Why the extension exists
The extension turns agent-written verification into something you can inspect like normal engineering work: code on the left, evidence beside it, debugger when needed. `explore/` is where exploratory API work can replace Postman without fragmenting the stack or trapping drafts in a second tool.
Open the workflow your agent wrote and run it from the gutter without leaving the editor.
Set breakpoints, inspect variables, and step through the code instead of guessing from terminal output.
Compare runs, inspect evidence, and decide whether the workflow is trustworthy enough to keep.
A workflow can start in `explore/` as a Postman replacement, then become the same file you commit, review, and promote to CI.
End to end
The extension is where you validate what the agent produced and decide whether the draft earns a place in the repo.
Prompt and context
“Verify checkout with promo code, tax calculation, and webhook delivery.”
Context fed into generation
Agent draft
import { test } from "@glubean/sdk";
export const listUserRepos = test(
{ id: "github-list-repos", tags: ["explore"] },
async (ctx) => {
const username = ctx.vars.require("GITHUB_USERNAME");
const token = ctx.vars.get("GITHUB_TOKEN");
const headers: Record<string, string> = {
Accept: "application/vnd.github+json",
};
if (token) {
headers["Authorization"] = `Bearer ${token}`;
}
const data = await ctx.http
.get(`https://api.github.com/users/${username}/repos`)
.json();
ctx.expect(data.length).toBeGreaterThan(0);
ctx.log("Repos", data.slice(0, 3));
},
);What the agent did
Used your OpenAPI routes
Matched auth, cart, promo, and checkout paths from the project spec.
Generated SDK workflow code
Named steps and typed assertions, not free-form fetch calls.
Followed project conventions
Respected existing config helpers and file placement.
Ready to run immediately
Click play to see traces and verify the draft before committing it.
Starts where Postman used to live
Exploratory API work can begin in explore/, then graduate into durable tests without changing tools.
Prompt
Context goes in
Code
TypeScript comes out
Trace
Evidence closes the loop
Why the draft stays grounded
The extension feels good because the draft is not generic. Specs, skills, SDK surfaces, and MCP tools keep the workflow tied to your project instead of drifting into demo code.
Agent-written code uses Glubean workflow primitives — named steps, typed assertions, shared config — so the output looks like code your team wrote.
Learn moreAnnotated specs and reduced context keep the agent focused on the routes, constraints, and response shapes that matter.
Learn moreA skill file teaches the agent your exact SDK API, auth patterns, assertion style, and conventions so drafts follow your team's patterns from the start.
Learn moreMCP tools let the agent run the workflow, read structured failures, fix the code, and rerun without dropping back to pasted logs.
Learn moreInside the extension
Once the agent writes the draft, the extension keeps the feedback loop tight: run it, check the trace, fix what needs fixing, and move on without leaving the editor.
Run one workflow, one file, or the whole workspace directly from the editor gutter.
Step through real code and inspect variables instead of guessing from logs.
Compare two runs with native diff to see exactly what changed in the workflow.
Use built-in validation patterns so generated code has real assertions behind it.
Move across local, staging, and production context from the status bar without rebuilding the test.
Everything stays in TypeScript, so PR review, branching, and refactoring work like normal.