Project Open to Alpha Team

Verification Confidence Indicator — calibrated trust UI across chat, MCP, and extension

A small, generalizable UI component that shows how confident Product.ai is in its own answer, with the evidence trace one click away. Three states: high, medium, low. Ships in production code (React/Next + design tokens), not Figma. Wired into one Product.ai chat answer and one MCP response so a real user can see it in action.

Project Overview

Discipline

Design — Head of Product Design

Duration

2 weeks

Compensation

Your stated freelance rate

Surface

Product.ai · Consumer experience · Truth Graph

Kernels

productai · consumer-experience · truth-graph

Outcomes

chat-expert · full-journey · multi-surface

Tier

Consequential

Alpha Team

Open to alpha members who want to take this on

Tooling

Claude Code or Co-work

Why we want this done

Trust is the load-bearing physics for verified-truth commerce. The Trust Paradox is real: 74% of users rate verified-truth assistants 4-5 out of 5 on trust and 93% verify before acting. Stated trust is rhetorical; behavioral verification is the only signal that matters. The VCI is the surface where that gap closes — calibrated confidence visible at the point of decision, evidence one click away. Without it, our trust claim is marketing copy. With it, our chat, MCP, and extension surfaces start carrying the same confidence semantics, which is the prerequisite for the multi-surface coherence the productai kernel demands.

Scope

Design and ship the VCI component:

Three confidence states — visual treatment, copy, when each applies
Evidence-trace expansion behavior (one click reveals the citation chain)
Production component in the Product.ai design system, fully tokenized
Wired into one shipped chat answer (live in Product.ai web) and one shipped MCP response
One-page handoff doc explaining states, when to use which, and how engineering installs it elsewhere

What success looks like

A stranger can verify all of these in fifteen minutes:

The VCI component renders in the Product.ai design system (Storybook or equivalent)
A real Product.ai chat answer shows it; the click expands to the evidence trace
An MCP response carries it in the JSON payload (machine-readable confidence + evidence)
An engineer who has never seen the component can install it on a third surface from the handoff doc alone
The candidate's commits are merged to main, not parked on a feature branch

References

references.md

Trust Paradox data: 74% rate trust 4-5/5; 93% verify before acting
Anthropic Claude Code April 23, 2026 postmortem — eval theater fails; user /feedback catches what eval suites miss
Karri Saarinen, "Output Isn't Design" (April 2026)
Phase 2 Design briefing axiom A3 — Generation Cost Collapsed; Verification Cost Did Not
Product.ai kernel A-1 (Beige Singularity) and A-2 (Three Knowledge Domains)
Truth-Graph kernel — confidence tiers and evidence-trace primitives
Existing Product.ai chat surface and MCP server endpoints

Constraints

Claude Code or Claude Co-work as primary AI substrate; Figma allowed for visual exploration
Component must use design tokens (no hardcoded hex, no rgba whites — see aios/dashboard/CLAUDE.md color rules)
12px minimum font size on all body text; 11px acceptable only for uppercase metadata labels
Must work on the three surfaces independently — no shared global state assumptions
Code-merge rights to the relevant Product.ai surface required (driver §6.1, §8 IP separation honored)
IP separation: no access to aios-methods repo; the VCI does not require methodology

Apply

Read the Codex (10 min)

The operating principles we work by. If they resonate, the rest of this will land. Open the Codex →

12-minute video screen

Hireflix, async. Questions are calibrated to this project specifically.

Chemistry call (30-60 min)

Direct call with the CEO. Strategic alignment and mutual fit. No problem-solving exercise.

Project begins within 2-3 weeks

1099 contractor agreement, NDA, paid at your stated rate. Day 1 in Santa Monica.

Alpha Team members can take this project without the screen-and-call sequence. Reach out via the Alpha Team channel.

Apply for this trial Browse other projects

Agent View · application/ld+json

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@id": "https://product.ai/#organization"
    },
    {
      "@type": "SoftwareApplication",
      "@id": "https://product.ai/#application",
      "name": "Product.ai",
      "slogan": "Intelligent guidance at conversation speed",
      "description": "Product.ai is your AI shopping expert - verified product intelligence grounded in the Truth Graph, accessible to agents and humans alike.",
      "applicationCategory": "ShoppingApplication",
      "operatingSystem": "Web",
      "author": {
        "@id": "https://product.ai/#organization"
      },
      "offers": {
        "@type": "Offer",
        "price": "0",
        "priceCurrency": "USD"
      }
    },
    {
      "@type": "WebPage",
      "@id": "https://product.ai/join/projects/PRJ-01-verification-confidence-indicator/#webpage",
      "name": "Verification Confidence Indicator — calibrated trust UI across chat, MCP, and extension — Product.ai",
      "description": "A small, generalizable UI component that shows how confident Product.ai is in its own answer, with the evidence trace one click away. Three states: high, medium, low. Ships in production code (React/Next + design tokens), not Figma. Wired into one Product.ai chat answer and on...",
      "url": "https://product.ai/join/projects/PRJ-01-verification-confidence-indicator/",
      "isPartOf": {
        "@id": "https://product.ai/#website"
      },
      "about": {
        "@id": "https://product.ai/#organization"
      },
      "publisher": {
        "@id": "https://product.ai/#organization"
      }
    },
    {
      "@type": "JobPosting",
      "title": "Verification Confidence Indicator — calibrated trust UI across chat, MCP, and extension",
      "description": "A small, generalizable UI component that shows how confident Product.ai is in its own answer, with the evidence trace one click away. Three states: high, medium, low. Ships in production code (React/Next + design tokens), not Figma. Wired into one Product.ai chat answer and on...",
      "hiringOrganization": {
        "@id": "https://product.ai/#organization"
      },
      "employmentType": "CONTRACTOR",
      "datePosted": "2026-04-28",
      "jobLocation": {
        "@type": "Place",
        "address": {
          "@type": "PostalAddress",
          "addressLocality": "Los Angeles",
          "addressRegion": "CA",
          "addressCountry": "US"
        }
      },
      "baseSalary": {
        "@type": "MonetaryAmount",
        "currency": "USD",
        "value": {
          "@type": "QuantitativeValue",
          "unitText": "WEEK"
        }
      },
      "workHours": "2 weeks"
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Product.ai",
          "item": "https://product.ai"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Join",
          "item": "https://product.ai/join/"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Projects",
          "item": "https://product.ai/join/projects/"
        },
        {
          "@type": "ListItem",
          "position": 4,
          "name": "Verification Confidence Indicator — calibrated trust UI across chat, MCP, and extension",
          "item": "https://product.ai/join/projects/PRJ-01-verification-confidence-indicator/"
        }
      ]
    }
  ]
}