Starter
$49per month1 product, up to 3 repositories, 25 verified changes per month, unlimited developers and agents, intent capture, generated tests, quality gate and error tracking. 14-day free trial. Official source 1 ↗
Website-checked tool profile
Tiden
Verify that code from your AI coding agents does what you asked, with versioned specs, linked tests and a quality gate on every merge.
Sources checked
- Pricing
- Paid plans with a 14-day free trial: Starter is $49 a month for one product, up to 3 repositories and 25 verified changes; Team is $199 per product per month with 100 verified changes per product, then $2.00 per extra change falling to $1.00 past 1,000; Enterprise is custom. Every plan includes unlimited developers and agents, and annual billing cuts product fees by 20%. Official source 1 ↗
- Available as
- Web app at app.tiden.ai plus the tiden command-line tool for macOS, Linux and Windows (Homebrew, a shell installer or PowerShell); a separate MCP server binary is also available. · Works beside Claude Code, Cursor, Copilot and Codex, and connects to GitHub, Jira, Linear, Notion and Azure DevOps. Official source 1 ↗ · Official source 2 ↗ · Official source 3 ↗ Official source 1 ↗
- Primary group
- Coding & Development
What it does
Tiden is a quality platform for teams that ship code written by AI coding agents. It reads your repositories and writes down what the product is supposed to do as versioned specs, links each spec to the tests that prove it, and blocks a coding-agent session or merge until every promise is covered, so reviewers see what was asked for and what was actually proven.
Official source 1 ↗ · Official source 2 ↗Features
- Product map of specs. Tiden reads your code and writes down each spec it finds, grouped by product component, and marks the ones no test proves. Official source 1 ↗
- Intent capture for agent sessions. Hooks for supported coding agents record each session as a working contract of promises; the session cannot close while a promise is still open, and the capture is distilled into a reviewable branch. Official source 1 ↗ · Official source 2 ↗
- Specs that follow the code. On every merge, including ones that skip Tiden, it drafts the spec update; agents propose changes on generated branches that a human reviews and merges. Official source 1 ↗ · Official source 2 ↗
- Quality gate per release. A go/no-go verdict computed from specs, tests, executions, component risk and production issues, for main, a release or a branch merge. Official source 1 ↗
- Built-in error tracking. Runtime SDKs for browser JavaScript, PHP and Laravel, Go and Python send errors to Tiden, where they are grouped into issues and traced back to the release; your agent can then fix them and add the missing test. Official source 1 ↗ · Official source 2 ↗
Pricing & free limits
Team
$199per product per monthAny number of products and repositories, 100 verified changes per product per month, then $2.00 per extra change ($1.50 up to 1,000, $1.00 after); impact analysis, SAML SSO, evidence kept 12 months. 14-day free trial. Official source 1 ↗
Enterprise
Customcontact salesEverything in Team plus telemetry at any volume, evidence kept to your policy, SCIM provisioning and self-hosted deployment as a paid add-on. Official source 1 ↗
Billing details
Billing counts verified changes: a pull request that merges with a passing quality gate bills once, however many runs it took; retries, failed changes and bot commits are free. Official source 1 ↗
Telemetry above the included amount is billed extra: error events at $0.50 per 1,000 (up to $200 per product per month) and test results at $0.10 per 1,000 (up to $400). Official source 1 ↗
Annual billing lowers product fees by 20%, but extra changes and telemetry are still billed monthly. Billing starts on day 15 of the trial if you keep your plan. Official source 1 ↗
Subscriptions renew automatically and fees are non-refundable; if you cancel early you keep access to the end of the paid term. Official source 1 ↗
Free access & limits
Free access and its limits were not established by the checked official sources.
Best for & limitations
Engineering teams that merge agent-written pull requests every day and want proof that each change does what was asked, not just that tests passed. Official source 1 ↗
Reviewing a branch by what was promised and what proves it, while code review itself stays with your human reviewer. Official source 1 ↗
- No free plan. After the 14-day trial you need a paid plan, starting at $49 a month for a single product. Official source 1 ↗
- Starter caps are hard limits. Starter covers 1 product, 3 repositories and 25 verified changes a month; past them Tiden asks you to move to Team rather than billing extra. Official source 1 ↗
- Agents need your own LLM credential. Tiden agents run on an LLM provider credential you add in workspace settings. Official source 1 ↗ · Official source 2 ↗
- Some areas are placeholders. Reports, analytics and execution can appear in the navigation but have no production workflows yet. Official source 1 ↗
- Claude Code auto mode can block the hooks. In Claude Code auto mode the classifier can deny tiden commands and break the intent loop, so setup adds allow rules to your Claude Code settings. Official source 1 ↗
Similar tools
Tools like Tiden
Published tools that share its categories.
ColdteaAn agentic development environment spanning code, release testing, and monitoring.
Visit 
LangfuseOpen-source tracing, prompt management and evaluations for LLM applications and agents.
Visit 
LatitudeObserve AI agent traces, discover recurring failures and dispatch coding agents to investigate fixes.
Visit 
SpecreelTurn Playwright traces or a pasted URL into narrated product demos that re-check themselves as tests.
Visit 
Together AICloud platform to run, fine-tune and serve open-source AI models through an OpenAI-compatible API.
Visit 
OctriTurns one OpenAPI spec into AI-drafted API docs, SDKs in ten languages, an MCP server and production monitoring.
Visit