cd /news/ai-agents/autoprover-ai-agents-and-formal-meth… · home topics ai-agents article
[ARTICLE · art-95865] src=app.certora.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

AutoProver: AI agents and formal methods for intent, specs, bugs analysis

AutoProver, a new tool from Certora, uses AI agents and formal methods to automatically infer intent from code, generate specifications, and prove the absence of bugs, turning plain-language documentation into formal verification rules. The tool generates tests and proofs from intent, reports code and design bugs automatically, and improves accuracy with each review cycle, with pricing starting at a pay-as-you-go credits model.

read3 min views1 publishedAug 13, 2026
AutoProver: AI agents and formal methods for intent, specs, bugs analysis
Image: source

AutoProver utilises AI agents and formal methods to automatically infer intent from your code, generate specifications, and prove the absence of bugs.

AutoProver turns docs into Formal Verification #

Generate tests and proofs from your intent, surface code and design bugs automatically, and improve the specification set with every review cycle.

Generates tests and proofs from your intent

Reads your docs, formalizes them into properties, converts those into fuzz tests and formal verification rules. No spec writing experience needed.### Reports bugs automatically

Specialized agents execute the tests and rules, handle triaging and troubleshooting, and a dedicated bug-hunting agent looks for unaccounted-for design issues. Results land in a structured report: code bugs, design bugs, property status.### Gets more accurate with every run

Accept or reject findings in plain text. AutoProver updates its understanding of your codebase with each iteration.## How AutoProver works

AutoProver orchestrates a set of AI agents to infer intent, generate specifications, run tests, and report results, with your feedback shaping every iteration.

Problem

Logic bugs go undetected.

The trickiest errors are logical, not syntactic. Manual code review is slow, expensive, and does not scale.

Solution

AutoProver identifies issues in your code and design that traditional testing misses.

Problem

AI agents do not guarantee correctness.

Models improve constantly, but they produce non-deterministic results and have no way to verify intent. Code written with one model can be broken by the next.

Solution

AutoProver infers and formalizes intent, so correctness is not left up to chance.

Problem

Formal verification requires specialists.

Writing specifications is a difficult craft that most development teams do not have in-house.

Solution

AutoProver generates specifications automatically from your existing documentation or a plain-language design doc.

From intent to proof, then back into feedback #

Each run turns plain-language intent into executable verification work, then uses your review to sharpen the next run.

Infer intent

AutoProver reads your existing code documentation or a design doc you write in plain language. No formal specification experience needed to get started.

Generate specifications

Intent is converted into formal properties covering individual modules and cross-module interactions, independent of the implementation.

Produce tests and proofs

Specifications become formal rules via Certora Prover, covering both specific scenarios and edge cases.

Run and triage automatically

Specialized agents execute the tests and rules, handle troubleshooting, and verify that results are sound. A separate bug-hunting agent looks for issues not covered by the design.

Review results

AutoProver delivers a report in three parts: code bugs, design bugs, and full property status with test and rule results for each.

Give feedback and iterate

Accept or reject findings in plain text. AutoProver updates based on your input. Open a PR with the generated tests and rules when you are ready.

Pricing #

Credits-based, pay-per-run. Plans add team seats, discounts, and automation access.

Plan Includes

1 Seat

Team members in your organization

Pay-as-you-go Runs billed from your balance at the standard rate

REST API access

Generate API keys for your custom integrations.

GitHub Action CI integration

One-click CI integration on the repos.

Priority support

Get faster help

Plan Includes

5 Seats

Team members in your organization

10% discount

Every run costs 10% less than the standard rate

REST API access

Generate API keys for your custom integrations.

GitHub Action CI integration

One-click CI integration on the repos.

Priority support

Get faster help

From

Plan Includes

Unlimited Seats

Team members in your organization

Higher Discount

Custom discount - greater than 10%.

2–36 month terms

Monthly committed credits with a fixed minimum term

REST API access

Generate API keys for your custom integrations.

GitHub Action CI integration

One-click CI integration on the repos.

Priority support

Get faster help

As easy to run as a compiler #

A compiler checks that your source code translates correctly to machine code. AutoProver checks that your intent written in plain language translates correctly to what your code actually does.

Available for Solidity. Rust, C, C++, Java, and Go coming soon.

FAQ

── more in #ai-agents 4 stories · sorted by recency
── more on @autoprover 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/autoprover-ai-agents…] indexed:0 read:3min 2026-08-13 ·