Project Open to Alpha Team

Multi-Surface Trust Pattern Library — how trust signals travel across web, chat, MCP, and extension

Audit the four Product.ai surfaces (web, chat, MCP, extension) for how each currently signals trust. Then design and ship a pattern library — a small, opinionated set of trust primitives (verdict states, evidence presentation, citation styles, confidence calibration) that travel coherently across all four. Output is a documented system, not a moodboard.

Project Overview

Discipline

Design — Head of Product Design

Duration

2 weeks

Compensation

Your stated freelance rate

Surface

Product.ai · Brand · Consumer experience

Kernels

productai · brand · consumer-experience

Outcomes

multi-surface · brand-entity · chat-expert

Tier

Applied

Alpha Team

Open to alpha members who want to take this on

Tooling

Claude Code or Co-work

Why we want this done

Each surface is governed by different physics. Consumer commerce (SimplyCodes) is conversion physics. Operational dashboards (Cortex) are cognitive-load physics. Agentic interfaces (Alloy) are trust physics. A single craft template can be excellent at one and adequate at another — but cannot be optimal at all three because the optimization functions conflict (Phase 2 Design axiom A6). Today, trust signals on each surface are improvised. A shopper who sees a verdict on chat, then encounters the same merchant on the extension, gets two different visual languages for the same epistemic claim. The pattern library closes that gap. Brand-entity outcome moves; multi-surface outcome moves; chat-expert outcome compounds because trust signals stop being re-invented per surface.

Scope

Surface audit — annotated screen captures of how each of the four surfaces currently signals trust
Identify three to five core trust primitives that recur (verdict, evidence, confidence, citation, escalation are the obvious candidates — accept or reject these from first principles)
Design each primitive in the design system — one component, four surface adaptations, full token discipline
Ship at least one primitive (not all five) into production on at least two surfaces — proves the pattern works under real constraints
Write the pattern library doc — one page per primitive, when to use which, what NOT to do

What success looks like

The audit reveals real inconsistency — not theoretical inconsistency
The primitives chosen are mechanism-distinct; a stranger cannot collapse two of them into one
One primitive ships on two surfaces in production, with code merged
The doc is concrete enough that an engineer extending the pattern to the mobile app does not need to re-ask the designer
The brand team can read the doc and recognize the trust voice as Product.ai's, not as generic AI-product polish

References

references.md

Product.ai kernel — A-1, A-2, A-3 (paradigm constants)
Brand kernel — voice, tone, what verified truth sounds like
Phase 2 Design axiom A6 — Surface-Template Alignment is load-bearing
Phase 2 Design Top-25 axioms section "Surface Templates" (A6-A9)
Existing Product.ai web, chat, MCP, extension surfaces (live)
Linear, Stripe, Anthropic Education Labs as pattern-library references (NOT to copy — to compare against)

Constraints

Claude Code or Co-work as primary substrate
All design tokens, no raw color hex
Must ship one primitive in production on two surfaces — a Figma-only deliverable is rejected
Must read the brand kernel and reconcile the pattern library with it (no orphan visual systems)

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-03-multi-surface-trust-pattern-library/#webpage",
      "name": "Multi-Surface Trust Pattern Library — how trust signals travel across web, chat, MCP, and extension — Product.ai",
      "description": "Audit the four Product.ai surfaces (web, chat, MCP, extension) for how each currently signals trust. Then design and ship a pattern library — a small, opinionated set of trust primitives (verdict states, evidence presentation, citation styles, confidence calibration) that trav...",
      "url": "https://product.ai/join/projects/PRJ-03-multi-surface-trust-pattern-library/",
      "isPartOf": {
        "@id": "https://product.ai/#website"
      },
      "about": {
        "@id": "https://product.ai/#organization"
      },
      "publisher": {
        "@id": "https://product.ai/#organization"
      }
    },
    {
      "@type": "JobPosting",
      "title": "Multi-Surface Trust Pattern Library — how trust signals travel across web, chat, MCP, and extension",
      "description": "Audit the four Product.ai surfaces (web, chat, MCP, extension) for how each currently signals trust. Then design and ship a pattern library — a small, opinionated set of trust primitives (verdict states, evidence presentation, citation styles, confidence calibration) that trav...",
      "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": "Multi-Surface Trust Pattern Library — how trust signals travel across web, chat, MCP, and extension",
          "item": "https://product.ai/join/projects/PRJ-03-multi-surface-trust-pattern-library/"
        }
      ]
    }
  ]
}