I build Giant Context.
An autonomous marketing platform, built and run by one person
About Giant Context
A real site the platform designed, wrote, and published on its own.
Latest Writing
New field notes from the build, as they land
I built a marketing platform artificial intelligence runs
Giant Context is a marketing platform where the intelligence is the operator. A model reads what a business is, works out what its marketing is missin...
|
Sep 2, 2026Cutting the homepage from 5.7MB to 217KB
Ten days of frontend performance work on the public site, including the four hypotheses that turned out to be wrong. Images were served raw because a ...
|
Sep 1, 2026Compute gets cheaper per request at scale
I price Giant Context at $25 per million tokens and had no defensible answer to what it costs to serve a thousand customers. Four of the five cost cla...
|
Aug 30, 2026The build in milestones
Nine months, one platform, one person. The turns that changed the build.
The business case for Giant Context
The market an autonomous marketing platform opens, and the case for building it.
Generating code from the API spec
One OpenAPI description generates the client, the types and the tests.
API keys, the SDK, and MCP from one spec
One specification becomes the console's client, a developer SDK and an agent's toolbox.
A single prompt cannot build a website
The prompt was never the hard part. The process was.
The Swiss Cheese Model
Eleven imperfect checks in sequence, each with a hole I can name.
Giant Context decides what marketing you need and builds it
One system reads the business and works out what marketing is missing.
The marketing is built from your files
Every claim anchors to a real file or it never reaches the page.
Rules cannot govern creative work
I deleted the rule layer from the builder and the pages got better.
What one person actually built
505 operations, nine services, two SDKs, four platforms, one person.
Rebuilding RBAC on GCP notation
Four systems answered one authorization question and disagreed.
Auditing an MCP server with an agent
An agent doing real editorial work found what testing could not reach.
Cutting the homepage from 5.7MB to 217KB
Ten days of performance work, including the four hypotheses that were wrong.
About me
Jesse Richard
I'm Jesse James Richard. Twenty years building software from the first line of code taught me the engineering only counts when it opens a market. Now I'm building Giant Context on my own, one architect directing a crew of AI agents, writing down how as I go. I live in Canada with my family, play more hockey than I should, and read more than anyone thinks is reasonable.