🗣️ Post 1: Show HN: Gensee – Free AI Agent Optimization and Deployment

As posted by: yiyingzhang  |  🔥 Points: 11

https://platform.gensee.ai

💬 Summary

I'm the co-founder of GenseeAI (https://www.gensee.ai). We've recently launched the public beta of Gensee, an AI agent/workflow platform oriented for developers and small teams.

Here’s what I’ve heard again and again: it's gotten much easier to build a proof-of-concept AI agent, but turning that prototype into a high-quality, scalable, and cost-effective product is still a massive chore, involving endless trial-and-error with prompts, models, tools, testing, analysis, etc.

We built Gensee to automate that "last mile" from prototype to production.

Here’s how it works:

- You provide the GitHub link to your project, a Docker image, or a Zipped package of your agent source to Gensee. They can be written in any framework or without a framework, as long as it’s in Python. No code modification or annotation needed.

- We handle input/output identification, model/tool call identification, test case generation, metrics generation, testing, automated optimization, server provisioning, containerization, tool/model calling, and endpoint creation to get it live as an API.

- You see detailed evaluation results with customized metrics and test cases, all fully automated.

- We optimize your agent automatically to achieve better quality, cost, and/or latency. You can download our optimized agent code, all transparent.

- You can choose any optimized or original agent configurations to serve. Simply copy the API endpoint to your frontend code calling the agent.

To support fellow developers, we give every new user 500 free monthly credits, enough to cover one to two agent deployment, optimization, and initial model and tool usage costs. If your usage grows, it becomes a cost-efficient pay-as-you-go service that scales with you.

We're still in beta and would love to get your feedback. Do you prefer no-code agent generation instead of source code uploading? Should Gensee also run your frontend and other code in addition to agents? Any other optimization goals you have? Any key missing features?

Thanks for taking a look!

Access Gensee: https://platform.gensee.ai

🗣️ Post 2: Show HN: Transform static presentations → dynamic AI-guided experiences

As posted by: ajabhish  |  🔥 Points: 2

https://app.toughtongueai.com/library/product-design-interview-tips-5-strategies-688bb9ca8021d1a72a3d25fa/

💬 Summary

Demo: https://youtu.be/W4uBOTf9KtY

Today we’re rolling out beta access to our AI agent that talks to Google Slides. - Ask a question → it jumps to the right slide - Need a diagram? → “Show slide 3” - Want to rewind? → “Go back two slides”

This can be a game changer for teaching new concepts, employee training (onboarding, explaining playbooks etc) ...

Our agent now has capability to display and navigate Google Slides based on conversation flow, creating truly interactive learning experiences.

Setup in 3 steps: 1⃣ Get the embed URL from Google Slides (File → Share → Publish to web → Embed) 2⃣ Enable the tool in scenario settings and paste the URL 3⃣ Add slide instructions to your AI prompt (e.g., “Show slide 3 for the architecture diagram”)

Create your own: https://app.toughtongueai.com/advanced-scenario-create/

Try the one I used: https://app.toughtongueai.com/run/paris-tough-tongue-ai-pitc...

Or the one that teaches: https://app.toughtongueai.com/library/product-design-intervi...

🗣️ Post 3: A prompt to improve SEO for Vibe-coded/AI-coded sites

As posted by: grahac  |  🔥 Points: 2

https://github.com/RivalSee/ai-seo-tools

💬 Summary

AI SEO Tools by RivalSee This is an open-source collection of tools and prompts to help developers identify and fix SEO issues in modern web applications, with a focus on AI-driven SEO optimization. It is provided by RivalSee, a leading AI search visibility platform that monitors and boosts your brands' mentions in ChatGPT, Claude, and Google AI. The Problem: Vibe-Coded Sites and AI SEO Modern web applications built with AI coding tools are prioritizing speed to develop and deploy and visual appeal over search engine optimization fundamentals, creating significant challenges: Client-side API calls : Content for many vibe-coding tools is fetched from the client using Supabase, Firebase, or other APIs after page load : Content for many vibe-coding tools is...

🗣️ Post 4: AI Risk Assessment Tool

As posted by: Yaelita  |  🔥 Points: 2

https://www.prompt.security/ai-risk-assessment-tool

💬 Summary

Get to know more about our team and mission

🗣️ Post 5: Free evals API for AI startups (ship 10x faster with evals you can trust)

As posted by: sfox100  |  🔥 Points: 2

https://news.ycombinator.com/item?id=44744510

💬 Summary

Hey HN,

We built Composo because AI apps fail unpredictably and teams have no idea if their changes helped.

LLM-as-judge doesn't work - it gives random scores, doesn't work well for agents, and doesn't tell you what to fix.

We've built purpose-built evaluation models that give you: - Deterministic scores (same input = same score, always) - Instant identification of where prompts, retrievals, agents & tool calls fail - Exact failure analysis ("tool calls are looping due to poorly specified schema")

We're 92% accurate vs 72% for SOTA LLM-as-judge.

Giving 10 startups free access: - 10k eval credits - Just launched our evals API for agents & tool calling - 5 min setup

Already helping teams at Palantir, Accenture, and Tesla ship reliable AI.

Apply: composo.short.gy/startups

Happy to answer questions about evaluation, reward models, or why LLMs are bad at judging themselves. startups@composo.ai

🎯 Final Takeaways

These discussions reveal how developers think about emerging AI trends, tool usage, and practical innovation. Take inspiration from these community insights to level up your own development or prompt workflows.