nowfound

AI · June 23, 2026

ForgePilot

AI workspace for FMEA, tolerance analysis & engineering Q&A

ForgePilot launched on June 23, 2026 with 2 votes.

What it does

Most engineering teams run FMEA in a spreadsheet that's two revisions behind by the time the product ships. Tolerance stack-up gets done in Excel the week before manufacturing. Engineering Q&A lives in email threads. ForgePilot fixes all three — FMEA generation from design inputs, instant worst-case and RSS tolerance analysis, and engineering Q&A built on domain knowledge. Not a generic AI. Purpose-built for engineers by an engineer who lived this problem across 5 product lines. Free.

AI workspace for mechanical engineers: FMEA generation, tolerance stack-up, GD&T drawing review, and standards compliance, all in one place with verifiable math.

Stop rebuilding your engineering analysis in a spreadsheet every revision. FMEA, tolerance stack-ups, GD&T drawing review, and standards compliance, all done by AI and versioned to the exact file it ran against, not scattered across four different tools. Solo or with your whole team. Works with whatever CAD you already export from, SolidWorks, Fusion 360, CATIA, NX, or none of the above. No plugin to install, no seat license, no IT procurement. Upload the file, get the analysis. AR 14 flutter onset ≈ 23 m/s, below cruise. Design-limiting. Not a weight issue, an aeroelastic one. L/D: +18% at AR 10 vs AR 8. Root bending moment: 2.4× at AR 12. Spar mass penalty: +340 g per AR unit above 10. AR…from forgepilot.dev

Does a similar job

all alternatives →
  • Forge – Guardrails take an 8B model from 53% to 99% on agentic tasksMay 2026 · github.com · ▲687

    Hi HN, I'm Antoine Zambelli, AI Director at Texas Instruments. I built Forge, an open-source reliability layer for self-hosted LLM tool-calling. What it does: - Adds domain-and-tool-agnostic guardrails (retry nudges, step enforcement, error recovery, VRAM-aware context management) to local models running on consumer hardware - Takes an 8B model from ~53% to ~99% on multi-step agentic workflows without changing the model - just the system around it - Ships with an eval harness and interactive dashboard so you can reproduce every number I wanted to run a handful of always-on agentic systems…

  • DevpilotNov 2025 · devpilot.com · ▲112

    The AI co-pilot for your entire development lifecycle.

  • Nearshore: AI for manufacturingNov 2025 · nearshored.ai · ▲11

    Use AI to create an RFQ & get matched with local factories

  • Spec27Apr 2026 · spec27.ai · ▲34

    Hi HN! We’re a team of ML validation specialists and we’ve been building /Spec27, a tool for testing whether AI agents still do their job safely and reliably as models, prompts, tools, and surrounding systems change. We started working on this because a lot of current LLM evaluation work seems aimed at scoring general model behavior, while many teams are deploying systems that have a specific mission to fulfill. Many of the tools also assume you have full access to the agent stack and traces so you can place SDKs and Gateways, but a lot of agents are being created on vendor platforms…

  • devtimate2024 · devtimate.com · ▲25

    Hey HN! I am a FE dev who is working at a software agency and im making 2-3 estimates per week. Creating estimates is painfull manual proccess, where you have to read a lot of .docx like RFP, SRS etc. This was really tiring for me Also in agency where im working we make estimates in google spreadsheets which is another pain, trying to drag something, copy, duplicate can really mess up the whole layout So i just wanted tool that can just automate this a bit. I just started researching and I couldnt find anything good enough for my usecase. So I made a tool for creating estimates with AI. I…

  • RFPilot 2025 · ▲7

    Escape Email Chaos: Store, Analyze, and Seal Deals Faster.

More ai this month

the category →
  • Video model that turns script into viral social media videos

    AI · 19d ago · spira.ai

  • The browser where Claude Code and Codex work beside you

    AI · 19d ago · rill.love

  • Kolibri is Aleph Alpha

    AI · 21d ago · tej.as

  • Paintings by AI models: programs run through a simulation of oil paint.

    AI · 22d ago · stillwet.art

  • Beam.win▲379

    Run AI agents on one Mac and use its windows on another

    AI · 6d ago · beam.win

  • Route requests to the right LLM for cost, latency & quality

    AI · 23d ago · fastrouter.ai

Source: Product Hunt launch ↗

Launched alongside, June 2026

the whole month →
  • Fundraisly▲1,537

    AI fundraising agent that finds investors and books meetings

    AI · Jun 2026 · fundraisly.com

  • Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!

    Dev tools · Jun 2026 · brew.sh

  • Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!

    Life & fun · Jun 2026 · vorpus.github.io

  • Upstream▲976

    The inbox designed for humans and agents

    AI · Jun 2026 · upstream.do

  • Goldfish▲958

    Press Option. It knows your work and replies like you

    AI · Jun 2026 · goldfish.sh

  • Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.

    Life & fun · Jun 2026 · hackernewstrends.com