How do you solve the trust problem with AI-generated code?
@MSFTResearch557K followers
21,201 views
14 Comments
Comments from the original post on X (Twitter)

@raulnogales
The trust problem is not that agents write bad code. It is that they write plausible code at a scale no human can review line by line. The fix is not more review. It is tests, constraints and code the agent can prove, not just produce.
3 likes

@mktpavlenko
Proof moves the review from the code to the Verus spec. Fewer lines to read, but each one now carries the whole intent.
2 likes

@razaaitech
Formal verification could be the missing trust layer for AI-generated code. Proving correctness beats simply hoping for it!
1 like

@opendocyai
At that scale, review has to move from reading every line to checking evidence: tests passed, rules satisfied, and a named person accountable for what ships. Reviewers verify the record, not the whole output.
1 like

@KrrishKapoor8
do the unproven parts still merge, or get blocked?
1 like

@identArk
A coding agent may give correct answer based on failed reasoning, how does PDD kit handle this reasoning failure

@cheneypiano
When agents generate more code than anyone can review line-by-line, what's the review gate you're trusting instead?

@Toby___l
@bot 介绍一下这个

@AmeliaonAI
Proofs checking agent code could finally build real trust

@CodeParticle
The part worth copying even without formal methods: mark where verification can't reach. Review of agent code tends to fail quietly at exactly that boundary. A spec that labels its own unverified edges tells the reviewer where to spend the hour.

@PRaSeN_S
That list of unproven parts could go straight onto the pull request, so a security reviewer spends their time there and a named person signs off before merge. Does the kit output it in a form a CI check can read?

@ddyods
Yes ! Reading every line does not scale. What I do is lock an expect.yml before the agent starts, then a script checks the real diff against it.

@RemoteBrewser
The scale problem is real, but line-by-line review was never the only gate. For agent-generated code, the leverage is in executable checks: tests the agent must pass, plus actually running the output in a sandbox and watching behavior. Reviewing intent beats reviewing diffs.

@VeyraWithAI
Proofs over vibes is exactly what agentic code needs

