70 pre-built scenarios

Test Case Library

Browse, filter, and select from curated test cases for evaluating AI systems across all dimensions.

Sign in

Access your evaluation projects.

or

Forgot your password?

Don't have an account? Create one

Create account

Start evaluating your AI systems.

or skip the password

Already have an account? Sign in

Reset password

Enter your email and we'll send you a reset link.

Back to sign in

Choose a new password

Enter and confirm your new password below.

Evaluation Builder

Define your system, select criteria, choose test cases, and run your evaluation.

1
System
2
Criteria
3
Test Cases
4
Evaluate
5
Results

Define Your System

Select Evaluation Criteria

These five dimensions define what "good" looks like for your AI system. We've pre-set the weights based on your system type - higher weight means that dimension counts more toward your overall score.

Hover the ⓘ icon next to each criterion to learn what it measures and when you might want to adjust its weight.

Select Test Cases

We've suggested test cases based on your system type. Select the ones you want to include, or add your own.

Run Evaluation

For each test case, paste the actual system output and score the result.

0 / 0 scored

Your Projects

+ New Evaluation
EU AI Act

EU AI Act Compliance Audit

Pre-configured evaluation template with all high-risk test cases mapped to EU AI Act obligations. Produces structured test evidence to support the testing and accuracy parts of your Articles 9-15 technical documentation.

Includes 54+ high-risk test cases across all 5 evaluation dimensions

Back to Dashboard

Compare Evaluations

Session Activity

Your wizard activity in this tab. This log stays in your browser and clears when you refresh or close the page. See our Privacy Policy for the site analytics we do collect.

Blog

Insights on AI evaluation

Practical guides, frameworks, and best practices for testing AI systems before production.

Views expressed in these articles reflect the EvalSpec team's experience and research. They do not constitute professional, legal, or regulatory advice.

← Back to all posts

The EU AI Act Delay Is Now Official. Here's What Changes and What Doesn't

For months, the question hanging over every EU AI Act compliance plan was whether the proposed delay to high-risk obligations would actually happen. It has. The European Parliament and Council have now signed off on the AI Act simplification package, and the high-risk deadlines are officially pushed back. If your team quietly stopped worrying about August 2026, it's worth checking exactly what moved and what didn't, because not everything did.

What's been delayed

The headline obligations under Annex III, covering AI used in recruitment, credit scoring, law enforcement, education and border control, now need to comply by 2 December 2027, not 2 August 2026. AI embedded in regulated products under Annex I, think medical devices, machinery and vehicles, moves from August 2027 to 2 August 2028.

That's real breathing room. Sixteen extra months to build the risk management system, technical documentation, data governance and conformity assessment processes that Article 16 and Article 17 require of high-risk system providers.

What hasn't moved

Article 50 transparency obligations are still due on 2 August 2026. If your product involves a chatbot, generates synthetic content, or produces deepfakes, the disclosure requirements land on schedule. Watermarking gets a modest four-month grace period on existing systems, not the wholesale reprieve some teams assumed. Bias detection powers have also been extended to cover all AI systems, not just those classed as high-risk, which quietly raises the stakes for anyone who thought they were out of scope.

The risk here isn't that teams do nothing. It's that they treat "delayed" as "cancelled" and lose the momentum they'd built.

Where the UK sits

The UK still has no standalone AI Act, and as of mid-2026 none is before Parliament. Regulation continues through existing bodies: the ICO on data protection, Ofcom under the Online Safety Act, and sector regulators applying general principles rather than a unified risk framework. It's a lighter-touch, innovation-first posture, deliberately different from Brussels.

But that doesn't mean UK teams are exempt. The AI Act's extraterritorial reach hasn't changed. If your AI system touches EU users or customers, the Act still applies to that activity, delay or no delay. UK businesses assuming distance from Brussels equals distance from the Act are making the same mistake that predates this whole omnibus process.

The practical takeaway

Use the extra time, don't waste it. The delay buys room to build proper testing, validation and monitoring infrastructure for high-risk classification, rather than a reason to shelve it. Keep transparency and watermarking work on the original August timeline. And if you're a UK team with any EU-facing AI product, map your exposure now rather than waiting for a UK equivalent that, on current form, isn't coming any time soon.

If you're mapping AI evaluation evidence against specific Act articles ahead of these deadlines, whichever ones apply to you, EvalSpec is built for exactly that.

Try EvalSpec free - evaluate your AI system across all 5 dimensions. No code required.

Start your free evaluation

Testing an AI system yourself?

Get the 70 test cases behind this framework, indexed by dimension and difficulty, or run a free evaluation with your own AI system.

The information in this article is provided for general guidance only. EvalSpec is a diagnostic evaluation tool and does not provide legal advice, regulatory certification, or compliance guarantees. For legal or regulatory questions, consult a qualified professional.

404

Page not found

The page you're looking for doesn't exist.

Back to home