ProofShot – Give AI coding agents eyes to verify the UI they build
I use AI agents to build UI features daily. The thing that kept annoying me: the agent writes code but never sees what it actually looks like in the browser. It can’t tell if the layout is broken or if the console is throwing errors.So I built a CLI that lets the agent open a browser, interact with the page, record what happens, and collect any errors. Then it bundles everything — video, screenshots, logs — into a self-contained HTML file I can review in seconds. proofshot start --run "npm run dev" --port 3000 # agent navigates, clicks, takes screenshots proofshot stop It works with whatever agent you use (Claude Code, Cursor, Codex, etc.) — it’s just shell commands. It's packaged as a skill so your AI coding agent knows exactly how it works. It's built on agent-browser from Vercel Labs which is far better and faster than Playwright MCP.It’s not a testing framework. The agent doesn’t decide pass/fail. It just gives me the evidence so I don’t have to open the browser myself every time.Open source and completely free.Website: https://proofshot.argil.io/
FL score
out of 100
Verdict
high confidence
Competition
10
competitors found, emerging market, funded players
Trend
No signal yet
A clever open-source CLI tool providing visual feedback for AI coding agents, solving a real developer pain point, but lacking a clear path to monetization.
The pain
The gap
Build angle
Strengths
- Addresses a specific, daily pain point for a growing audience of AI-assisted developers.
- Unique value proposition as an agent 'skill' providing observation, not automated testing.
- Leverages powerful underlying technology (Vercel's agent-browser).
- Open-source and free nature directly addresses common complaints about competitor pricing.
- Simple CLI interface ensures broad compatibility with various AI agents.
- Strong initial validation of the problem from Hacker News launch.
Risks
- The 'open source and completely free' model means zero direct revenue, making it unsustainable as a micro-SaaS.
- Requires a clear monetization strategy to transition from a project to a business.
- Market is crowded with funded visual testing tools, even if ProofShot's angle is different.
- Reliance on Vercel's agent-browser means some external dependency risk.
- Future competition from other open-source projects or big tech integrating similar features directly into their AI agent platforms.
Next steps
- Poll current users of ProofShot and AI agents: 'What paid problem would you solve related to AI visual verification?'
- Explore potential monetization models: enterprise features (e.g., team dashboards, advanced reporting, API for integrations), hosted cloud service, premium plugins, or commercial licenses for specific use cases.
- Validate demand for a paid tier or complementary service by offering a hypothetical 'Pro' version to gauge interest and willingness to pay.
- Continue building community around the open-source tool to establish authority and gather insights for potential paid offerings.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 25
- Solution gap
- 20
- Willingness to pay
- 10
- Buildability
- 12
A highly relevant tool for AI-assisted UI development, addressing a clear pain point with a clever technical angle and competitive differentiation. However, the 'open source and completely free' model fundamentally limits its business viability as a micro-SaaS.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
High value proposition and market timing, but the 'open source and free' model completely undermines its viability as a profit-generating venture under the Hormozi lens.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Excellent problem clarity, creator fit, and a strong niche, but completely fails on monetization due to its free, open-source nature, making it unsustainable for a solo builder.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Clear value and target audience with good early validation of the problem, but fundamentally lacks a viable business model as a free, open-source tool, creating significant risk for micro-SaaS.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Addresses a clear, growing pain point for developers using AI, with a simple, effective solution that leverages existing tools, but future growth for a *company* requires a monetization path beyond being free.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- Poll current users of ProofShot and AI agents: 'What paid problem would you solve related to AI visual verification?'
- Explore potential monetization models: enterprise features (e.g., team dashboards, advanced reporting, API for integrations), hosted cloud service, premium plugins, or commercial licenses for specific use cases.
- Validate demand for a paid tier or complementary service by offering a hypothetical 'Pro' version to gauge interest and willingness to pay.
- Continue building community around the open-source tool to establish authority and gather insights for potential paid offerings.
Who is already there, emerging market
Applitools is an AI-powered visual testing platform that detects visual discrepancies in software applications by comparing screenshots to baseline images.
Pricing: Not explicitly stated, but alternatives mention high subscription costs.
Percy is an AI-powered visual testing platform that automates visual regression testing for web applications, integrating with CI/CD pipelines.
Pricing: Comparable plans to Chromatic can cost around $549/month when billed monthly.
- ChromaticVisit
Chromatic is a visual regression and UI review platform built around Storybook, automatically snapshotting components and highlighting visual changes.
Pricing: Free for open-source projects, with paid plans for private repos based on snapshot count. A plan comparable to Percy costs less, at $4,440 less per year for more snapshots.
- Lost PixelVisit
Lost Pixel is an open-source visual regression testing tool that integrates with GitHub to catch visual bugs across Storybook, Next.js, and Playwright tests.
Pricing: Free in open-source mode, with a focus on offering better pricing for their platform.
Happo is a cross-browser visual regression testing tool focused on CI integration and speed, taking screenshots across real browsers.
Pricing: Not explicitly stated in search results, but it's a paid tool.
- TestSpriteVisit
TestSprite is an autonomous AI testing agent purpose-built for AI-driven development, automating the validation loop for UIs and E2E tests.
Pricing: Not explicitly stated on the website, offers a free download and community discord.
Testsigma is a no-code, AI-powered test automation platform supporting visual regression testing alongside functional, API, and cross-browser tests for web and mobile apps.
Pricing: Not explicitly stated, but offers a cloud-based platform.
Mabl is a low-code, AI-driven test automation platform for web, mobile, and API testing with features like auto-healing to adapt to UI changes.
Pricing: Not explicitly stated, but generally positioned for enterprise-scale testing, so potentially higher cost for smaller teams.
Testim (now part of Tricentis) leverages machine learning to accelerate authoring and maintenance of UI tests with self-healing capabilities.
Pricing: Not explicitly stated, but offers paid plans.
- AskUIVisit
AskUI uses a Vision Agent that interacts with applications at a pixel-level, visually identifying and clicking UI elements to make tests more resilient across platforms.
Pricing: Not explicitly stated, but offers a platform with different features.
What they charge
Recent news
Show HN: ProofShot – Give AI coding agents eyes to verify the UI they build
Hacker News, March 24 2026
deepidv: AI-native verifications & checks at 10x less cost
Product Hunt, March 13 2026
The best AI code testing in 2026
Product Hunt, March 18 2026
Uxia: Validate your User flows UX & UI in seconds with AI
Product Hunt, Not specified, but listed as similar to other products launched around early 2023.
Checkman: The best tool for UI/UX Designers to verify mobile app UI
Product Hunt, Not specified, but listed as a tool for UI/UX Designers.
Market signals
The market for AI-powered UI verification is growing and is becoming a significant area within the broader software testing industry. Recent activity shows a clear trend towards AI agents that can not only write code but also visually validate the UI, moving beyond traditional pixel-level comparisons to more intelligent, human-like understanding of visual changes. This is evidenced by numerous established testing platforms integrating AI for visual regression and new startups emerging with AI-native solutions.
What frustrates people
- Traditional pixel-perfect comparison tools often flag font rendering, anti-aliasing, and dynamic content as false positives, leading to review fatigue.
- High subscription costs and strict snapshot limits from established visual testing tools like Percy are a common complaint.
- The need for additional tools for functional testing when using primarily visual regression tools like Applitools.
- Difficulty in setting up and maintaining visual testing infrastructure for open-source solutions.
- Lack of deep Storybook integration in some visual testing tools, requiring extra setup.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “ProofShot – Give AI coding agents eyes to verify the UI they build”.