Tiden verifies your coding agents built what you actually asked for. Most checks run inside the session that wrote the code, so the tests agree with it by construction. Tiden keeps your intent as requirements that branch and merge like code, and checks every change against that record. The verdict comes from tests run in your environment; no model grades the diff. You decide what merges, and production errors trace back to the release. Works beside Claude Code, Cursor, Codex and Copilot.
Hi Product Hunt, I'm Nikita, and this is Tiden, the product we've been building for the past year. It's for engineering teams shipping agent-written code every day who want to let agents do the coding while keeping control of what ships.
Qase is a software testing platform used by tens of thousands of builders, and 9 years of building it for them taught us a lot about how quality work gets done. Last year that changed on our own team: agents started producing most of the code, and the rest of our process didn't speed up with it. Review, testing, release, keeping requirements current: all of it became bottlenecks.
Other engineering teams tell the same story. A gaming publisher I talked to, with about 1k+ developers, saw pull request volume go up 4 to 5 times while the number of features they shipped stayed flat. A payments company described 10 times the coding output and 10% more delivery.
The problem underneath it
An agent session produces the code, the tests that pass on that code, and the docs describing what it built. The next session reads those docs as fact. Every artifact agrees with every other one, because they all came from the same place. A QA automation lead at a tax and accounting platform put it best: "If you have an agent that decides what to build, and then another agent is grading what's being built against what was actually built, you're essentially encoding the wrong thing. Your tests will pass, they'll be green, but it wasn’t what you wanted."
The two usual fixes, another rules file in the repo and better AI code review, both sit inside that same loop. The judge has to sit outside it.
What Tiden does
Tiden is that judge. It's intent verification for coding agents: it sits beside your agents, whichever ones you use, and verifies that what they built is what you actually asked for. It keeps that intent as specs, versioned like code, and checks every change against them rather than against the session that produced it.
Every agent session becomes a closed loop:
A session hook captures what you asked for before the first edit
The change comes back as a requirement for you to review; requirements branch and merge like code
Tiden picks the tests the change touches, runs them in your environment, and the agent fixes what fails before anything merges
The gate is tied to the spec. Red tells the agent what to fix. Green is a pass you can defend, with the evidence attached
In production, an error traces back to the release, the change and the prompt behind it, and the fix comes with the test that was missing
Tiden works beside Claude Code, Cursor, Codex and Copilot, and belongs to none of them. Specs live as one versioned record every agent reads from, instead of a growing pile of markdown. You set the thresholds and the gates, and a person approves anything the loop can't settle.
One limit, stated plainly: Tiden checks the work against what you asked for. Whether you asked for the right thing is still a human judgment.
Get started
Tiden is live at https://tiden.ai. The CLI installs in one command, the docs are at https://docs.tiden.ai, and Starter and Team both come with a 14-day free trial. If you'd rather talk to us first, there's a short form on the site: https://tiden.ai/contact.
What I'd like from you
Honest feedback over upvotes. Where does your team feel this gap most: review, regression, release, or production? What would make you trust an external check?
Nikita and the team were shipping exciting features and products before, this one is a gem 💎
Love how Tiden is addressing the gap where AI coding assistants and agents can generate 1000s of lines of code in seconds, but it’s very difficult to validate the quality of that code, especially at enterprise scale. Tiden with Claude looks like a killer combination.
Can I use it without tests?
I just want to keep specs somewhere and use them across many repositories.
Hey 👋 Another engineer from Tiden is here, too!
It's a really interesting experience to use Tiden to build Tiden. I think it could be interesting for other people too!
At first, changing so many domains at once seemed risky to me, but with Tiden, the process went smoothly.
Tiden helps track every detail and edge case while your product keeps changing, especially over the long term.
I believe you should give it a try!
The real challenge with AI coding is not writing code faster but it’s making sure the code actually does what you intended.
Does this work if the team never wrote requirements in the first place? Most of our "spec" lives in tickets and people's heads
When Tiden flags a requirement as untested, what stops the agent from writing a shallow test just to turn it green?
Joined the Tiden team not from the very beginning, so there already was a lot of functionality, taken decisions and other things that make me nervous when I join new teams. Especially in this AI era, where even the most frontier model might want to shape the reality around itself in order to finish its job.
But building Tiden while using Tiden makes me worry much much less, I know Tiden will force my agent to take into account previous decisions and existing specs and no adjacent features will be broken because of that.
Engineer on the Tiden team here. My favourite bugs from building it were in our own gate, because they all had the same shape: it was too easy to pass.
Two of them:
A change that touched no known requirement passed. Nothing matched, so there was nothing to check, and "nothing to check" counted as green. Now it's a refusal, and accepting that risk is an explicit decision.
A requirement counted as verified on someone else's green run. Now only results from the change's own runs count.
Same lesson both times: a verifier is worth exactly as much as it is hard to fool. We build Tiden with Tiden, so we hit these ourselves first.
What's the sneakiest way your CI went green without really checking anything?
Great launch! With agents writing most of the code, keeping up with quality is becoming the real bottleneck. Specs that branch and merge like code is a smart touch
I do believe that no model grading is the right call. Our evals had deterministic routing tests before it could ship. That split is what kept people trusting it. How so you handle cases where deterministic tests aren't enough, like "this should feel fast"
Hi Product Hunt Community,
I am Nitin, and I am product manager for Tiden. Today, after six months of building, we are finally sharing it with you.
Here is the problem in one line: your agents are fast, but your delivery is not.
Coding agents can write a change in minutes. Yet that same change often takes days to reach production. The PR waits because nobody is sure what else it touches. CI catches a regression on the second push. A reviewer spots a function the agent invented. The code got faster. The delivery did not.
The data backs this up. In Stack Overflow's 2025 Developer Survey, trust in AI accuracy fell to 29%, and 66% of developers said they spend more time fixing "almost right" code. Faros AI found that teams with high AI adoption merge 98% more PRs, while review time rises 91%. Google's DORA research put it simply: AI amplifies what is already there.
The market's answer so far has been a point AI tool for every phase: one for context, one for tests, one for PR review, one for release signals. They are faster cars on old roads. The lifecycle underneath was designed for humans who read specs and follow instructions. Agents sometimes do, sometimes do not, and sometimes invent things that were never there. Throwing more AI at the problems AI creates is not a solution. It is an illusion.
So we started from a blank slate. Tiden is a continuous verification system for agentic coding teams, built around one idea: an enforceable boundary.
Here is how it works:
1. Before a single line of code: Tiden builds a context graph of your system, linking features, requirements, tests and components. When a change comes in, the agent walks that map, finds what is affected and fills the gaps. The result is captured as intent, and that intent becomes the boundary the code must deliver against.
2. Clear context, not all the context: the coding agent gets exactly what is relevant, so it ships in fewer iterations and gets it right more often.
3. Before the PR, not after it: Tiden picks the functional and regression tests that matter for this change, based on requirements and risk, and runs them before a PR exists. Only when that quality gate passes can the agent open the PR.
4. After the merge: release evidence is assembled automatically, and production issues are tracked, feeding the next change.
In our own use, cycle time from starting a change to releasing it came down by almost half. Not because code was written faster, but because the most of rework loops simply stopped happening.
Tiden is built by the team behind Qase, so almost a decade of quality assurance thinking has gone into how verification should work when agents write the code.
We would love your honest feedback:
- Where does your agentic workflow break down today?
- What would you need to trust an agent's change without reading every line?
- What is missing?
You can start a 14-day trial at tiden.ai. I will be here all day answering questions.
Agents build. Tiden verifies. Your team decides.
How easy is it to add Tiden to an existing project that's already using Cursor or Claude Code?
The ability to trace production errors back to a release is a useful addition. It could make debugging much less frustrating.
Can Tiden catch cases where the code passes all tests but still doesn't match what the user asked for?
I like that the final verdict comes from actual tests instead of an AI judging the code. That feels more reliable.
Keeping requirements updated alongside code changes sounds useful. It could help teams catch things that get missed development.
A green test suite can still be answering the wrong question. I like that Tiden keeps the request as a separate record for checking what ships.
About Tiden on Product Hunt
“Intent verification for coding agents”
Tiden launched on Product Hunt on October 14th, 2026 and earned 161 upvotes and 33 comments, placing #6 on the daily leaderboard. Tiden verifies your coding agents built what you actually asked for. Most checks run inside the session that wrote the code, so the tests agree with it by construction. Tiden keeps your intent as requirements that branch and merge like code, and checks every change against that record. The verdict comes from tests run in your environment; no model grades the diff. You decide what merges, and production errors trace back to the release. Works beside Claude Code, Cursor, Codex and Copilot.
Tiden was featured in Software Engineering (43.2k followers), Developer Tools (521.1k followers) and Artificial Intelligence (481k followers) on Product Hunt. Together, these topics include over 224.9k products, making this a competitive space to launch in.
Who hunted Tiden?
Tiden was hunted by Zac Zuo. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Tiden stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Zac Zuo
Hi Product Hunt, I'm Nikita, and this is Tiden, the product we've been building for the past year. It's for engineering teams shipping agent-written code every day who want to let agents do the coding while keeping control of what ships.
Qase is a software testing platform used by tens of thousands of builders, and 9 years of building it for them taught us a lot about how quality work gets done. Last year that changed on our own team: agents started producing most of the code, and the rest of our process didn't speed up with it. Review, testing, release, keeping requirements current: all of it became bottlenecks.
Other engineering teams tell the same story. A gaming publisher I talked to, with about 1k+ developers, saw pull request volume go up 4 to 5 times while the number of features they shipped stayed flat. A payments company described 10 times the coding output and 10% more delivery.
The problem underneath it
An agent session produces the code, the tests that pass on that code, and the docs describing what it built. The next session reads those docs as fact. Every artifact agrees with every other one, because they all came from the same place. A QA automation lead at a tax and accounting platform put it best: "If you have an agent that decides what to build, and then another agent is grading what's being built against what was actually built, you're essentially encoding the wrong thing. Your tests will pass, they'll be green, but it wasn’t what you wanted."
The two usual fixes, another rules file in the repo and better AI code review, both sit inside that same loop. The judge has to sit outside it.
What Tiden does
Tiden is that judge. It's intent verification for coding agents: it sits beside your agents, whichever ones you use, and verifies that what they built is what you actually asked for. It keeps that intent as specs, versioned like code, and checks every change against them rather than against the session that produced it.
Every agent session becomes a closed loop:
A session hook captures what you asked for before the first edit
The change comes back as a requirement for you to review; requirements branch and merge like code
Tiden picks the tests the change touches, runs them in your environment, and the agent fixes what fails before anything merges
The gate is tied to the spec. Red tells the agent what to fix. Green is a pass you can defend, with the evidence attached
In production, an error traces back to the release, the change and the prompt behind it, and the fix comes with the test that was missing
Tiden works beside Claude Code, Cursor, Codex and Copilot, and belongs to none of them. Specs live as one versioned record every agent reads from, instead of a growing pile of markdown. You set the thresholds and the gates, and a person approves anything the loop can't settle.
One limit, stated plainly: Tiden checks the work against what you asked for. Whether you asked for the right thing is still a human judgment.
Get started
Tiden is live at https://tiden.ai. The CLI installs in one command, the docs are at https://docs.tiden.ai, and Starter and Team both come with a 14-day free trial. If you'd rather talk to us first, there's a short form on the site: https://tiden.ai/contact.
What I'd like from you
Honest feedback over upvotes. Where does your team feel this gap most: review, regression, release, or production? What would make you trust an external check?