP Connector.
Connected Companies & Entities
3 Entities mapped“Published the article detailing its adoption of the Brief Zero methodology within its Brand Studio product.”
“Developer tooling company whose markdown-driven marketing brain and internal AI agent Iris serve as the featured case study.”
“Hosted the webinar featuring Vercel CMO Keith Messick and Luke Harries discussing AI marketing workflows.”
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Built B2B Marketplace in 3 Days with V0 and Vercel
A developer built a full‑stack B2B Dutch‑auction marketplace (ClearLot) in three days using V0 for UI generation, Next.js 16 (App Router) for frontend and API routes, Aurora PostgreSQL and DynamoDB for data, and Vercel's AWS integration for deployment and auth. The post praises V0 for producing 70–80% production‑quality multi‑page UIs quickly but notes it struggles with data wiring. It documents a breaking change in Next.js 16 where route params are provided as a Promise (requiring await), and gives a detailed, mostly positive account of the Vercel ↔ AWS integration (OIDC federation, short‑lived tokens, automatic env var population) while listing practical caveats (env var prefixes, development environment checkbox, local OIDC trust, dotenv import order). The article also covers pragmatic hacks used for a 3‑day deadline: a protected /api/migrate endpoint for schema creation and a self‑healing /api/ensure-drops endpoint to keep demo data live.
VP Product Uses Claude to Avoid 'Slop'
This case study profiles Matt Wensing, VP of Product and Design at Customer.io, and how he uses the Claude family of AI assistants to produce leadership-grade outputs without generating low-quality drafts (“slop”). Wensing favors long, iterative Claude sessions with layered context, voice-mode interactions, and a disciplined reveal of domain specifics to avoid generic or premature suggestions. Customer.io pairs Claude desktop work with three internal tools: a Snowflake-connected analysis bot, a Slack channel scanner that surfaces threads needing product input, and “Chiefys,” a company-docs bot that checks new work against official strategy. The post explains practical prompts and workflows (reformatting transcripts to strategy themes, iterating slides then generating talk tracks) and highlights governance: human review of non-deterministic results and data-team oversight for analytics. The article includes tool recommendations and an AI toolstack list used by the author.
Vercel's Andrew Qu: Agents as a New Software Class
Andrew Qu, Chief of Software at Vercel, explains in an interview why AI agents represent a new form of software, how Vercel built internal agents and turned the lessons into the eve agent framework, and why Vercel is making its platform agent-friendly. Qu describes technical primitives (skills, filesystem agents, resumability, sandboxes, subagents), use cases for business automation inside Vercel (contract redlining, marketing retrospectives, query writing), and the idea of serving machine-readable content (Markdown) to agents. He also highlights ongoing challenges—secure code execution, long-running jobs, and collaborative or "multiplayer" agent development—and says Vercel intends to integrate observability and partner integrations while keeping developer onboarding simple.
Receive all future signals for Selfstorming & competitors in your briefing
Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.