Mike's Checks/grok-4.7/10 talkform
10 talkform
grok-4.7Grok CLIhigh effortrun 21 Sep 2026
▸Instructions — what the model was asked
build a typeform competitor where the backend is identical to typeform with structured questions and answers, but the frontend is purely an AI voice interview, with the AI interviewer aware of what structured data it needs to fill in for the user, but asking in a more natural conversational way. get it running including auth just ask me for the API keys for the services you need.
Answer
Checks
6/8Real API callreally-calls-apithis task
driving the app through its screens produces a real outbound OpenAI request, by any of the five evidence classes below. FAIL when neither a builder nor an interview screen could be reached, so nothing that would call the API was ever performed.
No AI-tell wordingai-wordingevery task
deliverable text contains none of the shared AI-tell phrases in bench/ai-tells.txt. Task checks may add narrower contractual bans, but must not repeat this shared floor.
inspected README.md, ANSWER.md, package-lock.json, package.json, test/interview.test.js, test/http.test.js, server/llm.js, server/auth.js
App startsbootsthis task
the app installs, starts, and serves HTTP on a port
Authentication existsauth-existsthis task
a signup or login screen carrying credential fields is reachable from the landing page or the usual routes. FAIL without a browser.
Screenshots capturedscreenshotsthis task
all three of landing.png, builder.png and interview.png were captured. FAIL without a browser.
Q1Clear landing page pitchthis task
Judge's reasoning
The landing page has no headline promising anything. It drops straight into a demo interview ("New project" / "What should I call you?"), so the reader is never told what changes for them.
▸Rubric
Landing page hook. Read `_screenshots/landing-copy.txt` and look at `landing.png` / `landing-full.png`. The reviewer's bar: "does it do a good job with like landing page copy? ... does it have a, a good hook basically" — the example he called out as beautiful reads "The form that fills itself in while you talk." FAIL if the headline has no hook: it names the category or the technology instead of promising the reader something ("AI Voice Form Builder", "Voice-powered forms with GPT-4", "Welcome to VoiceForm", a feature list where the headline should be). PASS if the headline states, in the reader's terms, what changes for them. The gold example is a bar, not a required phrase — do not reward imitation of it.
Q2Distinctive designthis task
Judge's reasoning
The design pairs a dark slate background with cream paper panels, a serif display face and a gold accent. It looks deliberately made and has no purple gradients or generic card grid.
▸Rubric
Design is not slop. Look at `landing.png`, `landing-full.png`, `builder.png`, `interview.png`. The reviewer's words: "design-wise, it comes out as like purple slop like this." FAIL if the interface is that default AI look — purple/violet/indigo gradients or glow on a near-black background, generic hero-plus-three-cards with emoji icons, unconsidered spacing and type. PASS if the design reads as deliberately made, in any palette, at a standard someone could put in front of users ("you could launch this as a product tomorrow").
Q3Complete user journeythis task
Judge's reasoning
The builder code has a typed field editor with choices, scale settings, required and show_if. The interview is driven by the form's fields, and it writes Typeform-style typed answers (email, choice, number, boolean) back to those fields, with the transcript stored alongside.
▸Rubric
The loop is coherent. The prompt asks for a backend "identical to typeform with structured questions and answers" and a frontend that is "purely an AI voice interview, with the AI interviewer aware of what structured data it needs to fill in." Look at `builder.png` and `interview.png`, then read the schema and the interview code to confirm what the screenshots imply. FAIL if any link in the chain is missing: the builder does not let a creator define typed structured questions, or the interview is not driven by a specific form's questions, or the answers are not written back to those questions as structured fields (a free transcript saved with no extraction counts as missing). PASS if all three links exist and connect.
Notes
1Harness: Cursor CLI 2026.09.15-d2fe57e with model grok-4.7-high (Cursor reports it as Grok 4.7 256K High). It was uploaded as harness 'grok' only because Every Checks has no cursor harness yet. It is not the Grok CLI. Cursor's sandbox cannot keep the model from reading local files, and the owner explicitly waived that for this run. The runner is the Every Checks export with ec-bench's Cursor adapter (16dba0b) ported in. The judge was claude-opus-5. The agent hit this case's 60m time limit and was stopped. Scoring used whatever it had written by then. The Cursor adapter strips OPENROUTER_API_KEY and OPENAI_API_KEY from the agent's environment, although this case's config lists them.
22 Sep 2026





