Real AI agent use cases, with sources and setup prompts

Have Claude write both a VM and a separate proof generator from the same spec

For a JavaCard VM he had Claude implement the VM from the spec and separately a proof generator from the spec, so a bug would have to exist in both to slip through, and verified them with ESBMC.

See pricing pageweeksAdvancedSource linked

Source

UncleEntity on Hacker News · 2026-10-23

Written in our own words. Credit to the original author. Link checked 2026-10-23.

What they did

For a JavaCard VM he had Claude implement the VM from the spec and separately a proof generator from the spec, so a bug would have to exist in both to slip through, and verified them with ESBMC.

Result (as claimed)

The VM and bytecode verifier are statically verified, and ESBMC itself turned up a few bugs.

Tools they used

ClaudeESBMC

Cost: Pricing depends on the tools you pick; check each official pricing page.

Set it up

  1. Pick a contained repo or task

    Start on a branch or side project where mistakes are cheap.

  2. Install and configure

    Set up Claude, ESBMC. Read what it can run on your machine and limit permissions where possible.

  3. Run it on a real task

    Give it a well-scoped issue and let it work. Review the diff like any pull request.

  4. Add guardrails

    Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Have Claude write both a VM and a separate proof generator from the same spec
What the original author did: For a JavaCard VM he had Claude implement the VM from the spec and separately a proof generator from the spec, so a bug would have to exist in both to slip through, and verified them with ESBMC.
Reported result (as claimed by the author): The VM and bytecode verifier are statically verified, and ESBMC itself turned up a few bugs.
Source: https://news.ycombinator.com/item?id=50203143
Tools they used: Claude, ESBMC
Category: Dev & ops

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Related use cases

Dev & opsHacker News · dnw

Use Claude to map and shrink the attack surface of a codebase

Anthropic's Frontier Red Team had Claude map which code in a deployment is actually reachable, build an inventory of configuration options, then remove or restrict whatever a given deployment does not need to expose, instead of hunting bugs one at a time.

See pricing pageDaysAdvanced
Dev & opsHacker News · murtazayusuf

Build a Redis-compatible database in Rust with Claude as your pair

A developer started KiviDB in February to learn Rust after hitting GC pauses and out-of-memory crashes with Dragonfly at work. He used AI a lot but made the design decisions himself, based on tests Claude picked from his history of troubleshooting sessions. It speaks RESP2 and RESP3, shards the keyspace across threads and uses io_uring on Linux.

See pricing pageWeeksAdvanced