Blog

Notes from the build

How SeldonFrame is built, why we made the architecture choices we did, and what we learn from real founders shipping agents — plus original stories mined from the people actually doing it.

July 13, 2026·Maxime Houle

Why Original Content Wins SEO Now (and AI Slop Loses)

Google's own spam policy has a name for content mass-produced with no original value: scaled content abuse. The practical question for anyone using AI to write isn't whether the words came from a model — it's whether a real person's judgment, facts, or experience are in there.

Read post
July 13, 2026·Maxime Houle

Agents Are the New SaaS: The Playbook for Selling AI Labor, Not Software

Greg Isenberg's pitch is a one-line mindset flip: a SaaS product hands someone a tool; an agent SaaS product removes a job from their to-do list entirely. Here's his actual playbook for finding the workflow, building the smallest useful version, proving it works, and pricing it like labor.

Read post
May 7, 2026·SeldonFrame Team

Why we built SeldonFrame on MCP

Most AI startups wrap a single chatbot UI around an LLM. We took the opposite bet: expose the whole product as MCP tools and let Claude Code be the chrome. Here's why.

Read post
Coming soon·SeldonFrame TeamComing soon

How the eval gate works (and why agents need one)

A chatbot that hallucinates a price or claims it booked an appointment when it didn't isn't a bug — it's a real-money problem. The 8-scenario suite, the LLM-as-judge rubric, and the runtime regeneration that catches what the suite misses.

Coming soon·SeldonFrame TeamComing soon

BYOK is not a feature, it's the deal

Why SeldonFrame doesn't markup tokens, doesn't pool LLM access, and doesn't ration by tier. The economics work better when the customer owns the provider relationship.

Follow @seldonframe on 𝕏 for new posts, or join the Discord to talk to the team.